WO2021042856A1 - Method and device for determining lane centerline - Google Patents

Method and device for determining lane centerline Download PDF

Info

Publication number
WO2021042856A1
WO2021042856A1 PCT/CN2020/100046 CN2020100046W WO2021042856A1 WO 2021042856 A1 WO2021042856 A1 WO 2021042856A1 CN 2020100046 W CN2020100046 W CN 2020100046W WO 2021042856 A1 WO2021042856 A1 WO 2021042856A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
lane
center point
equation
intercept
Prior art date
Application number
PCT/CN2020/100046
Other languages
French (fr)
Chinese (zh)
Inventor
熊健晖
丁洁云
陶永祥
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2021042856A1 publication Critical patent/WO2021042856A1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0015—Planning or execution of driving tasks specially adapted for safety
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]

Definitions

  • This application relates to the field of automatic driving technology, and in particular to a method and device for determining the centerline of a lane.
  • the automatic driving system on the vehicle usually needs to identify the center line of the lane from the road environment around the vehicle to determine the driving lane around the vehicle, so that appropriate behavior decisions can be made to control the vehicle Drive safely.
  • the existing solution is to select the vehicle with the closest distance in front of the current vehicle as the tracking vehicle, and generate the trajectory of the tracking vehicle, so as to control the current vehicle to follow Drive on this driving track.
  • this solution is highly dependent on the existence and driving behavior of the tracking vehicle ahead.
  • the solution will not be effective, or when the tracking vehicle makes unconventional driving behaviors, For example, when the tracking vehicle is suddenly inserted into the lanes on both sides, if the current vehicle is still driving along the track of the tracking vehicle, that is, performing the same lane change operation to force the tracking vehicle to follow the tracking vehicle, it will most likely cause interference with other vehicles. Conflicting driving behaviors may bring driving risks.
  • the embodiments of the present application provide a method and device for determining the centerline of a lane, which are used to accurately determine the centerline of a lane so as to control the vehicle to drive safely.
  • the present application provides a lane line determination method, which includes: when determining the lane center line of the road where the target vehicle is located, first, the surrounding vehicles in the preset area around the target vehicle can be determined, as shown in Figure 3 As shown, the rectangle in the thick frame in Figure 3 represents the target vehicle, and the dashed frame represents the preset area centered on the location of the target vehicle. Then, all vehicles in the dashed frame except the target vehicle can be determined as the vehicles around the target vehicle .
  • the white box in the figure represents the target vehicle, and all white points on the lane around the white box indicate that the moving trajectory point of each surrounding vehicle follows the driving of the surrounding vehicle And constitute the set of driving trajectory points.
  • the position information of each driving trajectory point can be represented by the coordinates of the driving trajectory point.
  • each driving trajectory point in sequence by traversing each driving trajectory point in sequence, according to the position information (such as coordinate information) of every two driving trajectory points that are adjacent in time and belong to the same vehicle, according to the principle of determining a straight line between the two points , Respectively determine the corresponding multiple lines and the equation parameters corresponding to each line. Furthermore, the target equation parameters can be determined according to the determined equation parameters corresponding to each straight line; finally, the lane centerline can be accurately determined according to the determined target equation parameters.
  • position information such as coordinate information
  • the embodiment of the present application can use the linear equation parameters corresponding to the driving trajectory points of these surrounding vehicles to further Fitting the equation parameters of the lane centerline of the road where the target vehicle is located is used to accurately determine the lane centerline of the road where the target vehicle is located, thereby effectively improving the safety of vehicle driving and avoiding driving risks.
  • the first way is that the equation parameters corresponding to each straight line include the slope.
  • the target equation parameter includes a target slope
  • determining the target equation parameter according to the equation parameter corresponding to each straight line includes: determining the average value of the slope included in the equation parameter corresponding to each straight line as the target slope. Since the lane lines in the current urban roads are mostly parallel and continuous straight lines, the slope values corresponding to the center lines of the lanes are basically the same. Therefore, the accuracy of the target slope determined by this method is relatively high.
  • determining the lane centerline according to the target equation parameters includes: obtaining the location information of the target vehicle; determining the lane centerline of the lane where the target vehicle is located according to the target slope and the location information of the target vehicle. Because when the target equation parameters only include the target slope, not the target intercept (or the target intercept is 0), it means that the corresponding surrounding vehicles are located directly in front and behind the target vehicle, and the center of the lane where the target vehicle is located. The lines are consistent. In this way, after the target slope is calculated, it only needs to be fused with the position information of the target vehicle to determine the lane centerline. This not only simplifies the calculation process, but also improves the accuracy of determining the lane centerline. .
  • the method further includes: obtaining the lane centerline of the adjacent lane of the target vehicle according to the lane centerline of the lane where the target vehicle is located and the preset lane width.
  • the preset width range that is, a certain value between 2.8 meters and 3.5 meters
  • the preset width range should be satisfied according to the preset distance between the lane centerlines.
  • the target equation parameters include target slope and target intercept
  • determining the target equation parameters according to the equation parameters corresponding to each straight line includes: determining the average value of the slope included in the equation parameters corresponding to each straight line as the target slope; corresponding to each straight line
  • the parameters of the equation include the intercept to cluster to obtain the target intercept.
  • determining the lane center line according to the target equation parameters includes: taking a straight line determined according to the target slope and the target intercept as the lane center line.
  • the average value of each slope included in the equation parameter corresponding to each straight line is taken as the target slope through the above method, and the target is obtained by clustering each intercept included in the equation parameter corresponding to each straight line.
  • Intercept to determine the centerline of the lane It is not affected by the clarity of the lane line on the road, and at the same time, it does not need to rely on high-precision maps and high-precision positioning to accurately determine the centerline of the lane, thereby reducing the automatic driving system’s need for high-precision positioning and high-precision Dependence, which in turn reduces the cost of the automated driving system.
  • clustering the intercepts included in the equation parameters corresponding to each straight line to obtain the target intercept includes: selecting one of the unmarked intercepts in the equation parameters corresponding to each straight line as the initial center Point; determine from the equation parameters corresponding to each straight line that the absolute value of the difference from the initial center point is less than or equal to the intercept of the first threshold, and the absolute value of the difference from the initial center point is less than or equal to the first threshold The intercept and the initial center point are marked; the sum of the difference between each intercept in the equation parameters corresponding to the initial center point and each straight line is determined as the moving distance, and the initial center point and the moving distance And as the new initial center point, perform the above steps to iterate until the moving distance is less than or equal to the second threshold, and when the moving distance is less than or equal to the second threshold, the corresponding initial center point is added as a candidate center point to the candidate center point Set; perform the above steps again to iterate to obtain a new candidate center point; in the iterative process, if the difference
  • determining the lane centerline according to the target equation parameters includes: obtaining the last final equation parameter used to determine the lane centerline, and according to the last final equation parameter used to determine the lane centerline and this determination Determine the final equation parameters of this time, and then determine the lane center line according to the final equation parameters of this time.
  • the value of the equation parameter corresponding to each time can be stabilized, thereby stabilizing the value of the target vehicle every time.
  • the driving route will not change too frequently, which will affect the safety of the vehicle.
  • the method further includes: determining the lane centerlines whose widths of two adjacent lane centerlines among the plurality of lane centerlines are within a preset width range as The center line of the target lane. In this way, the width of the centerlines of the two adjacent lanes of the multiple lane centerlines can be within the preset width range, so that it can meet the requirements of urban road planning, and ensure that the determined lane centerline results are correct of.
  • the present application also provides a device for determining the centerline of a lane, the device comprising: an acquiring unit configured to acquire driving track points of a vehicle located around the target vehicle, where the driving track points represent position information during the driving of the vehicle; The first determining unit is used to determine the corresponding straight line according to every two driving trajectory points that are adjacent in time and belong to the same vehicle; the second determining unit is used to determine the target equation parameter according to the equation parameter corresponding to each straight line ; The third determining unit is used to determine the lane centerline according to the target equation parameters.
  • the equation parameter corresponding to each straight line includes a slope
  • the target equation parameter includes a target slope
  • the second determining unit is specifically configured to determine the average value of each slope in the equation parameter as the target slope.
  • the third determining unit includes: a location information acquiring subunit for acquiring location information of the target vehicle; a third determining subunit for determining where the target vehicle is based on the target slope and location information of the target vehicle The lane centerline of the lane.
  • the device further includes: an obtaining unit configured to obtain the lane center line of the adjacent lane of the target vehicle lane according to the lane center line of the target vehicle lane and the preset lane width.
  • the equation parameters corresponding to each straight line include slope and intercept
  • the target equation parameters include target slope and target intercept
  • the second determining unit includes: a target slope determining subunit, which is used to combine each straight line The mean value of the slope included in the corresponding equation parameter is determined as the target slope; the target intercept obtaining subunit is used to cluster the intercept included in the equation parameter corresponding to each straight line to obtain the target intercept;
  • the third determining unit is specifically configured to: use the straight line determined according to the target slope and the target intercept as the center line of the lane.
  • the target intercept acquisition subunit includes: a selection subunit for selecting one of the unmarked intercepts in the equation parameters corresponding to each straight line as the initial center point; and a marking subunit for Determine from the equation parameters corresponding to each straight line that the absolute value of the difference from the initial center point is less than or equal to the first threshold, and the absolute value of the difference from the initial center point is less than or equal to the first threshold Mark the intercept and the initial center point; the first iterative sub-unit is used to determine the sum of the difference between each intercept in the equation parameters corresponding to the initial center point and each straight line as the moving distance, and set the initial The sum of the center point and the moving distance is used as the new initial center point.
  • the corresponding initial center point is used as a candidate
  • the center point is added to the candidate center point set; the second iteration subunit is used to perform the above steps again to iterate to obtain a new candidate center point; the center point determination subunit is used in the iterative process, if the new candidate center
  • the difference between the point and the candidate center point in the candidate center set is greater than or equal to the third threshold, then the new candidate center point is added to the candidate center point set, otherwise the difference between the candidate center set and the new candidate center point is discarded
  • the candidate center point whose value is less than the third threshold is added to the candidate center point set; the target intercept determination subunit is used to determine the candidate center point in the candidate center point set as the target intercept.
  • the third determining unit includes: an equation parameter determination subunit, which is used to obtain the last final equation parameter used to determine the lane centerline, and according to the last final equation parameter used to determine the lane centerline And the target equation parameters determined this time, determine the final equation parameters this time; the lane centerline determination subunit is used to determine the lane centerline according to the final equation parameters this time.
  • the device further includes: a fourth determining unit configured to set the width of the centerlines of two adjacent lanes among the plurality of lane centerlines within the preset width range The centerline of the inner lane is determined as the centerline of the target lane.
  • the present application also provides a lane centerline determination device, the lane centerline determination device includes: a memory, a processor,
  • the memory is used to store instructions; the processor is used to execute the instructions in the memory and execute the above methods.
  • the present application also provides a computer-readable storage medium, including instructions, which when run on a computer, cause the computer to execute the above method.
  • the embodiment of the present application When determining the centerline of the lane of the road where the target vehicle is located, the embodiment of the present application first obtains the driving track points representing the position information of the vehicles located around the target vehicle during the driving process, and then, for every two adjacent and adjacent in time Data processing is performed on the driving trajectory points belonging to the same vehicle to determine the corresponding straight lines respectively. Then, the target equation parameters can be determined according to the equation parameters corresponding to each straight line determined, and finally, the target equation parameters are determined according to the target equation parameters.
  • the center line of the lane It can be seen that since the vehicle usually travels along the center line of the lane, the embodiment of the present application calculates the linear equation parameters determined by every two adjacent trajectory points of the vehicle around the target vehicle, and can use the driving of these surrounding vehicles.
  • the linear equation parameters corresponding to the trajectory points are further fitted to the equation parameters of the lane center line of the road where the target vehicle is located, so as to accurately determine the lane center line of the road where the target vehicle is located, so as to control the target vehicle to drive safely along the center line of the lane Therefore, compared with the current method of controlling the target vehicle to drive along the trajectory of the vehicle ahead, it can effectively improve the safety of the vehicle and avoid driving risks.
  • FIG. 1 is an example diagram of a hardware scenario provided by an embodiment of the application
  • FIG. 2 is a flowchart of a method for determining the centerline of a lane according to an embodiment of the application
  • FIG. 3 is a schematic diagram of surrounding vehicles located in a preset area centered on the location of the target vehicle according to an embodiment of the application;
  • FIG. 4 is a schematic diagram of the driving track points of vehicles around the target vehicle provided by an embodiment of the application.
  • Fig. 6 is a structural block diagram of a device for determining a lane center line provided by an embodiment of the application
  • Fig. 7 is a schematic structural diagram of a lane centerline determination device provided by an embodiment of the application.
  • the embodiments of the present application provide a method and device for determining the centerline of a lane, which are used to accurately determine the centerline of the lane, so as to improve the safety of vehicle driving.
  • the present application provides a method for determining the centerline of a lane.
  • the driving track points representing the position information of the vehicles located around the target vehicle during the driving process are obtained, and then, for every two adjacent vehicles in time.
  • the driving track points belonging to the same vehicle are subjected to data processing to determine the corresponding straight lines respectively.
  • the target equation parameters can be determined according to the equation parameters corresponding to each straight line determined, and finally, according to the target equation parameters, Accurately determine the center line of the lane.
  • the scenario includes a sensor 101 and a processor 102, where the processor 102 may be a vehicle The vehicle controller, or a terminal, computer, server and other devices with data processing capabilities that have a communication connection with the vehicle controller.
  • the sensor 101 can be a laser radar, millimeter wave radar, plane camera and other equipment installed on the vehicle.
  • the sensor 101 can be used to obtain the position and speed information of the current vehicle surrounding the vehicle.
  • the millimeter wave radar can be used to send millimeters to the surrounding vehicles.
  • the processor 102 when it receives the surrounding vehicle information sent by the sensor 101 After real-time position and speed, the equation parameters of the centerline of the lane of the road where the current vehicle is located can be fitted to the equation parameters of the lane centerline of the road where the current vehicle is located according to the linear equation parameters determined by each surrounding vehicle at different positions at two adjacent moments, so as to accurately determine where the current vehicle is located The centerline of the lane of the road.
  • the senor 101 and the processor 102 can be integrated into the vehicle or a terminal, computer, server and other devices with data processing capabilities that have a communication connection with the vehicle, that is, the vehicle or the vehicle can be used Devices with data processing capabilities such as terminals, computers, and servers having a communication connection relationship implement the above-mentioned functions of the sensor 101 and the processor 102 at the same time.
  • a server that has a communication connection with a vehicle when it obtains the real-time position and speed of the surrounding vehicles of the vehicle, it can determine the linear equation parameters according to the different positions of each surrounding vehicle at two adjacent moments. The equation parameters of the lane centerline of the road where the current vehicle is located are fitted to accurately determine the lane centerline of the road where the current vehicle is located.
  • a roadside device (such as a roadside unit) can also be used to replace the sensor 101 for data communication with the processor 102 through the Internet of Vehicles.
  • roadside units such as roadside units installed at traffic lights
  • the processor 102 fits the equation parameters of the lane centerline of the road where the current vehicle is located according to the position and speed of the surrounding vehicles, so as to accurately determine the lane centerline where the current vehicle is located, thereby solving the current inability to accurately determine the lane centerline. The problem.
  • a roadside device (such as a roadside unit) can also be used to replace the sensor 101 and the processor 102 at the same time, so as to realize the above-mentioned functions of both at the same time.
  • the real-time position and driving speed of vehicles around the current vehicle can be obtained through roadside equipment such as a roadside unit installed on the roadside, and then the roadside unit can obtain the position and speed of each surrounding vehicle according to the acquired position and speed of each surrounding vehicle.
  • the equation parameters of the lane centerline of the road where the current vehicle is located are fitted to accurately determine the centerline of the lane where the current vehicle is located, thereby solving the problem that the current lane centerline cannot be accurately determined.
  • an embodiment of the present application provides a method for determining the centerline of a lane, which is introduced below.
  • FIG. 2 shows a flowchart of a method for determining a lane centerline provided by an embodiment of the present application.
  • the method may be executed by the foregoing hardware structure, and may specifically include the following steps:
  • S201 Acquire driving trajectory points of vehicles located around the target vehicle, where the driving trajectory points represent position information during the driving of the vehicle.
  • any vehicle that uses this embodiment to determine the lane centerline of the road on which it is located is defined as the target vehicle.
  • the driving trajectory point refers to the position information during the driving of the vehicle, and the embodiment of the present application does not limit the number of the acquired driving trajectory points. For example, multiple driving trajectory points can be acquired or multiple driving trajectory points can be acquired. A collection of driving trajectory points, etc.
  • the vehicles around the target vehicle in the embodiment of the present application refer to the vehicles located in the preset area centered on the location of the target vehicle, which can be one or multiple vehicles, as shown in FIG.
  • the rectangle in the wire frame represents the target vehicle
  • the dashed frame represents the preset area centered on the location of the target vehicle
  • the vehicles except the target vehicle in the dashed frame are vehicles around the target vehicle.
  • the value range of the preset area can be set according to the implementation situation, and the embodiment of this application does not limit this. For example, it can be 100 meters in front, 50 meters behind, and left side centered on the location of the target vehicle.
  • the range of 30 meters and 30 meters on the right is set as the preset area, etc.
  • the preset speed refers to the critical value used to distinguish vehicles around the target vehicle in the preset area from non-surrounding vehicles.
  • the speed of a vehicle in the preset area is greater than or equal to the critical value, it can be As a vehicle around the target vehicle, on the contrary, it cannot be regarded as a vehicle around the target vehicle.
  • the value of the preset speed can be set according to actual conditions, and the embodiment of the present application does not limit this.
  • the preset speed can be set to 3 km/h.
  • the movement track point of the same designated position of each surrounding vehicle can be used as the driving track point of the corresponding surrounding vehicle.
  • the movement track point of the center position of each surrounding vehicle can be used as the corresponding
  • the driving trajectory points of surrounding vehicles, as shown in Fig. 3, the "black dot" corresponding to the center position of a surrounding vehicle shown in the figure can be used as a moving trajectory point of the surrounding vehicle.
  • a number of "black dots" can be obtained, and then the position information of these black dots can be used to indicate the position information of the surrounding vehicles during the driving process, and they can be used as the driving trajectory points of the surrounding vehicles, as shown in Figure 4, the white color in the figure
  • the box represents the target vehicle, and all the white points on the lane line around the white box represent the set of driving trajectory points formed by the moving trajectory points of each surrounding vehicle along with the driving of the surrounding vehicles.
  • the position information of each driving trajectory point can be represented by the coordinates of the driving trajectory point.
  • existing or future location acquisition methods can be used to acquire the location information of multiple driving trajectory points of surrounding vehicles.
  • the sensor 101 shown in FIG. 1 can be used, such as the lidar, Planar cameras, millimeter-wave radars, etc. transmit and receive corresponding light waves to calculate the position information of multiple driving trajectory points of surrounding vehicles.
  • the specific calculation method is consistent with the existing method and will not be repeated here.
  • S202 Determine a corresponding straight line according to every two driving track points that are adjacent in time and belong to the same vehicle.
  • data processing may be performed on the obtained driving trajectory points to determine the corresponding straight line according to the processing result.
  • the acquired driving track points represent the position information of the vehicles around the target vehicle during the driving process, that is, they represent the coordinate information of the surrounding vehicles during the driving process.
  • each vehicle corresponds to multiple driving trajectory points, and then each driving trajectory point can be traversed in sequence, and according to the two driving trajectory points that are adjacent in time and belong to the same vehicle.
  • Coordinate information according to the principle of two points to determine a straight line, respectively determine the corresponding multiple straight lines and the equation parameters corresponding to each straight line.
  • the distance between two adjacent driving trajectory points belonging to the same surrounding vehicle among all the acquired driving trajectory points is greater than or equal to the preset The distance, and the specific value of the preset distance can be set according to the actual situation, which is not limited in this application.
  • the parameters of the target equation refer to the parameters of the straight line equation corresponding to the center line of the lane of the road where the target vehicle is located.
  • the equation parameters determined in step S202 above can include two implementation methods, different target equation parameters can be determined according to the values of different equation parameters.
  • the equation parameter is the slope k'
  • the target equation parameter is also a slope, and can be expressed by k
  • the equation parameters are the slope k'and intercept b'
  • the slope k'and intercept From the processing of distance b', it can be determined that the target equation parameters are also slope and intercept, and can be expressed by k and b.
  • the two specific realization processes for determining the respective target equation parameters can be found in subsequent implementations. Detailed introduction of the case.
  • equation parameters corresponding to each straight line are determined in step S203, these equation parameters can be further used to form an equation parameter set to determine the lane center line.
  • the target equation parameters can be further used to determine the lane centerline.
  • the determined target equation parameter is the slope k
  • the method for determining the centerline of the lane when determining the centerline of the lane of the road where the target vehicle is located, first obtains the driving track points representing the position information of the vehicles located around the target vehicle during the driving process, and then , And then perform data processing on every two driving trajectory points that are adjacent in time and belong to the same vehicle to determine the corresponding straight lines respectively. Then, the target equation can be determined according to the equation parameters corresponding to each straight line determined Parameters, and finally, the centerline of the lane is determined according to the target equation parameters.
  • the embodiment of the present application calculates the linear equation parameters determined by every two adjacent trajectory points of the vehicle around the target vehicle, and can use the driving of these surrounding vehicles.
  • the linear equation parameters corresponding to the trajectory points are further fitted to the equation parameters of the lane center line of the road where the target vehicle is located, so as to accurately determine the lane center line of the road where the target vehicle is located, so as to control the target vehicle to drive safely along the center line of the lane Therefore, compared with the current method of controlling the target vehicle to drive along the trajectory of the vehicle ahead, it can effectively improve the safety of the vehicle and avoid driving risks.
  • this embodiment may also perform the following steps A1-A2:
  • Step A1 Obtain the last final equation parameters used to determine the lane centerline, and determine the final equation parameters this time according to the last final equation parameters used to determine the lane centerline and the target equation parameters determined this time.
  • the final equation parameters of this time can be determined according to the final equation parameters used to determine the centerline of the lane the last time and the target equation parameters determined this time.
  • a first-order digital filtering method can be used to determine the final equation parameters each time, so that the final equation parameters each time are more stable.
  • the last equation parameter of the lane centerline determined last time and the target equation parameter of the lane centerline determined this time can be used as the two input values of the filter respectively, and then the final equation parameters of this time can be used as the output of the filter.
  • the specific calculation formula is as follows:
  • y(n) represents the final equation parameter of this time
  • q is the filter coefficient
  • x(n) represents the target equation parameter of the lane centerline determined this time
  • y(n-1) represents the most recently determined lane centerline The final equation parameters.
  • the final equation parameter type y(n) this time and the target equation parameter x(n) type of the lane centerline determined this time and the final equation of the lane centerline determined last time The parameter type y(n-1) is consistent. For example, if the final equation parameter y(n) determined this time is the slope, the input used in filtering is: the slope included in the target equation parameter of the lane centerline determined this time and the lane centerline determined last time In the same way, if the final equation parameter y(n) is determined as the intercept, the input used in filtering is: the target equation parameter of the lane center line determined this time The intercept included and the intercept included in the final equation parameters of the last determined lane centerline.
  • Step A2 Determine the lane centerline according to the final equation parameters this time.
  • the slope (or slope and intercept) contained in the final equation parameters of this time can be used to determine the lane centerline.
  • the width of the centerlines of the two adjacent lanes among the multiple lane centerlines should be within the preset width range, so that it can meet the requirements of urban road planning ,
  • the preset width range can be set according to the characteristics of urban roads, for example, it can be set between 2.8 meters and 3.5 meters.
  • the value of the equation parameter corresponding to each time can be stabilized, thereby stabilizing the value of the target vehicle every time.
  • the driving route will not change too frequently, which will affect the safety of the vehicle.
  • the determination result can also be combined with the existing two methods of determining the lane line (using high-precision The map and high-precision positioning method, the method of detecting the lane line in the visual image) are compared and analyzed to obtain a more accurate lane centerline.
  • the three determination results can be averaged, and the calculation result can be used as the final determination result, or the weights set for the three determination results in advance can be used for weighting calculation to calculate the final determination result, etc. .
  • this embodiment will introduce two specific implementation processes of "determining the target equation parameter according to the equation parameter corresponding to each straight line" in step S203.
  • the equation parameters determined in step S202 above can include two implementation methods (the first can be slope, and the second can be slope and intercept), and the values can be selected according to different equation parameters. Different target equation parameters are determined, but because the lane lines on urban roads are mostly parallel and continuous straight lines in most cases, for example, the lane lines on highways and urban elevated roads are parallel and continuous straight lines.
  • the slope values corresponding to the center line of the lane are basically the same. Therefore, the slope processing methods in the above two implementations are the same.
  • the processing method of the intercept can be referred to the following step (2):
  • step S203 may include: The mean value of the slope is determined as the target slope.
  • the target equation parameter when the equation parameter corresponding to each straight line determined according to the driving track point in step S202 includes the slope k′, the target equation parameter must also include the target slope, and can be represented by k. It should be noted that, because the lane lines on urban roads are mostly parallel and continuous straight lines in most cases, the slope values corresponding to the center lines of the lanes are basically the same. Therefore, when calculating the target slope k, you can The slope k′ included in the equation parameters corresponding to each straight line is averaged, and the obtained average value is used as the value of the target slope k.
  • step S204 may include: obtaining the location information of the target vehicle; The slope and the location information of the target vehicle determine the lane centerline of the lane where the target vehicle is located.
  • the target equation parameters only include the target slope and not the target intercept (or the target intercept is 0)
  • the corresponding surrounding vehicles are located directly in front of and directly behind the target vehicle, and are in the same lane as the target vehicle.
  • the lane centerline of the target vehicle is consistent, and after obtaining the location information (such as coordinate information) of the target vehicle, the lane centerline of the lane where the target vehicle is located can be determined according to the target slope and the location information of the target vehicle.
  • the lane centerline of the adjacent lane of the lane where the target vehicle is located can also be obtained according to the lane centerline of the lane where the target vehicle is located and the preset lane width.
  • the width of the center lines of two adjacent lanes should be within a preset width range, and the preset width range is generally set to 2.8 meters to 3.5 meters, that is, the preset lane width is generally between 2.8 meters and 3.5 meters. Therefore, after determining the lane center line of the lane where the target vehicle is located, it can be determined that the lane is adjacent according to the preset lane width The lane centerline of the lane, and the distance between the lane centerlines of the two lanes meets a preset width range (that is, a certain value between 2.8 meters and 3.5 meters).
  • step S203 may include: The average value of the slope included in the equation parameters corresponding to the straight line is determined as the target slope; the intercept included in the equation parameters corresponding to each straight line is clustered to obtain the target intercept, and step S204 may include: determining according to the target slope and the target intercept The straight line as the center line of the lane.
  • the target equation parameter when the equation parameter corresponding to each straight line determined according to the driving track point in step S202 includes the intercept b′, the target equation parameter also includes the target intercept, and can be represented by b. It should be noted that since vehicles usually drive along the centerline of the lane, no matter which lane the vehicles around the target vehicle drive in, they basically drive along the centerline of the lane. The intercept values in the linear equation parameters determined by the trajectory points of the vehicles driving on the centerline of the same lane should be similar, and then the existing or future clustering algorithms can be used to determine the equation parameters corresponding to each straight line.
  • Each intercept b' is clustered, for example, the hill climbing algorithm (Mean shift algorithm) based on kernel density estimation can be used to cluster the intercept b'included in the equation parameters corresponding to each straight line, and cluster according to the obtained clustering
  • the value of the target intercept b is determined, that is, after clustering, several intercepts b'that can be used as the center points of the cluster are obtained, which is equivalent to obtaining the equation parameters corresponding to the center lines of several lanes including the target intercept
  • the value of the distance b, and further, the value of the determined target intercept b and the value of the target slope k determined in step (1) may be used to determine the corresponding straight line as the center line of the lane.
  • the specific clustering process of clustering the intercept b′ included in the equation parameter corresponding to each straight line may include the following steps B1-B6:
  • Step B1 Select one of the unmarked intercepts in the equation parameters corresponding to each straight line as the initial center point.
  • the intercepts b′ included in the equation parameters corresponding to each straight line firstly, from the equation parameters corresponding to each straight line, all the unlabeled intercepts b′ choose an intercept b'as the center point of the first clustering, that is, the initial center point, and define it as center.
  • Step B2 Determine from the equation parameters corresponding to each straight line that the absolute value of the difference from the initial center point is less than or equal to the first threshold, and the absolute value of the difference from the initial center point is less than or equal to the first threshold. The intercept of the threshold and the initial center point are marked.
  • the intercept After selecting the intercept as the initial center point center through step B1, in the equation parameters corresponding to each straight line, using the initial center point as the center of the circle, find the difference from the intercepts distributed around it
  • the absolute value of is less than or equal to the intercept of the first threshold, these intercepts are attributed to the initial center point to form a cluster centered on the initial center point, and the intercepts found in the cluster are corresponding to the initial center point
  • the intercepts are marked to indicate that these intercepts are those that have been clustered.
  • the value of the first threshold can be set according to actual conditions, which is not limited in this application. For example, the first threshold can be set to 1.0.
  • Step B3 Determine the sum of the difference between each intercept in the equation parameters corresponding to the initial center point and each straight line as the moving distance, and use the sum of the initial center point and the moving distance as the new initial center point. Steps are to iterate until the moving distance is less than or equal to the second threshold, and the initial center point corresponding to when the moving distance is less than or equal to the second threshold is added as a candidate center point to the candidate center point set.
  • the sum of the difference between the initial center point center determined in step B1 and each intercept in the equation parameters corresponding to each straight line can be calculated, and this value can be used as the moving distance, which is defined as shift .
  • the iterative calculation is stopped, and the corresponding initial center The point center 1 is added to the candidate center point set as a candidate center point.
  • the value of the second threshold can be set according to actual conditions, which is not limited in this application. For example, the second threshold can be set to 0.1.
  • Step B4 Perform the above steps again to iterate to obtain a new candidate center point.
  • step B3 After obtaining the candidate center point center 1 in the candidate center point set through step B3, the above step B3 can be repeated to iterate again to obtain a new candidate center point and add it to the candidate center point set.
  • Step B5 In the iterative process, if the difference between the new candidate center point and the candidate center points in the candidate center set is greater than or equal to the third threshold, add the new candidate center point to the candidate center point set. Otherwise, the candidate center point whose difference between the candidate center point and the new candidate center point is less than the third threshold is discarded, and the new candidate center point is added to the candidate center point set.
  • the new candidate can be The center point is added to the candidate center point set as a new cluster center point. Otherwise, if the difference between the new candidate center point and some existing candidate center points in the candidate center set is less than the third threshold, Then the new candidate center point can be merged with these existing candidate center points in the candidate center set, that is, the candidate center point whose difference between the candidate center set and the new candidate center point is less than the third threshold is discarded At the same time, the new candidate center point is added to the candidate center point set as a new cluster center point.
  • the value of the third threshold can be set according to actual conditions, which is not limited in this application. For example, the third threshold can be set to 3.0.
  • Step B6 Determine the candidate center point in the set of candidate center points as the target intercept.
  • each candidate center point can be determined as the value of the target intercept to determine the corresponding lane center line.
  • the centerlines of two adjacent lanes among the centerlines of the multiple lanes are within the preset width range, that is, multiple lanes can be combined.
  • the centerline the centerline of the two adjacent lanes whose width is within the preset width range is determined as the target lane centerline, and the preset width range can be set according to the characteristics of urban roads, for example, it can be set as Between 2.8 meters and 3.5 meters. If it is calculated that the width of the centerline of two adjacent lanes is not within the preset width range, it indicates that the result of the determined lane centerline is incorrect.
  • FIG. 5 shows a schematic diagram of the distribution of equation parameters corresponding to each straight line provided by the embodiment of the present application.
  • the clustering calculation of each intercept can obtain the center point values after three clusters, which can be used as the value of the target intercept respectively.
  • the slopes in the lower graph of FIG. 5 are averaged, and the average value obtained is used as the value of the target slope.
  • the obtained target slope and the three target intercepts can be used to determine the three lane centerlines, and it can be seen from Figure 5 that the three peak intervals of the intercept distribution in the equation parameters corresponding to each straight line are about 3.5, so The width of the centerlines of the two adjacent lanes among the three lane centerlines is within the preset width range, which conforms to the characteristics of urban roads, thus indicating that the determination result of the lane centerline is correct.
  • each intercept b'included in the equation parameters corresponding to each straight line described in the above steps B1-B6 is not unique, and is only an example of realizing the clustering process.
  • Other clustering algorithms can be used to perform clustering calculation, which is not limited in the embodiment of the present application.
  • the average value of each slope k'included in the equation parameter corresponding to each straight line is taken as the target slope k, and the target intercept is obtained by clustering the intercept b'included in the equation parameter corresponding to each straight line.
  • the method used to determine the centerline of the lane can not be affected by the clarity of the lane line on the road. At the same time, it does not need to rely on high-precision maps and high-precision positioning to accurately determine the centerline of the lane, thereby reducing the automatic driving system The reliance on high-precision positioning and high-precision maps further reduces the cost of the automated driving system.
  • an apparatus 600 for determining a centerline of a lane provided in an embodiment of the present application.
  • the apparatus 600 may include: an acquiring unit 601, a first determining unit 602, a second determining unit 603, and a third determining unit 604.
  • the acquiring unit 601 is configured to execute S201 in the embodiment shown in FIG. 2.
  • the first determining unit 602 is configured to execute S202 in the embodiment shown in FIG. 2.
  • the second determining unit 603 is configured to execute S203 in the embodiment shown in FIG. 2.
  • the third determining unit 604 is configured to execute S204 in the embodiment shown in FIG. 2.
  • the acquiring unit 601 is configured to acquire driving track points of vehicles located around the target vehicle, where the driving track points represent position information during the driving of the vehicle;
  • the first determining unit 602 is configured to determine a corresponding straight line according to every two driving trajectory points that are adjacent in time and belong to the same vehicle;
  • the second determining unit 603 is configured to determine the target equation parameter according to the equation parameter corresponding to each straight line;
  • the third determining unit 604 is configured to determine the center line of the lane according to the target equation parameters.
  • the equation parameter corresponding to each straight line includes a slope
  • the target equation parameter includes a target slope
  • the second determining unit 603 is specifically configured to determine the average value of each slope in the equation parameter as the target slope.
  • the third determining unit 604 includes: a location information obtaining subunit, used to obtain the location information of the target vehicle; the third determining subunit, used according to the target slope and the location information of the target vehicle Determine the lane centerline of the lane where the target vehicle is located.
  • the device further includes: an obtaining unit configured to obtain the lane center lines of the adjacent lanes of the lane where the target vehicle is located according to the lane centerline of the lane where the target vehicle is located and the preset lane width.
  • the equation parameters corresponding to each straight line include slope and intercept
  • the target equation parameters include target slope and target intercept
  • the second determining unit 603 includes:
  • the target slope determination subunit is used to determine the average value of the slope included in the equation parameters corresponding to each straight line as the target slope;
  • the target intercept obtaining subunit is used to cluster the intercept included in the equation parameters corresponding to each straight line to obtain the target intercept;
  • the third determining unit 604 is specifically configured to: use a straight line determined according to the target slope and the target intercept as the center line of the lane.
  • the target intercept obtaining subunit includes:
  • the marking subunit is used to determine the intercept that the absolute value of the difference from the initial center point is less than or equal to the first threshold from the equation parameters corresponding to each straight line, and to determine the absolute value of the difference from the initial center point Mark the intercept and the initial center point that are less than or equal to the first threshold;
  • the first iterative subunit is used to determine the sum of the difference between each intercept in the equation parameters corresponding to the initial center point and each straight line as the moving distance, and the sum of the initial center point and the moving distance as the new
  • the initial center point performs the above steps to iterate until the moving distance is less than or equal to the second threshold, and when the moving distance is less than or equal to the second threshold, the corresponding initial center point is added as a candidate center point to the candidate center point set;
  • the second iteration subunit is used to perform the above steps again to iterate to obtain a new candidate center point
  • the center point determination subunit is used to add the new candidate center point to the candidate if the difference between the new candidate center point and the candidate center point in the candidate center set is greater than or equal to the third threshold in the iterative process Center point set, otherwise discard the candidate center points whose difference between the candidate center set and the new candidate center point is less than the third threshold, and add the new candidate center point to the candidate center point set;
  • the target intercept determination subunit is used to determine the candidate center point in the candidate center point set as the target intercept.
  • the third determining unit 604 includes:
  • the equation parameter determination subunit is used to obtain the last final equation parameters used to determine the lane centerline, and determine the final equation parameters this time based on the last final equation parameters used to determine the lane centerline and the target equation parameters determined this time Equation parameter
  • the lane centerline determination subunit is used to determine the lane centerline according to the final equation parameters this time.
  • the device further includes:
  • the fourth determining unit is used to determine the centerline of the lane with the centerline of the two adjacent lanes in the preset width range among the centerlines of the multiple lanes as the centerline of the target lane
  • the lane centerline determining device when determining the lane centerline of the road on which the target vehicle is located, first obtain the driving trajectory indicating the position information of the vehicle located around the target vehicle during the driving process Then, data processing is performed on every two driving trajectory points that are adjacent in time and belong to the same vehicle to determine the corresponding straight line. Then, it can be determined according to the equation parameters corresponding to each straight line determined Determine the target equation parameters, and finally, determine the lane center line according to the target equation parameters.
  • the embodiment of the present application calculates the linear equation parameters determined by every two adjacent trajectory points of the vehicle around the target vehicle, and can use the driving of these surrounding vehicles.
  • the linear equation parameters corresponding to the trajectory points are further fitted to the equation parameters of the lane center line of the road where the target vehicle is located, so as to accurately determine the lane center line of the road where the target vehicle is located, so as to control the target vehicle to drive safely along the center line of the lane Therefore, compared with the current method of controlling the target vehicle to drive along the trajectory of the vehicle ahead, it can effectively improve the safety of the vehicle and avoid driving risks.
  • an embodiment of the present application provides a lane centerline determination device 700, which includes a memory 701, a processor 702, and a communication interface 703.
  • the memory 701 is used to store instructions
  • the processor 702 is configured to execute instructions in the memory 701, and execute the above-mentioned method for determining the lane centerline applied in the embodiment shown in FIG. 2;
  • the communication interface 703 is used for communication.
  • the memory 701, the processor 702, and the communication interface 703 are connected to each other through a bus 704; the bus 704 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus Wait.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 7, but it does not mean that there is only one bus or one type of bus.
  • the processor 702 is configured to, when determining the centerline of the lane of the road where the target vehicle is located, obtain driving track points that represent the location information of the vehicles located around the target vehicle during driving, and then calculate every two Data processing is performed on the driving trajectory points that are adjacent in time and belong to the same vehicle to determine the corresponding straight lines respectively. Then, the target equation parameters can be determined according to the equation parameters corresponding to each straight line determined, and finally, according to the The target equation parameters determine the centerline of the lane.
  • the processor 702 please refer to the detailed description of S201, S202, S203, and S204 in the embodiment shown in FIG. 2, which will not be repeated here.
  • the above-mentioned memory 701 may be random-access memory (RAM), flash memory (flash), read only memory (ROM), erasable programmable read only memory (EPROM) ), electrically erasable programmable read only memory (EEPROM), register, hard disk, mobile hard disk, CD-ROM or any other form of storage medium known to those skilled in the art.
  • RAM random-access memory
  • flash flash memory
  • ROM read only memory
  • EPROM erasable programmable read only memory
  • EEPROM electrically erasable programmable read only memory
  • register hard disk, mobile hard disk, CD-ROM or any other form of storage medium known to those skilled in the art.
  • the aforementioned processor 702 may be, for example, a central processing unit (CPU), a general-purpose processor, a digital signal processor (digital signal processor, DSP), or an application specific integrated circuit.
  • CPU central processing unit
  • DSP digital signal processor
  • the processor may also be a combination of computing functions, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and so on.
  • the above-mentioned communication interface 703 may be, for example, an interface card or the like, and may be an ethernet interface or an asynchronous transfer mode (ATM) interface.
  • ATM asynchronous transfer mode
  • the embodiment of the present application also provides a computer-readable storage medium, including instructions, which when run on a computer, cause the computer to execute the above-mentioned method for determining the lane centerline.
  • the disclosed system, device, and method may be implemented in other ways.
  • the device embodiments described above are merely illustrative, for example, the division of units is only a logical business division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or integrated. To another system, or some features can be ignored, or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • service units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software business unit.
  • the integrated unit is implemented in the form of a software business unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes. .
  • the services described in the present invention can be implemented by hardware, software, firmware, or any combination thereof.
  • these services can be stored in a computer-readable medium or transmitted as one or more instructions or codes on the computer-readable medium.
  • the computer-readable medium includes a computer storage medium and a communication medium, where the communication medium includes any medium that facilitates the transfer of a computer program from one place to another.
  • the storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Automation & Control Theory (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Operations Research (AREA)
  • Evolutionary Computation (AREA)
  • Algebra (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Traffic Control Systems (AREA)

Abstract

Disclosed in embodiments of the present application are a method and a device for determining a lane centerline, applied to the field of automatic driving and used for accurately determining the lane centerline so as to control a smart car to travel safely. The method according to the embodiments of the present application comprises: first, obtaining traveling track points representing position information of vehicles around a target vehicle during a traveling process; next, performing data processing on every two traveling track points that are adjacent in time and belong to the same vehicle to separately determine corresponding straight lines; then, determining target equation parameters according to the determined equation parameters corresponding to individual straight lines; and finally, accurately determining a lane centerline according to the target equation parameters.

Description

一种车道中心线确定方法及装置Method and device for determining centerline of lane
本申请要求于2019年9月2日提交中国国家知识产权局、申请号为201910823629.9、发明名称为“一种车道中心线确定方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims the priority of a Chinese patent application filed with the State Intellectual Property Office of China, the application number is 201910823629.9, and the invention title is "a method and device for determining the centerline of a lane" on September 2, 2019, the entire content of which is incorporated by reference In this application.
技术领域Technical field
本申请涉及自动驾驶技术领域，尤其涉及一种车道中心线确定方法及装置。This application relates to the field of automatic driving technology, and in particular to a method and device for determining the centerline of a lane.
背景技术Background technique
随着智能化***被应用到车辆驾驶领域中，越来越多的车辆上配置了能够实现自动驾驶功能或辅助驾驶功能的自动驾驶***。为了实现自动驾驶功能或辅助驾驶功能，车辆上的自动驾驶***通常需要从车辆周围的道路环境中识别出车道中心线，以确定车辆周围的行驶车道，从而可以做出适当的行为决策，控制车辆进行安全行驶。As intelligent systems are applied to the field of vehicle driving, more and more vehicles are equipped with automatic driving systems that can realize automatic driving functions or assisted driving functions. In order to realize the automatic driving function or auxiliary driving function, the automatic driving system on the vehicle usually needs to identify the center line of the lane from the road environment around the vehicle to determine the driving lane around the vehicle, so that appropriate behavior decisions can be made to control the vehicle Drive safely.
目前，自动驾驶***确定车道线的方法通常有两种：一种是通过查询高精度地图，来获得高精度地图中预存的车道线信息，但该方法过度依赖于高精度地图的制作精度、更新和维护频率、以及对车辆定位的准确度，当遇到实际路段与高精度地图出现分歧时，***将无法准确识别出车道线；而另一种常用的识别车道线的方法则是检测视觉图像中的车道线，但该方法过度依赖于车道线的清晰度以及实时的环境条件，容易产生无法准确识别车道线的情况。At present, there are usually two methods for automatic driving systems to determine lane lines: one is to obtain the pre-stored lane line information in the high-precision map by querying the high-precision map, but this method is excessively dependent on the accuracy and update of the high-precision map And maintenance frequency, and the accuracy of vehicle positioning, when the actual road section and the high-precision map are different, the system will not be able to accurately identify the lane line; another commonly used method to identify the lane line is to detect the visual image However, this method relies too much on the clarity of the lane line and real-time environmental conditions, and it is easy to cause the situation that the lane line cannot be accurately recognized.
当通过上述两种方法均无法准确识别出车道线时，现有的解决方案是选取当前车辆正前方距离最近的车辆作为跟踪车辆，并生成该跟踪车辆的行驶轨迹，进而可以控制当前车辆沿着该行驶轨迹进行行驶。但这种解决方案对前方跟踪车辆的存在性以及驾驶行为依赖性较强，当前方不存在跟踪车辆时，该解决方案将无法生效，或者，在该跟踪车辆做出非常规的驾驶行为时，如该跟踪车辆突然***两侧车道时，若当前车辆仍沿着跟踪车辆的行驶轨迹进行行驶，即，执行同样的换道操作来强行跟随该跟踪车辆，将极有可能会造成与其他车辆的驾驶行为冲突，进而可能带来驾驶风险。When the lane line cannot be accurately identified by the above two methods, the existing solution is to select the vehicle with the closest distance in front of the current vehicle as the tracking vehicle, and generate the trajectory of the tracking vehicle, so as to control the current vehicle to follow Drive on this driving track. However, this solution is highly dependent on the existence and driving behavior of the tracking vehicle ahead. When there is no tracking vehicle in front, the solution will not be effective, or when the tracking vehicle makes unconventional driving behaviors, For example, when the tracking vehicle is suddenly inserted into the lanes on both sides, if the current vehicle is still driving along the track of the tracking vehicle, that is, performing the same lane change operation to force the tracking vehicle to follow the tracking vehicle, it will most likely cause interference with other vehicles. Conflicting driving behaviors may bring driving risks.
发明内容Summary of the invention
本申请实施例提供了一种车道中心线确定方法及装置，用于准确确定出车道中心线，以便控制车辆进行安全行驶。The embodiments of the present application provide a method and device for determining the centerline of a lane, which are used to accurately determine the centerline of a lane so as to control the vehicle to drive safely.
第一方面，本申请提供了一种车道线确定方法，该方法包括：在确定目标车辆所在道路的车道中心线时，首先可以确定出在目标车辆周围预设区域内的周围车辆，比如图3所示，图3中粗线框的长方形表示目标车辆，虚线框表示以目标车辆所在位置为中心的预设区域，则可以将虚线框中除目标车辆外的车辆均确定为目标车辆周围的车辆。然后，通过目标车辆(或与其具有通信连接关系的服务器、路侧单元等设备)获取到表示位于目标车辆周围的车辆行驶过程中的位置信息的多个行驶轨迹点或由多个行驶轨迹点组成的行驶轨 迹点集，比如图4所示，图中白色方框表示目标车辆，白色方框周围车道线上所有白色的点则表示每一辆周围车辆的移动轨迹点随着该周围车辆的行驶而构成的行驶轨迹点集。其中，每一行驶轨迹点的位置信息可以用该行驶轨迹点的坐标来表示。接着，可以通过依次按序遍历每一行驶轨迹点，根据其中每两个在时间上相邻且属于同一个车辆的行驶轨迹点的位置信息(如坐标信息)，按照两点确定一条直线的原理，分别确定出对应的多条直线以及每条直线分别对应的方程参数。进而可以根据确定出的每条直线对应的方程参数确定目标方程参数；最后，可以根据确定出的目标方程参数准确确定出车道中心线。In the first aspect, the present application provides a lane line determination method, which includes: when determining the lane center line of the road where the target vehicle is located, first, the surrounding vehicles in the preset area around the target vehicle can be determined, as shown in Figure 3 As shown, the rectangle in the thick frame in Figure 3 represents the target vehicle, and the dashed frame represents the preset area centered on the location of the target vehicle. Then, all vehicles in the dashed frame except the target vehicle can be determined as the vehicles around the target vehicle . Then, through the target vehicle (or a server, roadside unit, etc.) that has a communication connection with it, multiple driving trajectory points or multiple driving trajectory points representing the location information of the vehicle located around the target vehicle during the driving process are obtained For example, as shown in Figure 4, the white box in the figure represents the target vehicle, and all white points on the lane around the white box indicate that the moving trajectory point of each surrounding vehicle follows the driving of the surrounding vehicle And constitute the set of driving trajectory points. Wherein, the position information of each driving trajectory point can be represented by the coordinates of the driving trajectory point. Then, by traversing each driving trajectory point in sequence, according to the position information (such as coordinate information) of every two driving trajectory points that are adjacent in time and belong to the same vehicle, according to the principle of determining a straight line between the two points , Respectively determine the corresponding multiple lines and the equation parameters corresponding to each line. Furthermore, the target equation parameters can be determined according to the determined equation parameters corresponding to each straight line; finally, the lane centerline can be accurately determined according to the determined target equation parameters.
与传统技术相比，本申请实施例在计算出目标车辆周围的车辆的每两个相邻轨迹点确定的直线的方程参数后，可以利用这些周围车辆的行驶轨迹点对应的直线方程参数，进一步拟合出目标车辆所在道路的车道中心线的方程参数，用以准确确定出目标车辆所在道路的车道中心线，从而能够有效提高车辆行驶的安全性，避免带来驾驶风险。Compared with the traditional technology, after calculating the linear equation parameters determined by every two adjacent trajectory points of the vehicles around the target vehicle, the embodiment of the present application can use the linear equation parameters corresponding to the driving trajectory points of these surrounding vehicles to further Fitting the equation parameters of the lane centerline of the road where the target vehicle is located is used to accurately determine the lane centerline of the road where the target vehicle is located, thereby effectively improving the safety of vehicle driving and avoiding driving risks.
在本申请实施例中，方程可以有如下两种可能的实现方式：In the embodiment of this application, the equation can be implemented in the following two possible ways:
第一种方式是，各条直线对应的方程参数包括斜率。The first way is that the equation parameters corresponding to each straight line include the slope.
那么，目标方程参数包括目标斜率，根据各条直线对应的方程参数确定目标方程参数包括：将各条直线对应的方程参数包括的斜率的均值确定为目标斜率。由于目前城市道路中的车道线大多数情况下都是平行且连续的直线，所以各车道中心线对应的斜率值基本是一致的，因此，通过该方式确定出的目标斜率的准确率较高。Then, the target equation parameter includes a target slope, and determining the target equation parameter according to the equation parameter corresponding to each straight line includes: determining the average value of the slope included in the equation parameter corresponding to each straight line as the target slope. Since the lane lines in the current urban roads are mostly parallel and continuous straight lines, the slope values corresponding to the center lines of the lanes are basically the same. Therefore, the accuracy of the target slope determined by this method is relatively high.
在此基础上，一种可能的设计是，根据目标方程参数确定车道中心线包括：获取目标车辆的位置信息；根据目标斜率和目标车辆的位置信息确定目标车辆所在车道的车道中心线。由于当目标方程参数仅包括目标斜率，不包括目标截距(或目标截距为0)时，说明此时对应的周围车辆均位于目标车辆的正前方和正后方，与目标车辆所在车道的车道中心线是一致的，这样，在计算出目标斜率后，仅需要与目标车辆的位置信息进行融合计算，即可确定出车道中心线，不仅可以简化计算过程，还能够提高确定车道中心线的准确率。On this basis, a possible design is that determining the lane centerline according to the target equation parameters includes: obtaining the location information of the target vehicle; determining the lane centerline of the lane where the target vehicle is located according to the target slope and the location information of the target vehicle. Because when the target equation parameters only include the target slope, not the target intercept (or the target intercept is 0), it means that the corresponding surrounding vehicles are located directly in front and behind the target vehicle, and the center of the lane where the target vehicle is located. The lines are consistent. In this way, after the target slope is calculated, it only needs to be fused with the position information of the target vehicle to determine the lane centerline. This not only simplifies the calculation process, but also improves the accuracy of determining the lane centerline. .
进一步的，一种可能的设计是，该方法还包括：根据目标车辆所在车道的车道中心线以及预设车道宽度，得到目标车辆所在车道相邻车道的车道中心线。这样，在确定出目标车辆所在车道的车道中心线后，可以根据预先设置的车道中心线之间的距离应该满足预设的宽度范围(即2.8米至3.5米之间的某一取值)，快速确定出该车道相邻车道的车道中心线，提高了确定道路中各个车道中心线的速率，且使得各个车道的宽度即中心线间距符合城市道路的构建特征。Further, a possible design is that the method further includes: obtaining the lane centerline of the adjacent lane of the target vehicle according to the lane centerline of the lane where the target vehicle is located and the preset lane width. In this way, after determining the lane centerline of the lane where the target vehicle is located, the preset width range (that is, a certain value between 2.8 meters and 3.5 meters) should be satisfied according to the preset distance between the lane centerlines. Quickly determine the lane centerline of the adjacent lanes of the lane, which improves the speed of determining the centerline of each lane in the road, and makes the width of each lane, that is, the centerline spacing conform to the construction characteristics of urban roads.
第二种方式是，各条直线对应的方程参数包括斜率和截距。The second way is that the equation parameters corresponding to each straight line include slope and intercept.
那么，目标方程参数包括目标斜率和目标截距，根据各条直线对应的方程参数确定目标方程参数包括：将各条直线对应的方程参数包括的斜率的均值确定为目标斜率；对各条直线对应的方程参数包括的截距进行聚类得到目标截距。进而，根据目标方程参数确定车道中心线包括：将根据目标斜率和目标截距确定的直线作为车道中心线。Then, the target equation parameters include target slope and target intercept, and determining the target equation parameters according to the equation parameters corresponding to each straight line includes: determining the average value of the slope included in the equation parameters corresponding to each straight line as the target slope; corresponding to each straight line The parameters of the equation include the intercept to cluster to obtain the target intercept. Furthermore, determining the lane center line according to the target equation parameters includes: taking a straight line determined according to the target slope and the target intercept as the lane center line.
在本申请实施例中，通过上述方式，将各条直线对应的方程参数包括的各个斜率的平均值作为目标斜率，并通过对各条直线对应的方程参数包括的各个截距进行聚类得到目标截距，来确定车道中心线。可以不受道路上车道线的清晰度的影响，同时也不需要依靠高 精度地图和高精度定位，即可准确确定出车道中心线，从而降低了自动驾驶***对高精度定位与高精度地图的依赖，进而也降低了自动驾驶***的成本。In the embodiment of the present application, the average value of each slope included in the equation parameter corresponding to each straight line is taken as the target slope through the above method, and the target is obtained by clustering each intercept included in the equation parameter corresponding to each straight line. Intercept to determine the centerline of the lane. It is not affected by the clarity of the lane line on the road, and at the same time, it does not need to rely on high-precision maps and high-precision positioning to accurately determine the centerline of the lane, thereby reducing the automatic driving system’s need for high-precision positioning and high-precision Dependence, which in turn reduces the cost of the automated driving system.
一种可能的实现方式中，对对各条直线对应的方程参数包括的截距进行聚类得到目标截距包括：选取各条直线对应的方程参数中未被标记的其中一个截距作为初始中心点；从各条直线对应的方程参数中确定与初始中心点的差值的绝对值小于或等于第一阈值的截距，并对与初始中心点的差值的绝对值小于或等于第一阈值的截距和所述初始中心点进行标记；将初始中心点与各条直线对应的方程参数中每个截距之间的差值之和确定为移动距离，并将初始中心点与移动距离之和作为新的初始中心点执行上述步骤，以进行迭代，直到移动距离小于或等于第二阈值，并将在移动距离小于或等于第二阈值时对应的初始中心点作为候选中心点加入候选中心点集；再次执行上述步骤以进行迭代，得到新的候选中心点；在迭代的过程中，若新的候选中心点与候选中心集中的候选中心点之间的差值均大于或等于第三阈值，则将新的候选中心点加入候选中心点集，否则丢弃候选中心集中与新的候选中心点之间的差值小于第三阈值的候选中心点，并将新的候选中心点加入候选中心点集中；再将候选中心点集中的候选中心点确定为目标截距。In a possible implementation manner, clustering the intercepts included in the equation parameters corresponding to each straight line to obtain the target intercept includes: selecting one of the unmarked intercepts in the equation parameters corresponding to each straight line as the initial center Point; determine from the equation parameters corresponding to each straight line that the absolute value of the difference from the initial center point is less than or equal to the intercept of the first threshold, and the absolute value of the difference from the initial center point is less than or equal to the first threshold The intercept and the initial center point are marked; the sum of the difference between each intercept in the equation parameters corresponding to the initial center point and each straight line is determined as the moving distance, and the initial center point and the moving distance And as the new initial center point, perform the above steps to iterate until the moving distance is less than or equal to the second threshold, and when the moving distance is less than or equal to the second threshold, the corresponding initial center point is added as a candidate center point to the candidate center point Set; perform the above steps again to iterate to obtain a new candidate center point; in the iterative process, if the difference between the new candidate center point and the candidate center points in the candidate center set is greater than or equal to the third threshold, Then add the new candidate center point to the candidate center point set, otherwise discard the candidate center point whose difference between the candidate center point and the new candidate center point is less than the third threshold, and add the new candidate center point to the candidate center point set ; Then determine the candidate center point in the candidate center point concentration as the target intercept.
在本申请实施例中，由于车辆通常都是沿车道中心线进行行驶的，因此，无论目标车辆的周围车辆是在哪个车道行驶，基本都是沿着该车道的车道中心线进行行驶的，所以利用沿着同一车道中心线行驶的周围车辆的行驶轨迹点确定的直线方程参数中的截距值应该是相近的，由此，通过上述方式对各条直线对应的方程参数包括的各个截距进行聚类后，能够得到更加准确的目标截距，即，提高了确定目标截距的准确率。In the embodiments of this application, since vehicles usually travel along the centerline of the lane, no matter which lane the surrounding vehicles of the target vehicle are traveling in, they basically travel along the centerline of the lane. The intercept values in the linear equation parameters determined by the trajectory points of surrounding vehicles driving along the center line of the same lane should be similar. Therefore, the intercepts included in the equation parameters corresponding to each straight line are calculated in the above manner. After clustering, a more accurate target intercept can be obtained, that is, the accuracy of determining the target intercept is improved.
一种可能的实现方式中，根据目标方程参数确定车道中心线包括：获取最近一次用于确定车道中心线的最终方程参数，并根据最近一次用于确定车道中心线的最终方程参数和本次确定的目标方程参数，确定本次的最终方程参数；再根据本次的最终方程参数确定车道中心线。In a possible implementation, determining the lane centerline according to the target equation parameters includes: obtaining the last final equation parameter used to determine the lane centerline, and according to the last final equation parameter used to determine the lane centerline and this determination Determine the final equation parameters of this time, and then determine the lane center line according to the final equation parameters of this time.
这样，在周期性的确定目标车辆所在道路的车道中心线时，通过对每一次对应的方程参数进行滤波的方式，可以稳定每一次对应的方程参数的取值，从而稳定了每一次目标车辆的行车路线，使其不会发生过于频繁的变动，影响车辆行驶的安全性。In this way, when periodically determining the lane center line of the road where the target vehicle is located, by filtering the corresponding equation parameters for each time, the value of the equation parameter corresponding to each time can be stabilized, thereby stabilizing the value of the target vehicle every time. The driving route will not change too frequently, which will affect the safety of the vehicle.
一种可能的实现方式中，若车道中心线为多条，则该方法还包括：将多条车道中心线中相邻两条车道中心线的宽度在预设宽度范围内的车道中心线确定为目标车道中心线。通过该方式可以使得这多条车道中心线中相邻两条车道中心线的宽度在预设宽度范围内，进而能够使其满足城市道路规划要求，并确保了确定出的车道中心线结果是正确的。In a possible implementation manner, if there are multiple lane centerlines, the method further includes: determining the lane centerlines whose widths of two adjacent lane centerlines among the plurality of lane centerlines are within a preset width range as The center line of the target lane. In this way, the width of the centerlines of the two adjacent lanes of the multiple lane centerlines can be within the preset width range, so that it can meet the requirements of urban road planning, and ensure that the determined lane centerline results are correct of.
第二方面，本申请还提供了一种车道中心线确定装置，该装置包括：获取单元，用于获取位于目标车辆周围的车辆的行驶轨迹点，行驶轨迹点表示车辆行驶过程中的位置信息；第一确定单元，用于根据每两个在时间上相邻且属于同一个车辆的行驶轨迹点分别确定对应的直线；第二确定单元，用于根据各条直线对应的方程参数确定目标方程参数；第三确定单元，用于根据目标方程参数确定车道中心线。In a second aspect, the present application also provides a device for determining the centerline of a lane, the device comprising: an acquiring unit configured to acquire driving track points of a vehicle located around the target vehicle, where the driving track points represent position information during the driving of the vehicle; The first determining unit is used to determine the corresponding straight line according to every two driving trajectory points that are adjacent in time and belong to the same vehicle; the second determining unit is used to determine the target equation parameter according to the equation parameter corresponding to each straight line ; The third determining unit is used to determine the lane centerline according to the target equation parameters.
一种可能的实现方式中，各条直线对应的方程参数包括斜率，目标方程参数包括目标斜率，第二确定单元具体用于：将方程参数中各个斜率的均值确定为目标斜率。In a possible implementation manner, the equation parameter corresponding to each straight line includes a slope, the target equation parameter includes a target slope, and the second determining unit is specifically configured to determine the average value of each slope in the equation parameter as the target slope.
一种可能的实现方式中，第三确定单元包括：位置信息获取子单元，用于获取目标车辆的位置信息；第三确定子单元，用于根据目标斜率和目标车辆的位置信息确定目标车辆所在车道的车道中心线。In a possible implementation manner, the third determining unit includes: a location information acquiring subunit for acquiring location information of the target vehicle; a third determining subunit for determining where the target vehicle is based on the target slope and location information of the target vehicle The lane centerline of the lane.
一种可能的实现方式中，该装置还包括：获得单元，用于根据目标车辆所在车道的车道中心线以及预设车道宽度，得到目标车辆所在车道相邻车道的车道中心线。In a possible implementation manner, the device further includes: an obtaining unit configured to obtain the lane center line of the adjacent lane of the target vehicle lane according to the lane center line of the target vehicle lane and the preset lane width.
一种可能的实现方式中，各条直线对应的方程参数包括斜率和截距，目标方程参数包括目标斜率和目标截距，第二确定单元包括：目标斜率确定子单元，用于将各条直线对应的方程参数包括的斜率的均值确定为目标斜率；目标截距获得子单元，用于对各条直线对应的方程参数包括的截距进行聚类得到目标截距；In a possible implementation manner, the equation parameters corresponding to each straight line include slope and intercept, the target equation parameters include target slope and target intercept, and the second determining unit includes: a target slope determining subunit, which is used to combine each straight line The mean value of the slope included in the corresponding equation parameter is determined as the target slope; the target intercept obtaining subunit is used to cluster the intercept included in the equation parameter corresponding to each straight line to obtain the target intercept;
第三确定单元具体用于：将根据目标斜率和目标截距确定的直线作为车道中心线。The third determining unit is specifically configured to: use the straight line determined according to the target slope and the target intercept as the center line of the lane.
一种可能的实现方式中，目标截距获得子单元包括：选取子单元，用于选取各条直线对应的方程参数中未被标记的其中一个截距作为初始中心点；标记子单元，用于从各条直线对应的方程参数中确定与初始中心点的差值的绝对值小于或等于第一阈值的截距，并对与所述初始中心点的差值的绝对值小于或等于第一阈值的截距和初始中心点进行标记；第一迭代子单元，用于将初始中心点与各条直线对应的方程参数中每个截距之间的差值之和确定为移动距离，并将初始中心点与移动距离之和作为新的初始中心点执行上述步骤，以进行迭代，直到移动距离小于或等于第二阈值，并将在移动距离小于或等于第二阈值时对应的初始中心点作为候选中心点加入候选中心点集；第二迭代子单元，用于再次执行上述步骤以进行迭代，得到新的候选中心点；中心点确定子单元，用于在迭代的过程中，若新的候选中心点与候选中心集中的候选中心点之间的差值均大于或等于第三阈值，则将新的候选中心点加入候选中心点集，否则丢弃候选中心集中与新的候选中心点之间的差值小于第三阈值的候选中心点，并将新的候选中心点加入候选中心点集中；目标截距确定子单元，用于将候选中心点集中的候选中心点确定为目标截距。In a possible implementation manner, the target intercept acquisition subunit includes: a selection subunit for selecting one of the unmarked intercepts in the equation parameters corresponding to each straight line as the initial center point; and a marking subunit for Determine from the equation parameters corresponding to each straight line that the absolute value of the difference from the initial center point is less than or equal to the first threshold, and the absolute value of the difference from the initial center point is less than or equal to the first threshold Mark the intercept and the initial center point; the first iterative sub-unit is used to determine the sum of the difference between each intercept in the equation parameters corresponding to the initial center point and each straight line as the moving distance, and set the initial The sum of the center point and the moving distance is used as the new initial center point. Perform the above steps to iterate until the moving distance is less than or equal to the second threshold. When the moving distance is less than or equal to the second threshold, the corresponding initial center point is used as a candidate The center point is added to the candidate center point set; the second iteration subunit is used to perform the above steps again to iterate to obtain a new candidate center point; the center point determination subunit is used in the iterative process, if the new candidate center The difference between the point and the candidate center point in the candidate center set is greater than or equal to the third threshold, then the new candidate center point is added to the candidate center point set, otherwise the difference between the candidate center set and the new candidate center point is discarded The candidate center point whose value is less than the third threshold is added to the candidate center point set; the target intercept determination subunit is used to determine the candidate center point in the candidate center point set as the target intercept.
一种可能的实现方式中，第三确定单元包括：方程参数确定子单元，用于获取最近一次用于确定车道中心线的最终方程参数，并根据最近一次用于确定车道中心线的最终方程参数和本次确定的目标方程参数，确定本次的最终方程参数；车道中心线确定子单元，用于根据本次的最终方程参数确定车道中心线。In a possible implementation manner, the third determining unit includes: an equation parameter determination subunit, which is used to obtain the last final equation parameter used to determine the lane centerline, and according to the last final equation parameter used to determine the lane centerline And the target equation parameters determined this time, determine the final equation parameters this time; the lane centerline determination subunit is used to determine the lane centerline according to the final equation parameters this time.
一种可能的实现方式中，若车道中心线为多条，则该装置还包括：第四确定单元，用于将多条车道中心线中相邻两条车道中心线的宽度在预设宽度范围内的车道中心线确定为目标车道中心线。In a possible implementation manner, if there are multiple lane centerlines, the device further includes: a fourth determining unit configured to set the width of the centerlines of two adjacent lanes among the plurality of lane centerlines within the preset width range The centerline of the inner lane is determined as the centerline of the target lane.
第三方面，本申请还提供了一种车道中心线确定设备，该车道中心线确定设备包括：存储器、处理器，In the third aspect, the present application also provides a lane centerline determination device, the lane centerline determination device includes: a memory, a processor,
存储器，用于存储指令；处理器，用于执行存储器中的指令，执行上述方法。The memory is used to store instructions; the processor is used to execute the instructions in the memory and execute the above methods.
第四方面，本申请还提供了一种计算机可读存储介质，包括指令，当其在计算机上运行时，使得计算机执行上述方法。In a fourth aspect, the present application also provides a computer-readable storage medium, including instructions, which when run on a computer, cause the computer to execute the above method.
从以上技术方案可以看出，本申请实施例具有以下优点：It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:
本申请实施例在确定目标车辆所在道路的车道中心线时，首先获取到表示位于目标车 辆周围的车辆行驶过程中的位置信息的行驶轨迹点，然后，再对每两个在时间上相邻且属于同一个车辆的行驶轨迹点进行数据处理，以分别确定出对应的直线，接着，可以根据确定出的每条直线对应的方程参数确定出目标方程参数，最后，再根据该目标方程参数确定出车道中心线。可见，由于车辆通常是沿车道中心线进行行驶的，所以本申请实施例在计算出目标车辆周围的车辆的每两个相邻轨迹点确定的直线的方程参数后，可以利用这些周围车辆的行驶轨迹点对应的直线方程参数，进一步拟合出目标车辆所在道路的车道中心线的方程参数，用以准确确定出目标车辆所在道路的车道中心线，以便控制目标车辆沿该车道中心线进行安全行驶，因此，相较于目前控制目标车辆沿着前方跟踪车辆的行驶轨迹进行行驶的方法而言，能够有效提高车辆行驶的安全性，避免带来驾驶风险。When determining the centerline of the lane of the road where the target vehicle is located, the embodiment of the present application first obtains the driving track points representing the position information of the vehicles located around the target vehicle during the driving process, and then, for every two adjacent and adjacent in time Data processing is performed on the driving trajectory points belonging to the same vehicle to determine the corresponding straight lines respectively. Then, the target equation parameters can be determined according to the equation parameters corresponding to each straight line determined, and finally, the target equation parameters are determined according to the target equation parameters. The center line of the lane. It can be seen that since the vehicle usually travels along the center line of the lane, the embodiment of the present application calculates the linear equation parameters determined by every two adjacent trajectory points of the vehicle around the target vehicle, and can use the driving of these surrounding vehicles. The linear equation parameters corresponding to the trajectory points are further fitted to the equation parameters of the lane center line of the road where the target vehicle is located, so as to accurately determine the lane center line of the road where the target vehicle is located, so as to control the target vehicle to drive safely along the center line of the lane Therefore, compared with the current method of controlling the target vehicle to drive along the trajectory of the vehicle ahead, it can effectively improve the safety of the vehicle and avoid driving risks.
附图说明Description of the drawings
图1为本申请实施例提供的一种硬件场景的示例图；FIG. 1 is an example diagram of a hardware scenario provided by an embodiment of the application;
图2为本申请实施例提供的一种车道中心线确定方法的流程图；FIG. 2 is a flowchart of a method for determining the centerline of a lane according to an embodiment of the application;
图3为本申请实施例提供的位于以目标车辆所在位置为中心的预设区域内的周围车辆的示意图；3 is a schematic diagram of surrounding vehicles located in a preset area centered on the location of the target vehicle according to an embodiment of the application;
图4为本申请实施例提供的目标车辆周围的车辆的行驶轨迹点的示意图；4 is a schematic diagram of the driving track points of vehicles around the target vehicle provided by an embodiment of the application;
图5为本申请实施例提供的各条直线对应的方程参数的分布示意图；5 is a schematic diagram of the distribution of equation parameters corresponding to each straight line provided by an embodiment of the application;
图6为本申请实施例提供的一种车道中心线确定装置的结构框图；Fig. 6 is a structural block diagram of a device for determining a lane center line provided by an embodiment of the application;
图7为本申请实施例提供的一种车道中心线确定设备的结构示意图。Fig. 7 is a schematic structural diagram of a lane centerline determination device provided by an embodiment of the application.
具体实施方式detailed description
本申请实施例提供了一种车道中心线确定方法及装置，用于准确确定出车道中心线，以提高车辆行驶的安全性。The embodiments of the present application provide a method and device for determining the centerline of a lane, which are used to accurately determine the centerline of the lane, so as to improve the safety of vehicle driving.
下面结合附图，对本申请的实施例进行描述。The embodiments of the present application will be described below in conjunction with the drawings.
目前在控制车辆进行自动驾驶时，通常是选取当前车辆正前方距离最近的车辆作为跟踪车辆，并控制当前车辆沿着该跟踪车辆的行驶轨迹进行行驶，这种方式对跟踪车辆的存在性以及驾驶行为依赖性较强，容易带来驾驶风险。At present, when controlling a vehicle for automatic driving, it usually selects the vehicle with the closest distance in front of the current vehicle as the tracking vehicle, and controls the current vehicle to drive along the tracking vehicle's trajectory. This method has an impact on the existence and driving of the tracking vehicle. The behavior dependence is strong, and it is easy to bring driving risks.
为了解决上述问题，本申请提供了一种车道中心线确定方法，先获取到表示位于目标车辆周围的车辆的行驶过程中的位置信息的行驶轨迹点，然后，对每两个在时间上相邻且属于同一个车辆的行驶轨迹点进行数据处理，以分别确定出对应的直线，接着，可以根据确定出的每条直线对应的方程参数确定出目标方程参数，最后，再根据该目标方程参数，准确确定出车道中心线。In order to solve the above-mentioned problems, the present application provides a method for determining the centerline of a lane. First, the driving track points representing the position information of the vehicles located around the target vehicle during the driving process are obtained, and then, for every two adjacent vehicles in time. And the driving track points belonging to the same vehicle are subjected to data processing to determine the corresponding straight lines respectively. Then, the target equation parameters can be determined according to the equation parameters corresponding to each straight line determined, and finally, according to the target equation parameters, Accurately determine the center line of the lane.
参见图1，其示出了本申请实施例提供的一种硬件场景的示例图，如图1所示，该场景中，包括了传感器101和处理器102，其中，处理器102可以是车辆的整车控制器，或者是与整车控制器具有通信连接关系的终端、计算机、服务器等具有数据处理能力的设备。传感器101可以是安装在车辆上的激光雷达、毫米波雷达、平面摄像头等设备，利用传感器101可以获取到当前车辆周围车辆的位置以及速度信息等，比如，可以利用毫米波雷达 向周围车辆发送毫米波并接收反射回的毫米波，用以计算出周围车辆所在位置以及行驶速度，并将得到的计算结果发送至处理器102，以便处理器102根据周围车辆的位置以及速度，拟合出当前车辆所在道路的车道中心线的方程参数，用以准确确定出当前车辆所在道路的车道中心线，以处理器102为当前车辆的整车控制器为例，当其接收到传感器101发送的周围车辆的实时位置和速度后，可以根据每一周围车辆在相邻两个时刻不同位置确定出的直线方程参数，拟合出当前车辆所在道路的车道中心线的方程参数，用以准确确定出当前车辆所在道路的车道中心线。Refer to FIG. 1, which shows an example diagram of a hardware scenario provided by an embodiment of the present application. As shown in FIG. 1, the scenario includes a sensor 101 and a processor 102, where the processor 102 may be a vehicle The vehicle controller, or a terminal, computer, server and other devices with data processing capabilities that have a communication connection with the vehicle controller. The sensor 101 can be a laser radar, millimeter wave radar, plane camera and other equipment installed on the vehicle. The sensor 101 can be used to obtain the position and speed information of the current vehicle surrounding the vehicle. For example, the millimeter wave radar can be used to send millimeters to the surrounding vehicles. And receive the reflected millimeter waves to calculate the location and speed of surrounding vehicles, and send the calculated results to the processor 102 so that the processor 102 can fit the current vehicle according to the location and speed of the surrounding vehicles The equation parameters of the lane centerline of the road on which the current vehicle is located are used to accurately determine the lane centerline of the road where the current vehicle is located. Taking the processor 102 as the vehicle controller of the current vehicle as an example, when it receives the surrounding vehicle information sent by the sensor 101 After real-time position and speed, the equation parameters of the centerline of the lane of the road where the current vehicle is located can be fitted to the equation parameters of the lane centerline of the road where the current vehicle is located according to the linear equation parameters determined by each surrounding vehicle at different positions at two adjacent moments, so as to accurately determine where the current vehicle is located The centerline of the lane of the road.
或者，在另一硬件场景中，可以将传感器101和处理器102集成于车辆或与车辆具有通信连接关系的终端、计算机、服务器等具有数据处理能力的设备中，即，可以利用车辆或与车辆具有通信连接关系的终端、计算机、服务器等具有数据处理能力的设备同时实现传感器101和处理器102的上述功能。例如，以与车辆具有通信连接关系的服务器为例，当其获取到车辆的周围车辆的实时位置和速度后，可以根据每一周围车辆在相邻两个时刻不同位置确定出的直线方程参数，拟合出当前车辆所在道路的车道中心线的方程参数，用以准确确定出当前车辆所在道路的车道中心线。Or, in another hardware scenario, the sensor 101 and the processor 102 can be integrated into the vehicle or a terminal, computer, server and other devices with data processing capabilities that have a communication connection with the vehicle, that is, the vehicle or the vehicle can be used Devices with data processing capabilities such as terminals, computers, and servers having a communication connection relationship implement the above-mentioned functions of the sensor 101 and the processor 102 at the same time. For example, taking a server that has a communication connection with a vehicle as an example, when it obtains the real-time position and speed of the surrounding vehicles of the vehicle, it can determine the linear equation parameters according to the different positions of each surrounding vehicle at two adjacent moments. The equation parameters of the lane centerline of the road where the current vehicle is located are fitted to accurately determine the lane centerline of the road where the current vehicle is located.
或者，在另一硬件场景中，也可以利用路边设备(如路侧单元)取代传感器101，用以通过车联网的方式与处理器102进行数据通信。具体来讲，可以通过设置在道路两侧指定位置的路侧单元(比如设置在红绿灯处的路侧单元)获取当前车辆周围车辆的实时位置和行驶速度，并将其发送至处理器102，以便处理器102根据周围车辆的位置以及速度，拟合出当前车辆所在道路的车道中心线的方程参数，用以准确确定出当前车辆所在的车道中心线，从而解决了目前无法准确确定出车道中心线的问题。Alternatively, in another hardware scenario, a roadside device (such as a roadside unit) can also be used to replace the sensor 101 for data communication with the processor 102 through the Internet of Vehicles. Specifically, it is possible to obtain the real-time position and driving speed of vehicles around the current vehicle through roadside units (such as roadside units installed at traffic lights) at designated locations on both sides of the road, and send them to the processor 102 for The processor 102 fits the equation parameters of the lane centerline of the road where the current vehicle is located according to the position and speed of the surrounding vehicles, so as to accurately determine the lane centerline where the current vehicle is located, thereby solving the current inability to accurately determine the lane centerline. The problem.
或者，在另一硬件场景中，也可以利用路边设备(如路侧单元)同时取代传感器101和处理器102，用以同时实现二者的上述功能。具体来讲，首先可以通过设置在路边的路侧单元等路边设备获取当前车辆周围车辆的实时位置和行驶速度，然后该路侧单元可以根据获取到的每一周围车辆的位置以及速度，拟合出当前车辆所在道路的车道中心线的方程参数，用以准确确定出当前车辆所在的车道中心线，从而解决了目前无法准确确定出车道中心线的问题。Alternatively, in another hardware scenario, a roadside device (such as a roadside unit) can also be used to replace the sensor 101 and the processor 102 at the same time, so as to realize the above-mentioned functions of both at the same time. Specifically, firstly, the real-time position and driving speed of vehicles around the current vehicle can be obtained through roadside equipment such as a roadside unit installed on the roadside, and then the roadside unit can obtain the position and speed of each surrounding vehicle according to the acquired position and speed of each surrounding vehicle. The equation parameters of the lane centerline of the road where the current vehicle is located are fitted to accurately determine the centerline of the lane where the current vehicle is located, thereby solving the problem that the current lane centerline cannot be accurately determined.
需要注意的是，上述几种应用场景仅是为了便于理解本申请而示出，本申请的实施方式在此方面不受任何限制。相反，本申请的实施方式可以应用于适用的任何场景。It should be noted that the above several application scenarios are only shown to facilitate the understanding of this application, and the implementation of this application is not limited in this respect. On the contrary, the embodiments of the present application can be applied to any applicable scenarios.
基于以上应用场景，本申请实施例提供了一种车道中心线确定方法，下面对该方法进行介绍。Based on the above application scenarios, an embodiment of the present application provides a method for determining the centerline of a lane, which is introduced below.
参见图2，其示出了本申请实施例提供的一种车道中心线确定方法的流程图，该方法可由前述硬件结构来执行，具体可以包括以下步骤：Refer to FIG. 2, which shows a flowchart of a method for determining a lane centerline provided by an embodiment of the present application. The method may be executed by the foregoing hardware structure, and may specifically include the following steps:
S201：获取位于目标车辆周围的车辆的行驶轨迹点，其中，行驶轨迹点表示车辆行驶过程中的位置信息。S201: Acquire driving trajectory points of vehicles located around the target vehicle, where the driving trajectory points represent position information during the driving of the vehicle.
在本实施例中，将采用本实施例确定其所在道路的车道中心线的任一车辆定义为目标车辆，在确定目标车辆所在道路的车道中心线时，首先需要获取到位于目标车辆周围的车辆的行驶轨迹点，该行驶轨迹点指的是车辆行驶过程中的位置信息，且本申请实施例不限 定获取到的行驶轨迹点的个数，比如可以获取到多个行驶轨迹点或者是由多个行驶轨迹点组成的集合等。In this embodiment, any vehicle that uses this embodiment to determine the lane centerline of the road on which it is located is defined as the target vehicle. When determining the lane centerline of the road on which the target vehicle is located, it is first necessary to obtain the vehicles located around the target vehicle. The driving trajectory point refers to the position information during the driving of the vehicle, and the embodiment of the present application does not limit the number of the acquired driving trajectory points. For example, multiple driving trajectory points can be acquired or multiple driving trajectory points can be acquired. A collection of driving trajectory points, etc.
其中，本申请实施例中目标车辆周围的车辆指的是位于以目标车辆所在位置为中心的预设区域内的车辆，可以是一辆也可以是多辆，如图3所示，图中粗线框的长方形表示目标车辆，虚线框表示以目标车辆所在位置为中心的预设区域，虚线框中除目标车辆外的车辆均为目标车辆周围的车辆。需要说明的是，该预设区域的取值范围可根据实现情况进行设置，本申请实施例对此不进行限制，比如可以以目标车辆所在位置为中心的前方100米、后方50米、左侧30米、右侧30米的范围设置为预设区域等。Among them, the vehicles around the target vehicle in the embodiment of the present application refer to the vehicles located in the preset area centered on the location of the target vehicle, which can be one or multiple vehicles, as shown in FIG. The rectangle in the wire frame represents the target vehicle, the dashed frame represents the preset area centered on the location of the target vehicle, and the vehicles except the target vehicle in the dashed frame are vehicles around the target vehicle. It should be noted that the value range of the preset area can be set according to the implementation situation, and the embodiment of this application does not limit this. For example, it can be 100 meters in front, 50 meters behind, and left side centered on the location of the target vehicle. The range of 30 meters and 30 meters on the right is set as the preset area, etc.
并且，为了提高周围车辆的识别准确率，需要将预设区域内速度大于或等于预设速度的车辆，作为目标车辆周围的车辆，这是为了排除预设区域内停放的车辆(或路面上的石头等其他非车辆物质)或速度特别低的车辆，这些车辆的速度与目标车辆相比，并非正常车速，对后续车道中心线的确定也基本没有作用，所以在确定目标车辆周围的车辆时，需要将这些速度低于预设速度的车辆排除。其中，预设速度指的是用于区分预设区域内目标车辆周围的车辆与非周围的车辆的临界值，若预设区域内某一车辆的速度大于或等于该临界值，则可以将其作为目标车辆周围的车辆，反之，则不能将其作为目标车辆周围的车辆。需要说明的是，该预设速度的取值可根据实际情况进行设置，本申请实施例对此不进行限制，比如可以将预设速度设置为3km/h等。In addition, in order to improve the recognition accuracy of surrounding vehicles, vehicles with speeds greater than or equal to the preset speed in the preset area need to be regarded as vehicles around the target vehicle. This is to exclude vehicles parked in the preset area (or on the road). Rocks and other non-vehicle substances) or vehicles with a particularly low speed. Compared with the target vehicle, the speed of these vehicles is not the normal speed, and it has basically no effect on the determination of the centerline of the subsequent lane. Therefore, when determining the vehicles around the target vehicle, It is necessary to exclude these vehicles whose speed is lower than the preset speed. Among them, the preset speed refers to the critical value used to distinguish vehicles around the target vehicle in the preset area from non-surrounding vehicles. If the speed of a vehicle in the preset area is greater than or equal to the critical value, it can be As a vehicle around the target vehicle, on the contrary, it cannot be regarded as a vehicle around the target vehicle. It should be noted that the value of the preset speed can be set according to actual conditions, and the embodiment of the present application does not limit this. For example, the preset speed can be set to 3 km/h.
需要说明的是，在本实施例中，可以将每一周围车辆的同一指定位置的移动轨迹点作为对应周围车辆的行驶轨迹点，比如可以将每一周围车辆的中心位置的移动轨迹点作为对应周围车辆的行驶轨迹点，如图3所示，可以将图中所示的一辆周围车辆中心位置对应的“黑点”作为该周围车辆的一个移动轨迹点，随着该周围车辆的行驶，可以得到多个“黑点”，进而可以利用这些黑点的位置信息表示该周围车辆行驶过程中的位置信息，并将其作为该周围车辆的行驶轨迹点，如图4所示，图中白色方框表示目标车辆，白色方框周围车道线上所有白色的点则表示每一辆周围车辆的移动轨迹点随着该周围车辆的行驶而构成的行驶轨迹点集。其中，每一行驶轨迹点的位置信息可以用该行驶轨迹点的坐标来表示。It should be noted that in this embodiment, the movement track point of the same designated position of each surrounding vehicle can be used as the driving track point of the corresponding surrounding vehicle. For example, the movement track point of the center position of each surrounding vehicle can be used as the corresponding The driving trajectory points of surrounding vehicles, as shown in Fig. 3, the "black dot" corresponding to the center position of a surrounding vehicle shown in the figure can be used as a moving trajectory point of the surrounding vehicle. As the surrounding vehicle travels, A number of "black dots" can be obtained, and then the position information of these black dots can be used to indicate the position information of the surrounding vehicles during the driving process, and they can be used as the driving trajectory points of the surrounding vehicles, as shown in Figure 4, the white color in the figure The box represents the target vehicle, and all the white points on the lane line around the white box represent the set of driving trajectory points formed by the moving trajectory points of each surrounding vehicle along with the driving of the surrounding vehicles. Wherein, the position information of each driving trajectory point can be represented by the coordinates of the driving trajectory point.
具体来讲，可以采用现有或未来出现的位置获取方法，获取周围车辆的多个行驶轨迹点的位置信息，比如，可以利用图1所示的传感器101，如目标车辆上安装的激光雷达、平面摄像头、或毫米波雷达等发射和接收相应的光波，用以计算周围车辆的多个行驶轨迹点的位置信息，具体计算方法与现有方法一致，在此不再赘述。Specifically, existing or future location acquisition methods can be used to acquire the location information of multiple driving trajectory points of surrounding vehicles. For example, the sensor 101 shown in FIG. 1 can be used, such as the lidar, Planar cameras, millimeter-wave radars, etc. transmit and receive corresponding light waves to calculate the position information of multiple driving trajectory points of surrounding vehicles. The specific calculation method is consistent with the existing method and will not be repeated here.
需要说明的是，将图3所示的周围车辆的中心位置对应的“黑点”作为行驶轨迹点仅仅是一种示例，本领域技术人员可根据实际情况确定出周围车辆的行驶轨迹点的其他表现方式，比如车头位置或车尾位置等，本申请实施例对此不进行限定。但为了便于描述，本申请后续将以周围车辆中心位置对应的行驶轨迹点的坐标信息的集合作为对应周围车辆的行驶轨迹点集，而其它表示形式的行驶轨迹点集的处理方式与之类似，不再一一赘述。It should be noted that using the "black dots" corresponding to the center positions of surrounding vehicles as shown in FIG. 3 as the driving trajectory point is only an example, and those skilled in the art can determine other driving trajectory points of surrounding vehicles according to the actual situation. The manner of expression, such as the front position or the rear position, etc., is not limited in the embodiment of the present application. However, for ease of description, this application will subsequently use the collection of coordinate information of the driving trajectory points corresponding to the center position of the surrounding vehicles as the driving trajectory point set corresponding to the surrounding vehicles, and the processing method of the driving trajectory point sets in other representation forms is similar. I will not repeat them one by one.
S202：根据每两个在时间上相邻且属于同一个车辆的行驶轨迹点分别确定对应的直线。S202: Determine a corresponding straight line according to every two driving track points that are adjacent in time and belong to the same vehicle.
在本实施例中，通过步骤S201获取到位于目标车辆周围的车辆的行驶轨迹点后，进一步可以通过对获取到的行驶轨迹点进行数据处理，以根据处理结果确定出对应的直线。In this embodiment, after obtaining the driving trajectory points of the vehicle located around the target vehicle in step S201, data processing may be performed on the obtained driving trajectory points to determine the corresponding straight line according to the processing result.
具体来讲，由于获取到的行驶轨迹点表示的是目标车辆周围的车辆行驶过程中的位置信息，即，是表示周围车辆行驶过程中的坐标信息，如图4所示，在获取到的这些行驶轨迹点中，每一车辆各自对应了多个行驶轨迹点，进而可以通过依次按序遍历每一行驶轨迹点，并根据每两个在时间上相邻且属于同一个车辆的行驶轨迹点的坐标信息，按照两点确定一条直线的原理，分别确定出对应的多条直线以及每条直线分别对应的方程参数。Specifically, because the acquired driving track points represent the position information of the vehicles around the target vehicle during the driving process, that is, they represent the coordinate information of the surrounding vehicles during the driving process. In the driving trajectory points, each vehicle corresponds to multiple driving trajectory points, and then each driving trajectory point can be traversed in sequence, and according to the two driving trajectory points that are adjacent in time and belong to the same vehicle. Coordinate information, according to the principle of two points to determine a straight line, respectively determine the corresponding multiple straight lines and the equation parameters corresponding to each straight line.
其中，需要说明的是，为了提高周围车辆行驶轨迹点的识别准确率，需要保证获取到的所有行驶轨迹点中属于同一个周围车辆的、相邻两个行驶轨迹点的距离大于或等于预设距离，且该预设距离的具体取值可根据实际情况进行设置，本申请对此不进行限定。Among them, it should be noted that, in order to improve the recognition accuracy of surrounding vehicle driving trajectory points, it is necessary to ensure that the distance between two adjacent driving trajectory points belonging to the same surrounding vehicle among all the acquired driving trajectory points is greater than or equal to the preset The distance, and the specific value of the preset distance can be set according to the actual situation, which is not limited in this application.
这样，可以有效避免采集到错误的行驶轨迹点，比如，可以避免采集到传感器噪声点等距离较小的移动轨迹点作为行驶轨迹点，从而提高了周围车辆行驶轨迹点的识别准确率。In this way, it is possible to effectively avoid collecting wrong driving track points. For example, it is possible to avoid collecting moving track points with small distances such as sensor noise points as driving track points, thereby improving the accuracy of identifying the driving track points of surrounding vehicles.
在本实施例的一种可能的实施方式中，通过本步骤S202确定出的各条直线对应的方程参数可以包括两种实现方式：第一种可以为斜率，并可以利用k'来表示，此时对应的车辆均位于目标车辆的正前方和正后方，与目标车辆所在车道的车道中心线是一致的，进而可以根据该斜率以及目标车辆的当前位置信息确定出车道中心线；第二种可以为斜率和截距，并分别可以利用k'和b'来表示，进而可以将对应的直线表示为y'＝k'x+b'，此时对应的周围车辆可以位于目标车辆的侧方向，比如，位于目标车辆的左前方或右后方等，与目标车辆所在车道的车道中心线是不一致的。In a possible implementation manner of this embodiment, the equation parameters corresponding to each straight line determined in this step S202 may include two implementation manners: the first one may be a slope, which may be expressed by k', When the corresponding vehicles are located directly in front of and directly behind the target vehicle, they are consistent with the lane centerline of the lane where the target vehicle is located. Then the lane centerline can be determined according to the slope and the current position information of the target vehicle; the second type can be The slope and intercept can be expressed by k'and b'respectively, and the corresponding straight line can be expressed as y'=k'x+b'. At this time, the corresponding surrounding vehicles can be located in the side direction of the target vehicle, for example , Located at the front left or rear right of the target vehicle, etc., are inconsistent with the centerline of the lane where the target vehicle is located.
S203：根据各条直线对应的方程参数确定目标方程参数。S203: Determine the target equation parameter according to the equation parameter corresponding to each straight line.
在本实施例中，通过步骤S202确定出多条直线以及每条直线分别对应的方程参数后，进一步可以通过对各条直线对应的方程参数进行数据处理，以根据处理结果确定出目标方程参数，其中，目标方程的参数指的是目标车辆所在道路的车道中心线对应的直线方程的参数。In this embodiment, after the multiple straight lines and the equation parameters corresponding to each straight line are determined in step S202, data processing can be performed on the equation parameters corresponding to each straight line to determine the target equation parameters according to the processing results. Among them, the parameters of the target equation refer to the parameters of the straight line equation corresponding to the center line of the lane of the road where the target vehicle is located.
需要说明的是，由于通过上述步骤S202中确定出的方程参数可以包括两种实现方式，进而可以根据不同的方程参数取值，确定出不同的目标方程参数，当方程参数为斜率k'时，则通过对各个斜率k'的处理，可以确定出目标方程参数也为斜率，并可以利用k来表示；当方程参数为斜率k'和截距b'时，则通过对各个斜率k'和截距b'的处理，可以确定出目标方程参数也为斜率和截距，并可以利用k和b来表示，这两种实现方式确定各自对应的目标方程参数的两种具体实现过程可参见后续实施例的详细介绍。It should be noted that since the equation parameters determined in step S202 above can include two implementation methods, different target equation parameters can be determined according to the values of different equation parameters. When the equation parameter is the slope k', Then through the processing of each slope k', it can be determined that the target equation parameter is also a slope, and can be expressed by k; when the equation parameters are the slope k'and intercept b', then through the slope k'and intercept From the processing of distance b', it can be determined that the target equation parameters are also slope and intercept, and can be expressed by k and b. The two specific realization processes for determining the respective target equation parameters can be found in subsequent implementations. Detailed introduction of the case.
在本实施例中，通过本步骤S203确定出各条直线对应的方程参数后，进一步还可以利用这些方程参数共同构成方程参数集，用以确定车道中心线。In this embodiment, after the equation parameters corresponding to each straight line are determined in step S203, these equation parameters can be further used to form an equation parameter set to determine the lane center line.
S204：根据目标方程参数确定车道中心线。S204: Determine the lane center line according to the target equation parameters.
在本实施例中，通过步骤S203确定出目标方程参数后，进一步可利用该目标方程参数确定出车道中心线，其中，当确定出的目标方程参数为斜率k时，则确定出的车道中心线可以表示为：y＝kx；当确定出的目标方程参数为斜率k和截距b时，则确定出的车道中心线可以表示为：y＝kx+b。In this embodiment, after the target equation parameters are determined in step S203, the target equation parameters can be further used to determine the lane centerline. When the determined target equation parameter is the slope k, the determined lane centerline It can be expressed as: y=kx; when the determined target equation parameters are slope k and intercept b, the determined lane centerline can be expressed as: y=kx+b.
综上，本实施例提供的一种车道中心线确定方法，在确定目标车辆所在道路的车道中心线时，首先获取到表示位于目标车辆周围的车辆行驶过程中的位置信息的行驶轨迹点， 然后，再对每两个在时间上相邻且属于同一个车辆的行驶轨迹点进行数据处理，以分别确定出对应的直线，接着，可以根据确定出的每条直线对应的方程参数确定出目标方程参数，最后，再根据该目标方程参数确定出车道中心线。可见，由于车辆通常是沿车道中心线进行行驶的，所以本申请实施例在计算出目标车辆周围的车辆的每两个相邻轨迹点确定的直线的方程参数后，可以利用这些周围车辆的行驶轨迹点对应的直线方程参数，进一步拟合出目标车辆所在道路的车道中心线的方程参数，用以准确确定出目标车辆所在道路的车道中心线，以便控制目标车辆沿该车道中心线进行安全行驶，因此，相较于目前控制目标车辆沿着前方跟踪车辆的行驶轨迹进行行驶的方法而言，能够有效提高车辆行驶的安全性，避免带来驾驶风险。In summary, the method for determining the centerline of the lane provided by this embodiment, when determining the centerline of the lane of the road where the target vehicle is located, first obtains the driving track points representing the position information of the vehicles located around the target vehicle during the driving process, and then , And then perform data processing on every two driving trajectory points that are adjacent in time and belong to the same vehicle to determine the corresponding straight lines respectively. Then, the target equation can be determined according to the equation parameters corresponding to each straight line determined Parameters, and finally, the centerline of the lane is determined according to the target equation parameters. It can be seen that since the vehicle usually travels along the center line of the lane, the embodiment of the present application calculates the linear equation parameters determined by every two adjacent trajectory points of the vehicle around the target vehicle, and can use the driving of these surrounding vehicles. The linear equation parameters corresponding to the trajectory points are further fitted to the equation parameters of the lane center line of the road where the target vehicle is located, so as to accurately determine the lane center line of the road where the target vehicle is located, so as to control the target vehicle to drive safely along the center line of the lane Therefore, compared with the current method of controlling the target vehicle to drive along the trajectory of the vehicle ahead, it can effectively improve the safety of the vehicle and avoid driving risks.
一种可选的实现方式是，为了提高车道中心线确定结果的准确性，本实施例还可以执行下述步骤A1-A2：An optional implementation is that, in order to improve the accuracy of the lane centerline determination result, this embodiment may also perform the following steps A1-A2:
步骤A1：获取最近一次用于确定车道中心线的最终方程参数，并根据最近一次用于确定车道中心线的最终方程参数和本次确定的目标方程参数，确定本次的最终方程参数。Step A1: Obtain the last final equation parameters used to determine the lane centerline, and determine the final equation parameters this time according to the last final equation parameters used to determine the lane centerline and the target equation parameters determined this time.
在本实现方式中，由于是周期性的多次获取目标车辆周围的车辆的行驶轨迹点，用以周期性的确定其所在道路的车道中心线，因此，为了提高车道中心线确定结果的准确性，可以根据最近一次用于确定车道中心线的最终方程参数和本次确定的目标方程参数，确定本次的最终方程参数。In this implementation, since the trajectory points of vehicles around the target vehicle are periodically acquired multiple times to periodically determine the lane centerline of the road on which it is located, in order to improve the accuracy of the lane centerline determination result , The final equation parameters of this time can be determined according to the final equation parameters used to determine the centerline of the lane the last time and the target equation parameters determined this time.
具体来讲，为了稳定目标车辆的行车路线，使其不会发生过于频繁的变动，可以采用一阶数字滤波的方式，来确定每一次的最终方程参数，使得每一次的最终方程参数更加稳定。具体的，可以先将最近一次确定的车道中心线的最终方程参数和本次确定的车道中心线的目标方程参数分别作为滤波的两个输入值，再将本次的最终方程参数作为滤波的输出值，进行滤波，以确定出本次的最终方程参数，具体计算公式如下：Specifically, in order to stabilize the driving route of the target vehicle so that it does not change too frequently, a first-order digital filtering method can be used to determine the final equation parameters each time, so that the final equation parameters each time are more stable. Specifically, the last equation parameter of the lane centerline determined last time and the target equation parameter of the lane centerline determined this time can be used as the two input values of the filter respectively, and then the final equation parameters of this time can be used as the output of the filter. Value, filter to determine the final equation parameters this time, the specific calculation formula is as follows:
y(n)＝q*x(n)+(1-q)*y(n-1)y(n)=q*x(n)+(1-q)*y(n-1)
其中，y(n)表示本次的最终方程参数；q为滤波系数；x(n)表示本次确定的车道中心线的目标方程参数；y(n-1)表示最近一次确定的车道中心线的最终方程参数。Among them, y(n) represents the final equation parameter of this time; q is the filter coefficient; x(n) represents the target equation parameter of the lane centerline determined this time; y(n-1) represents the most recently determined lane centerline The final equation parameters.
需要说明的是，在上述计算过程中，本次的最终方程参数类型y(n)与本次确定的车道中心线的目标方程参数x(n)类型和最近一次确定的车道中心线的最终方程参数类型y(n-1)是一致的。例如，若确定出的本次的最终方程参数y(n)为斜率，则滤波时采用的输入为：本次确定的车道中心线的目标方程参数中包括的斜率以及最近一次确定的车道中心线的最终方程参数中包括的斜率；同理，若确定出的本次的最终方程参数y(n)为截距，则滤波时采用的输入为：本次确定的车道中心线的目标方程参数中包括的截距以及最近一次确定的车道中心线的最终方程参数中包括的截距。It should be noted that in the above calculation process, the final equation parameter type y(n) this time and the target equation parameter x(n) type of the lane centerline determined this time and the final equation of the lane centerline determined last time The parameter type y(n-1) is consistent. For example, if the final equation parameter y(n) determined this time is the slope, the input used in filtering is: the slope included in the target equation parameter of the lane centerline determined this time and the lane centerline determined last time In the same way, if the final equation parameter y(n) is determined as the intercept, the input used in filtering is: the target equation parameter of the lane center line determined this time The intercept included and the intercept included in the final equation parameters of the last determined lane centerline.
步骤A2：根据本次的最终方程参数确定车道中心线。Step A2: Determine the lane centerline according to the final equation parameters this time.
通过步骤A1确定出本次的最终方程参数后，进一步的，可以利用该本次的最终方程参数中包含的斜率(或斜率和截距)，确定出车道中心线。其中，需要说明的是，若确定出的车道中心线为多条，则这多条车道中心线中相邻两条车道中心线的宽度应该在预设宽度范围内，使其满足城市道路规划要求，其中，该预设宽度范围可根据城市道路的特征进行设 定，比如可以设定为2.8米至3.5米之间。After the final equation parameters of this time are determined through step A1, further, the slope (or slope and intercept) contained in the final equation parameters of this time can be used to determine the lane centerline. Among them, it should be noted that if there are multiple lane centerlines determined, the width of the centerlines of the two adjacent lanes among the multiple lane centerlines should be within the preset width range, so that it can meet the requirements of urban road planning , Wherein, the preset width range can be set according to the characteristics of urban roads, for example, it can be set between 2.8 meters and 3.5 meters.
这样，在周期性的确定目标车辆所在道路的车道中心线时，通过对每一次对应的方程参数进行滤波的方式，可以稳定每一次对应的方程参数的取值，从而稳定了每一次目标车辆的行车路线，使其不会发生过于频繁的变动，影响车辆行驶的安全性。In this way, when periodically determining the lane center line of the road where the target vehicle is located, by filtering the corresponding equation parameters for each time, the value of the equation parameter corresponding to each time can be stabilized, thereby stabilizing the value of the target vehicle every time. The driving route will not change too frequently, which will affect the safety of the vehicle.
另外，为了进一步提高车道中心线确定结果的准确性，在通过本申请实施例的方式确定出车道中心线后，还可以将该确定结果与利用现有确定车道线的两种方式(利用高精度地图和高精度定位的方式、检测视觉图像中的车道线的方式)确定出的结果进行对比分析，以得到更为准确的车道中心线。比如，可以将三个确定结果进行求平均计算，并将计算结果作为最终的确定结果，或者，也可以利用预先为三个确定结果设置的权重，进行加权计算，以计算出最终的确定结果等。In addition, in order to further improve the accuracy of the lane centerline determination result, after the lane centerline is determined by the method of the embodiment of the present application, the determination result can also be combined with the existing two methods of determining the lane line (using high-precision The map and high-precision positioning method, the method of detecting the lane line in the visual image) are compared and analyzed to obtain a more accurate lane centerline. For example, the three determination results can be averaged, and the calculation result can be used as the final determination result, or the weights set for the three determination results in advance can be used for weighting calculation to calculate the final determination result, etc. .
接下来，本实施例将对通过步骤S203“根据各条直线对应的方程参数确定目标方程参数”的两种具体实现过程进行介绍。Next, this embodiment will introduce two specific implementation processes of "determining the target equation parameter according to the equation parameter corresponding to each straight line" in step S203.
需要说明的是，尽管通过上述步骤S202确定出的方程参数可以包括两种实现方式(第一种可以为斜率、第二种可以为斜率和截距)，进而可以根据不同的方程参数取值，确定出不同的目标方程参数，但由于目前城市道路中的车道线大多数情况下都是平行且连续的直线，比如高速公路、城市高架道路上的车道线均为平行且连续的直线，所以各车道中心线对应的斜率值基本是一致的，因此，对于上述这两种实现方式中斜率的处理方式是一致的，具体计算过程请参见下述步骤(1)。当方程参数中包括截距(即对应上述第二种实现方式)时，对于截距的处理方式可参见下述步骤(2)：It should be noted that although the equation parameters determined in step S202 above can include two implementation methods (the first can be slope, and the second can be slope and intercept), and the values can be selected according to different equation parameters, Different target equation parameters are determined, but because the lane lines on urban roads are mostly parallel and continuous straight lines in most cases, for example, the lane lines on highways and urban elevated roads are parallel and continuous straight lines. The slope values corresponding to the center line of the lane are basically the same. Therefore, the slope processing methods in the above two implementations are the same. For the specific calculation process, please refer to the following step (1). When the intercept is included in the equation parameters (that is, corresponding to the above-mentioned second implementation method), the processing method of the intercept can be referred to the following step (2):
(1)在本实施例的第一种实现方式中，当各条直线对应的方程参数包括斜率时，目标方程参数包括目标斜率，则步骤S203可以包括：将各条直线对应的方程参数包括的斜率的均值确定为目标斜率。(1) In the first implementation of this embodiment, when the equation parameter corresponding to each straight line includes the slope, and the target equation parameter includes the target slope, step S203 may include: The mean value of the slope is determined as the target slope.
在本实现方式中，当通过步骤S202根据行驶轨迹点确定出的各条直线对应的方程参数包括斜率k'时，目标方程参数也必定会包括目标斜率，并可以利用k来表示。需要说明的是，由于目前城市道路中的车道线大多数情况下都是平行且连续的直线，所以各车道中心线对应的斜率值基本是一致的，因此，在计算目标斜率k时，可以对各条直线对应的方程参数包括的斜率k'进行求平均计算，并将得到的平均值作为目标斜率k的值。In this implementation manner, when the equation parameter corresponding to each straight line determined according to the driving track point in step S202 includes the slope k′, the target equation parameter must also include the target slope, and can be represented by k. It should be noted that, because the lane lines on urban roads are mostly parallel and continuous straight lines in most cases, the slope values corresponding to the center lines of the lanes are basically the same. Therefore, when calculating the target slope k, you can The slope k′ included in the equation parameters corresponding to each straight line is averaged, and the obtained average value is used as the value of the target slope k.
在此基础上，当方程参数仅包括斜率，即目标方程参数仅包括目标斜率，不包括目标截距(或目标截距为0)时，步骤S204可以包括：获取目标车辆的位置信息；根据目标斜率和目标车辆的位置信息确定目标车辆所在车道的车道中心线。On this basis, when the equation parameter only includes the slope, that is, the target equation parameter only includes the target slope and does not include the target intercept (or the target intercept is 0), step S204 may include: obtaining the location information of the target vehicle; The slope and the location information of the target vehicle determine the lane centerline of the lane where the target vehicle is located.
具体来讲，当目标方程参数仅包括目标斜率，不包括目标截距(或目标截距为0)时，说明此时对应的周围车辆均位于目标车辆的正前方和正后方，与目标车辆所在车道的车道中心线是一致的，进而可以在获取到目标车辆的位置信息(如坐标信息)后，根据目标斜率以及该目标车辆的位置信息确定出目标车辆所在车道的车道中心线。Specifically, when the target equation parameters only include the target slope and not the target intercept (or the target intercept is 0), it means that the corresponding surrounding vehicles are located directly in front of and directly behind the target vehicle, and are in the same lane as the target vehicle. The lane centerline of the target vehicle is consistent, and after obtaining the location information (such as coordinate information) of the target vehicle, the lane centerline of the lane where the target vehicle is located can be determined according to the target slope and the location information of the target vehicle.
这样，在计算出目标斜率后，仅需要与目标车辆的位置信息进行融合计算，即可确定出车道中心线，不仅可以简化计算过程，还能够提高确定车道中心线的准确率。In this way, after calculating the target slope, it only needs to perform fusion calculation with the location information of the target vehicle to determine the lane centerline, which not only simplifies the calculation process, but also improves the accuracy of determining the lane centerline.
进一步的，在确定出目标车辆所在车道的车道中心线后，还可以根据目标车辆所在车道的车道中心线以及预设车道宽度，得到目标车辆所在车道相邻车道的车道中心线。Further, after determining the lane centerline of the lane where the target vehicle is located, the lane centerline of the adjacent lane of the lane where the target vehicle is located can also be obtained according to the lane centerline of the lane where the target vehicle is located and the preset lane width.
具体来讲，根据目前城市道路规划要求，对于存在多条车道的道路来说，相邻两条车道中心线的宽度应该在预设宽度范围内，且该预设宽度范围一般设置为2.8米至3.5米之间，即预设的车道宽度一般为2.8米至3.5米之间，因此，在确定出目标车辆所在车道的车道中心线后，可以根据预先设置的车道宽度，确定出该车道相邻车道的车道中心线，且两条车道的车道中心线之间的距离满足预设的宽度范围(即2.8米至3.5米之间的某一取值)。Specifically, according to the current urban road planning requirements, for roads with multiple lanes, the width of the center lines of two adjacent lanes should be within a preset width range, and the preset width range is generally set to 2.8 meters to 3.5 meters, that is, the preset lane width is generally between 2.8 meters and 3.5 meters. Therefore, after determining the lane center line of the lane where the target vehicle is located, it can be determined that the lane is adjacent according to the preset lane width The lane centerline of the lane, and the distance between the lane centerlines of the two lanes meets a preset width range (that is, a certain value between 2.8 meters and 3.5 meters).
(2)在本实施例的第二种实现方式中，当各条直线对应的方程参数包括斜率和截距时，目标方程参数包括目标斜率和目标截距，则步骤S203可以包括：将各条直线对应的方程参数包括的斜率的均值确定为目标斜率；对各条直线对应的方程参数包括的截距进行聚类得到目标截距，进而步骤S204可以包括：将根据目标斜率和目标截距确定的直线作为车道中心线。(2) In the second implementation of this embodiment, when the equation parameters corresponding to each straight line include slope and intercept, and the target equation parameters include target slope and target intercept, step S203 may include: The average value of the slope included in the equation parameters corresponding to the straight line is determined as the target slope; the intercept included in the equation parameters corresponding to each straight line is clustered to obtain the target intercept, and step S204 may include: determining according to the target slope and the target intercept The straight line as the center line of the lane.
在本实现方式中，当通过步骤S202根据行驶轨迹点确定出的各条直线对应的方程参数包括截距b'时，则目标方程参数也包括目标截距，并可以利用b来表示。需要说明的是，由于车辆通常都是沿车道中心线进行行驶的，因此，无论目标车辆周围的车辆是在哪个车道行驶，基本都是沿着该车道的车道中心线进行行驶的，所以利用沿着同一车道中心线行驶的车辆的行驶轨迹点确定的直线方程参数中的截距值应该是相近的，进而可利用现有或未来出现的聚类算法，对各条直线对应的方程参数包括的各个截距b'进行聚类，比如，可利用基于核密度估计的爬山算法(Mean shift算法)，对各条直线对应的方程参数包括的截距b'进行聚类，并根据得到的聚类结果，确定出目标截距b的值，即，聚类后得到了几个可以作为聚类中心点的截距b'，就相当于得到了几个车道中心线对应的方程参数中包含目标截距b的值，进而，可以利用确定出的目标截距b的值以及通过步骤(1)确定出的目标斜率k的值，确定出对应的直线，用以作为车道中心线。其中，对各条直线对应的方程参数包括的截距b'进行聚类的具体聚类过程可以包括下述步骤B1-B6：In this implementation manner, when the equation parameter corresponding to each straight line determined according to the driving track point in step S202 includes the intercept b′, the target equation parameter also includes the target intercept, and can be represented by b. It should be noted that since vehicles usually drive along the centerline of the lane, no matter which lane the vehicles around the target vehicle drive in, they basically drive along the centerline of the lane. The intercept values in the linear equation parameters determined by the trajectory points of the vehicles driving on the centerline of the same lane should be similar, and then the existing or future clustering algorithms can be used to determine the equation parameters corresponding to each straight line. Each intercept b'is clustered, for example, the hill climbing algorithm (Mean shift algorithm) based on kernel density estimation can be used to cluster the intercept b'included in the equation parameters corresponding to each straight line, and cluster according to the obtained clustering As a result, the value of the target intercept b is determined, that is, after clustering, several intercepts b'that can be used as the center points of the cluster are obtained, which is equivalent to obtaining the equation parameters corresponding to the center lines of several lanes including the target intercept The value of the distance b, and further, the value of the determined target intercept b and the value of the target slope k determined in step (1) may be used to determine the corresponding straight line as the center line of the lane. Wherein, the specific clustering process of clustering the intercept b′ included in the equation parameter corresponding to each straight line may include the following steps B1-B6:
步骤B1：选取各条直线对应的方程参数中未被标记的其中一个截距作为初始中心点。Step B1: Select one of the unmarked intercepts in the equation parameters corresponding to each straight line as the initial center point.
在本申请实施例中，在对各条直线对应的方程参数包括的各个截距b'进行聚类的过程中，首先，从各条直线对应的方程参数中所有未被标记的截距b'中选取一个截距b'作为首次聚类的中心点，即初始中心点，并将其定义为center。In the embodiment of the present application, in the process of clustering the intercepts b′ included in the equation parameters corresponding to each straight line, firstly, from the equation parameters corresponding to each straight line, all the unlabeled intercepts b′ Choose an intercept b'as the center point of the first clustering, that is, the initial center point, and define it as center.
步骤B2：从各条直线对应的方程参数中确定与初始中心点的差值的绝对值小于或等于第一阈值的截距，并对与初始中心点的差值的绝对值小于或等于第一阈值的截距和初始中心点进行标记。Step B2: Determine from the equation parameters corresponding to each straight line that the absolute value of the difference from the initial center point is less than or equal to the first threshold, and the absolute value of the difference from the initial center point is less than or equal to the first threshold. The intercept of the threshold and the initial center point are marked.
通过步骤B1选取出作为初始中心点center的截距后，可以在各条直线对应的方程参数中，以该初始中心点为圆心，从分布在其四周的截距中，查找出与其的差值的绝对值小于或等于第一阈值的截距，将这些截距归属于初始中心点，形成以初始中心点为中心的簇，并将该簇中这些查找出来的截距和初始中心点对应的截距进行标记，以表明这些截距是已经做过聚类计算的截距。其中，第一阈值的取值可根据实际情况进行设置，本申请对此不 进行限定，比如可以将第一阈值取为1.0。After selecting the intercept as the initial center point center through step B1, in the equation parameters corresponding to each straight line, using the initial center point as the center of the circle, find the difference from the intercepts distributed around it The absolute value of is less than or equal to the intercept of the first threshold, these intercepts are attributed to the initial center point to form a cluster centered on the initial center point, and the intercepts found in the cluster are corresponding to the initial center point The intercepts are marked to indicate that these intercepts are those that have been clustered. The value of the first threshold can be set according to actual conditions, which is not limited in this application. For example, the first threshold can be set to 1.0.
步骤B3：将初始中心点与各条直线对应的方程参数中每个截距之间的差值之和确定为移动距离，并将初始中心点与移动距离之和作为新的初始中心点执行上述步骤，以进行迭代，直到移动距离小于或等于第二阈值，并将在移动距离小于或等于第二阈值时对应的初始中心点作为候选中心点加入候选中心点集。Step B3: Determine the sum of the difference between each intercept in the equation parameters corresponding to the initial center point and each straight line as the moving distance, and use the sum of the initial center point and the moving distance as the new initial center point. Steps are to iterate until the moving distance is less than or equal to the second threshold, and the initial center point corresponding to when the moving distance is less than or equal to the second threshold is added as a candidate center point to the candidate center point set.
在本实现方式中，可以计算出步骤B1中确定的初始中心点center与各条直线对应的方程参数中每个截距之间的差值之和，并将该值作为移动距离，定义为shift，然后，将步骤B1中确定的初始中心点center与该移动距离shift之和作为新的初始中心点，并将该新的初始中心点定义为center 1，则center 1＝center+shift，进而可以利用该新的初始中心点center 1来重复执行步骤B2，在进行多次迭代计算后，直至移动距离shift的取值小于或等于第二阈值时，停止迭代计算，并将此时对应的初始中心点center 1作为候选中心点加入候选中心点集。其中，第二阈值的取值可根据实际情况进行设置，本申请对此不进行限定，比如可以将第二阈值取为0.1。 In this implementation, the sum of the difference between the initial center point center determined in step B1 and each intercept in the equation parameters corresponding to each straight line can be calculated, and this value can be used as the moving distance, which is defined as shift , And then, the sum of the initial center point center determined in step B1 and the shift distance shift is used as the new initial center point, and the new initial center point is defined as center 1 , then center 1 = center+shift, and then Use the new initial center point center 1 to repeat step B2. After multiple iterative calculations, until the value of the shift distance shift is less than or equal to the second threshold, the iterative calculation is stopped, and the corresponding initial center The point center 1 is added to the candidate center point set as a candidate center point. The value of the second threshold can be set according to actual conditions, which is not limited in this application. For example, the second threshold can be set to 0.1.
步骤B4：再次执行上述步骤以进行迭代，得到新的候选中心点。Step B4: Perform the above steps again to iterate to obtain a new candidate center point.
通过步骤B3得到候选中心点集中候选中心点center 1后，可再次重复执行上述步骤B3以进行迭代，得到新的候选中心点，并将其加入候选中心点集中。 After obtaining the candidate center point center 1 in the candidate center point set through step B3, the above step B3 can be repeated to iterate again to obtain a new candidate center point and add it to the candidate center point set.
步骤B5：在迭代的过程中，若新的候选中心点与候选中心集中的候选中心点之间的差值均大于或等于第三阈值，则将该新的候选中心点加入候选中心点集，否则丢弃候选中心集中与该新的候选中心点之间的差值小于第三阈值的候选中心点，并将该新的候选中心点加入候选中心点集中。Step B5: In the iterative process, if the difference between the new candidate center point and the candidate center points in the candidate center set is greater than or equal to the third threshold, add the new candidate center point to the candidate center point set. Otherwise, the candidate center point whose difference between the candidate center point and the new candidate center point is less than the third threshold is discarded, and the new candidate center point is added to the candidate center point set.
在执行上述步骤B4进行迭代计算的过程中，若得到的新的候选中心点与候选中心集中已经存在的候选中心点之间的差值均大于或等于第三阈值，则可以将该新的候选中心点作为一个新的聚类中心点加入到候选中心点集中，否则，若得到的新的候选中心点与候选中心集中某些已经存在的候选中心点之间的差值均小于第三阈值，则可以将该新的候选中心点与候选中心集中这些已经存在的候选中心点进行合并，即，将候选中心集中与该新的候选中心点之间的差值小于第三阈值的候选中心点丢弃的同时，将该新的候选中心点作为一个新的聚类中心点加入到候选中心点集中。其中，第三阈值的取值可根据实际情况进行设置，本申请对此不进行限定，比如可以将第三阈值取为3.0。In the process of performing the iterative calculation of step B4, if the difference between the obtained new candidate center point and the candidate center point that already exists in the candidate center set is greater than or equal to the third threshold, the new candidate can be The center point is added to the candidate center point set as a new cluster center point. Otherwise, if the difference between the new candidate center point and some existing candidate center points in the candidate center set is less than the third threshold, Then the new candidate center point can be merged with these existing candidate center points in the candidate center set, that is, the candidate center point whose difference between the candidate center set and the new candidate center point is less than the third threshold is discarded At the same time, the new candidate center point is added to the candidate center point set as a new cluster center point. The value of the third threshold can be set according to actual conditions, which is not limited in this application. For example, the third threshold can be set to 3.0.
步骤B6：将候选中心点集中的候选中心点确定为目标截距。Step B6: Determine the candidate center point in the set of candidate center points as the target intercept.
通过上述步骤B1-B5确定出候选中心点集中的所有的候选中心点后，可以将每一候选中心点分别确定为目标截距的取值，用以确定出对应的车道中心线。After determining all the candidate center points in the candidate center point set through the above steps B1-B5, each candidate center point can be determined as the value of the target intercept to determine the corresponding lane center line.
需要说明的是，在确定出同一道路上的多条车道中心线时，应该确保多条车道中心线中相邻两条车道中心线的宽度在预设宽度范围内，即，可以将多条车道中心线中相邻两条车道中心线的宽度在预设宽度范围内的车道中心线确定为目标车道中心线，且该预设宽度范围可根据城市道路的特征进行设定，比如可以设定为2.8米至3.5米之间。若计算出相邻两条车道中心线的宽度未在预设宽度范围内，则表明确定出的车道中心线结果是不正确的。It should be noted that when determining the centerlines of multiple lanes on the same road, it should be ensured that the centerlines of two adjacent lanes among the centerlines of the multiple lanes are within the preset width range, that is, multiple lanes can be combined. In the centerline, the centerline of the two adjacent lanes whose width is within the preset width range is determined as the target lane centerline, and the preset width range can be set according to the characteristics of urban roads, for example, it can be set as Between 2.8 meters and 3.5 meters. If it is calculated that the width of the centerline of two adjacent lanes is not within the preset width range, it indicates that the result of the determined lane centerline is incorrect.
举例说明：参见图5，其示出了本申请实施例提供的各条直线对应的方程参数的分布示意图，利用上述第(2)种实现方式中的步骤B1-B6对图5上方图中的各个截距进行聚类计算可以得到三个聚类后的中心点值，并可以分别将其作为目标截距的值。同时，通过执行上述第(1)种实现方式中的步骤，对图5下方图中的各个斜率进行求平均计算，再将得到的平均值作为目标斜率的值。进而可以利用得到的目标斜率以及3个目标截距确定出3条车道中心线，且从图5可以看出各条直线对应的方程参数中截距分布的三个峰值间隔在3.5左右，因此得到的3条车道中心线中相邻两条车道中心线的宽度是在预设的宽度范围内，符合城市道路的特征，从而表明车道中心线的确定结果是正确的。For example: referring to FIG. 5, which shows a schematic diagram of the distribution of equation parameters corresponding to each straight line provided by the embodiment of the present application. The clustering calculation of each intercept can obtain the center point values after three clusters, which can be used as the value of the target intercept respectively. At the same time, by performing the steps in the above-mentioned realization method (1), the slopes in the lower graph of FIG. 5 are averaged, and the average value obtained is used as the value of the target slope. Furthermore, the obtained target slope and the three target intercepts can be used to determine the three lane centerlines, and it can be seen from Figure 5 that the three peak intervals of the intercept distribution in the equation parameters corresponding to each straight line are about 3.5, so The width of the centerlines of the two adjacent lanes among the three lane centerlines is within the preset width range, which conforms to the characteristics of urban roads, thus indicating that the determination result of the lane centerline is correct.
再举例说明：假设利用上述第(2)种实现方式中的步骤B1-B6对各个截距进行聚类计算得到的三个聚类中心点的值分别为-5、0、5，则可以分别将其作为目标截距b 1、b 2、b 3的值，即，b 1＝-5、b 2＝0、b 3＝5，同时，假设通过执行上述第(1)种实现方式中的步骤，计算出目标斜率为
Figure PCTCN2020100046-appb-000001
则得到的3条车道中心线分别为
Figure PCTCN2020100046-appb-000002
Figure PCTCN2020100046-appb-000003
通过计算可得这3条车道中心线中相邻两条车道中心线的宽度为3，是在预设的宽度范围内，符合城市道路的特征，从而表明这三条车道中心线的确定结果是正确的，如图4中三条平行的白线所示。 Another example: Assuming that the values of the three cluster center points obtained by clustering calculation of the intercepts using steps B1-B6 in the above-mentioned (2) implementation manner are -5, 0, and 5, respectively, you can respectively Take it as the value of the target intercepts b 1 , b 2 , and b 3 , that is, b 1 =-5, b 2 =0, b 3 =5. At the same time, it is assumed that by performing the above-mentioned (1) realization method Step, calculate the target slope as
Figure PCTCN2020100046-appb-000001
Then the centerlines of the three lanes obtained are
Figure PCTCN2020100046-appb-000002
Figure PCTCN2020100046-appb-000003
By calculation, the width of the centerlines of the two adjacent lanes among the three lane centerlines is 3, which is within the preset width range and conforms to the characteristics of urban roads, thus indicating that the determination results of the three lane centerlines are correct , As shown by the three parallel white lines in Figure 4.
需要说明的是，上述步骤B1-B6所描述的对各条直线对应的方程参数包括的各个截距b'进行聚类的方法并不是唯一的，仅是实现聚类过程的一种示例，也可以采取其他聚类算法进行聚类计算，本申请实施例对此不进行限制。It should be noted that the method of clustering each intercept b'included in the equation parameters corresponding to each straight line described in the above steps B1-B6 is not unique, and is only an example of realizing the clustering process. Other clustering algorithms can be used to perform clustering calculation, which is not limited in the embodiment of the present application.
综上，将各条直线对应的方程参数包括的各个斜率k'的平均值作为目标斜率k，并通过对各条直线对应的方程参数包括的各个截距b'进行聚类得到目标截距，用以确定车道中心线的方式，可以不受道路上车道线的清晰度的影响，同时也不需要依靠高精度地图和高精度定位，即可准确确定出车道中心线，从而降低了自动驾驶***对高精度定位与高精度地图的依赖，进而也降低了自动驾驶***的成本。In summary, the average value of each slope k'included in the equation parameter corresponding to each straight line is taken as the target slope k, and the target intercept is obtained by clustering the intercept b'included in the equation parameter corresponding to each straight line. The method used to determine the centerline of the lane can not be affected by the clarity of the lane line on the road. At the same time, it does not need to rely on high-precision maps and high-precision positioning to accurately determine the centerline of the lane, thereby reducing the automatic driving system The reliance on high-precision positioning and high-precision maps further reduces the cost of the automated driving system.
为便于更好的实施本申请实施例的上述方案，下面还提供用于实施上述方案的相关装置。请参见图6所示，本申请实施例提供的车道中心线确定装置600。该装置600可以包括：获取单元601、第一确定单元602、第二确定单元603和第三确定单元604。其中，获取单元601用于执行图2所示实施例中的S201。第一确定单元602用于执行图2所示实施例中的S202。第二确定单元603用于执行图2所示实施例中的S203。第三确定单元604用于执行图2所示实施例中的S204。具体的，To facilitate better implementation of the above-mentioned solutions in the embodiments of the present application, related devices for implementing the above-mentioned solutions are also provided below. Please refer to FIG. 6, an apparatus 600 for determining a centerline of a lane provided in an embodiment of the present application. The apparatus 600 may include: an acquiring unit 601, a first determining unit 602, a second determining unit 603, and a third determining unit 604. Wherein, the acquiring unit 601 is configured to execute S201 in the embodiment shown in FIG. 2. The first determining unit 602 is configured to execute S202 in the embodiment shown in FIG. 2. The second determining unit 603 is configured to execute S203 in the embodiment shown in FIG. 2. The third determining unit 604 is configured to execute S204 in the embodiment shown in FIG. 2. specific,
获取单元601，用于获取位于目标车辆周围的车辆的行驶轨迹点，行驶轨迹点表示车辆行驶过程中的位置信息；The acquiring unit 601 is configured to acquire driving track points of vehicles located around the target vehicle, where the driving track points represent position information during the driving of the vehicle;
第一确定单元602，用于根据每两个在时间上相邻且属于同一个车辆的行驶轨迹点分别确定对应的直线；The first determining unit 602 is configured to determine a corresponding straight line according to every two driving trajectory points that are adjacent in time and belong to the same vehicle;
第二确定单元603，用于根据各条直线对应的方程参数确定目标方程参数；The second determining unit 603 is configured to determine the target equation parameter according to the equation parameter corresponding to each straight line;
第三确定单元604，用于根据目标方程参数确定车道中心线。The third determining unit 604 is configured to determine the center line of the lane according to the target equation parameters.
在本实施例的一种实现方式中，各条直线对应的方程参数包括斜率，目标方程参数包括目标斜率，第二确定单元603具体用于：将方程参数中各个斜率的均值确定为目标斜率。In an implementation of this embodiment, the equation parameter corresponding to each straight line includes a slope, the target equation parameter includes a target slope, and the second determining unit 603 is specifically configured to determine the average value of each slope in the equation parameter as the target slope.
在本实施例的一种实现方式中，第三确定单元604包括：位置信息获取子单元，用于获取目标车辆的位置信息；第三确定子单元，用于根据目标斜率和目标车辆的位置信息确定目标车辆所在车道的车道中心线。In an implementation of this embodiment, the third determining unit 604 includes: a location information obtaining subunit, used to obtain the location information of the target vehicle; the third determining subunit, used according to the target slope and the location information of the target vehicle Determine the lane centerline of the lane where the target vehicle is located.
在本实施例的一种实现方式中，该装置还包括：获得单元，用于根据目标车辆所在车道的车道中心线以及预设车道宽度，得到目标车辆所在车道相邻车道的车道中心线。In an implementation of this embodiment, the device further includes: an obtaining unit configured to obtain the lane center lines of the adjacent lanes of the lane where the target vehicle is located according to the lane centerline of the lane where the target vehicle is located and the preset lane width.
在本实施例的一种实现方式中，各条直线对应的方程参数包括斜率和截距，目标方程参数包括目标斜率和目标截距，第二确定单元603包括：In an implementation of this embodiment, the equation parameters corresponding to each straight line include slope and intercept, the target equation parameters include target slope and target intercept, and the second determining unit 603 includes:
目标斜率确定子单元，用于将各条直线对应的方程参数包括的斜率的均值确定为目标斜率；The target slope determination subunit is used to determine the average value of the slope included in the equation parameters corresponding to each straight line as the target slope;
目标截距获得子单元，用于对各条直线对应的方程参数包括的截距进行聚类得到目标截距；The target intercept obtaining subunit is used to cluster the intercept included in the equation parameters corresponding to each straight line to obtain the target intercept;
第三确定单元604具体用于：将根据目标斜率和目标截距确定的直线作为车道中心线。The third determining unit 604 is specifically configured to: use a straight line determined according to the target slope and the target intercept as the center line of the lane.
在本实施例的一种实现方式中，目标截距获得子单元包括：In an implementation manner of this embodiment, the target intercept obtaining subunit includes:
选取子单元，用于选取各条直线对应的方程参数中未被标记的其中一个截距作为初始中心点；Select sub-units to select one of the unmarked intercepts of the equation parameters corresponding to each straight line as the initial center point;
标记子单元，用于从各条直线对应的方程参数中确定与初始中心点的差值的绝对值小于或等于第一阈值的截距，并对与所述初始中心点的差值的绝对值小于或等于第一阈值的截距和初始中心点进行标记；The marking subunit is used to determine the intercept that the absolute value of the difference from the initial center point is less than or equal to the first threshold from the equation parameters corresponding to each straight line, and to determine the absolute value of the difference from the initial center point Mark the intercept and the initial center point that are less than or equal to the first threshold;
第一迭代子单元，用于将初始中心点与各条直线对应的方程参数中每个截距之间的差值之和确定为移动距离，并将初始中心点与移动距离之和作为新的初始中心点执行上述步骤，以进行迭代，直到移动距离小于或等于第二阈值，并将在移动距离小于或等于第二阈值时对应的初始中心点作为候选中心点加入候选中心点集；The first iterative subunit is used to determine the sum of the difference between each intercept in the equation parameters corresponding to the initial center point and each straight line as the moving distance, and the sum of the initial center point and the moving distance as the new The initial center point performs the above steps to iterate until the moving distance is less than or equal to the second threshold, and when the moving distance is less than or equal to the second threshold, the corresponding initial center point is added as a candidate center point to the candidate center point set;
第二迭代子单元，用于再次执行上述步骤以进行迭代，得到新的候选中心点；The second iteration subunit is used to perform the above steps again to iterate to obtain a new candidate center point;
中心点确定子单元，用于在迭代的过程中，若新的候选中心点与候选中心集中的候选中心点之间的差值均大于或等于第三阈值，则将新的候选中心点加入候选中心点集，否则丢弃候选中心集中与新的候选中心点之间的差值小于第三阈值的候选中心点，并将新的候选中心点加入候选中心点集中；The center point determination subunit is used to add the new candidate center point to the candidate if the difference between the new candidate center point and the candidate center point in the candidate center set is greater than or equal to the third threshold in the iterative process Center point set, otherwise discard the candidate center points whose difference between the candidate center set and the new candidate center point is less than the third threshold, and add the new candidate center point to the candidate center point set;
目标截距确定子单元，用于将候选中心点集中的候选中心点确定为目标截距。The target intercept determination subunit is used to determine the candidate center point in the candidate center point set as the target intercept.
在本实施例的一种实现方式中，第三确定单元604包括：In an implementation manner of this embodiment, the third determining unit 604 includes:
方程参数确定子单元，用于获取最近一次用于确定车道中心线的最终方程参数，并根据最近一次用于确定车道中心线的最终方程参数和本次确定的目标方程参数，确定本次的最终方程参数；The equation parameter determination subunit is used to obtain the last final equation parameters used to determine the lane centerline, and determine the final equation parameters this time based on the last final equation parameters used to determine the lane centerline and the target equation parameters determined this time Equation parameter
车道中心线确定子单元，用于根据本次的最终方程参数确定车道中心线。The lane centerline determination subunit is used to determine the lane centerline according to the final equation parameters this time.
在本实施例的一种实现方式中，若车道中心线为多条，则该装置还包括：In an implementation of this embodiment, if there are multiple lane centerlines, the device further includes:
第四确定单元，用于将多条车道中心线中相邻两条车道中心线的宽度在预设宽度范围内的车道中心线确定为目标车道中心线The fourth determining unit is used to determine the centerline of the lane with the centerline of the two adjacent lanes in the preset width range among the centerlines of the multiple lanes as the centerline of the target lane
综上所述，本申请实施例中提供的车道中心线确定装置中，在确定目标车辆所在道路的车道中心线时，首先获取到表示位于目标车辆周围的车辆行驶过程中的位置信息的行驶轨迹点，然后，再对每两个在时间上相邻且属于同一个车辆的行驶轨迹点进行数据处理，以分别确定出对应的直线，接着，可以根据确定出的每条直线对应的方程参数确定出目标方程参数，最后，再根据该目标方程参数确定出车道中心线。可见，由于车辆通常是沿车道中心线进行行驶的，所以本申请实施例在计算出目标车辆周围的车辆的每两个相邻轨迹点确定的直线的方程参数后，可以利用这些周围车辆的行驶轨迹点对应的直线方程参数，进一步拟合出目标车辆所在道路的车道中心线的方程参数，用以准确确定出目标车辆所在道路的车道中心线，以便控制目标车辆沿该车道中心线进行安全行驶，因此，相较于目前控制目标车辆沿着前方跟踪车辆的行驶轨迹进行行驶的方法而言，能够有效提高车辆行驶的安全性，避免带来驾驶风险。In summary, in the lane centerline determining device provided in the embodiments of the present application, when determining the lane centerline of the road on which the target vehicle is located, first obtain the driving trajectory indicating the position information of the vehicle located around the target vehicle during the driving process Then, data processing is performed on every two driving trajectory points that are adjacent in time and belong to the same vehicle to determine the corresponding straight line. Then, it can be determined according to the equation parameters corresponding to each straight line determined Determine the target equation parameters, and finally, determine the lane center line according to the target equation parameters. It can be seen that since the vehicle usually travels along the center line of the lane, the embodiment of the present application calculates the linear equation parameters determined by every two adjacent trajectory points of the vehicle around the target vehicle, and can use the driving of these surrounding vehicles. The linear equation parameters corresponding to the trajectory points are further fitted to the equation parameters of the lane center line of the road where the target vehicle is located, so as to accurately determine the lane center line of the road where the target vehicle is located, so as to control the target vehicle to drive safely along the center line of the lane Therefore, compared with the current method of controlling the target vehicle to drive along the trajectory of the vehicle ahead, it can effectively improve the safety of the vehicle and avoid driving risks.
参见图7，本申请实施例提供了一种车道中心线确定设备700，该设备包括存储器701、处理器702和通信接口703，Referring to FIG. 7, an embodiment of the present application provides a lane centerline determination device 700, which includes a memory 701, a processor 702, and a communication interface 703.
存储器701，用于存储指令；The memory 701 is used to store instructions;
处理器702，用于执行存储器701中的指令，执行上述应用于图2所示实施例中的车道中心线确定方法；The processor 702 is configured to execute instructions in the memory 701, and execute the above-mentioned method for determining the lane centerline applied in the embodiment shown in FIG. 2;
通信接口703，用于进行通信。The communication interface 703 is used for communication.
存储器701、处理器702和通信接口703通过总线704相互连接；总线704可以是外设部件互连标准(peripheral component interconnect，简称PCI)总线或扩展工业标准结构(extended industry standard architecture，简称EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图7中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。The memory 701, the processor 702, and the communication interface 703 are connected to each other through a bus 704; the bus 704 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus Wait. The bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 7, but it does not mean that there is only one bus or one type of bus.
在具体实施例中，处理器702用于在确定目标车辆所在道路的车道中心线时，获取表示位于目标车辆周围的车辆行驶过程中的位置信息的行驶轨迹点，然后，再对每两个在时间上相邻且属于同一个车辆的行驶轨迹点进行数据处理，以分别确定出对应的直线，接着，可以根据确定出的每条直线对应的方程参数确定出目标方程参数，最后，再根据该目标方程参数确定出车道中心线。该处理器702的详细处理过程请参考上述图2所示实施例中S201、S202、S203和S204的详细描述，这里不再赘述。In a specific embodiment, the processor 702 is configured to, when determining the centerline of the lane of the road where the target vehicle is located, obtain driving track points that represent the location information of the vehicles located around the target vehicle during driving, and then calculate every two Data processing is performed on the driving trajectory points that are adjacent in time and belong to the same vehicle to determine the corresponding straight lines respectively. Then, the target equation parameters can be determined according to the equation parameters corresponding to each straight line determined, and finally, according to the The target equation parameters determine the centerline of the lane. For the detailed processing process of the processor 702, please refer to the detailed description of S201, S202, S203, and S204 in the embodiment shown in FIG. 2, which will not be repeated here.
上述存储器701可以是随机存取存储器(random-access memory，RAM)、闪存(flash)、只读存储器(read only memory，ROM)、可擦写可编程只读存储器(erasable programmable read only memory，EPROM)、电可擦除可编程只读存储器(electrically erasable programmable read only memory，EEPROM)、寄存器(register)、硬盘、移动硬盘、CD-ROM或者本领域技术人员知晓的任何其他形式的存储介质。The above-mentioned memory 701 may be random-access memory (RAM), flash memory (flash), read only memory (ROM), erasable programmable read only memory (EPROM) ), electrically erasable programmable read only memory (EEPROM), register, hard disk, mobile hard disk, CD-ROM or any other form of storage medium known to those skilled in the art.
上述处理器702例如可以是中央处理器(central processing unit，CPU)、通用处理 器、数字信号处理器(digital signal processor，DSP)、专用集成电路The aforementioned processor 702 may be, for example, a central processing unit (CPU), a general-purpose processor, a digital signal processor (digital signal processor, DSP), or an application specific integrated circuit.
(application-specific integrated circuit，ASIC)、现场可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、晶体管逻辑器件、硬件部件或者其任意组合。其可以实现或执行结合本申请公开内容所描述的各种示例性的逻辑方框，模块和电路。处理器也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，DSP和微处理器的组合等等。(application-specific integrated circuit, ASIC), field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination of computing functions, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and so on.
上述通信接口703例如可以是接口卡等，可以为以太(ethernet)接口或异步传输模式(asynchronous transfer mode，ATM)接口。The above-mentioned communication interface 703 may be, for example, an interface card or the like, and may be an ethernet interface or an asynchronous transfer mode (ATM) interface.
本申请实施例还提供了一种计算机可读存储介质，包括指令，当其在计算机上运行时，使得计算机执行上述车道中心线确定方法。The embodiment of the present application also provides a computer-readable storage medium, including instructions, which when run on a computer, cause the computer to execute the above-mentioned method for determining the lane centerline.
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等(如果存在)是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、***、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects, without having to use To describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in a sequence other than the content illustrated or described herein. In addition, the terms "including" and "having" and any variations of them are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those clearly listed. Those steps or units may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or equipment.
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的***，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that, for the convenience and conciseness of the description, the specific working process of the above-described system, device, and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.
在本申请所提供的几个实施例中，应该理解到，所揭露的***，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，单元的划分，仅仅为一种逻辑业务划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。In the several embodiments provided in this application, it should be understood that the disclosed system, device, and method may be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of units is only a logical business division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or integrated. To another system, or some features can be ignored, or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
另外，在本申请各个实施例中的各业务单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件业务单元的形式实现。In addition, the service units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software business unit.
集成的单元如果以软件业务单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例方法的全部或部分步骤。 而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。If the integrated unit is implemented in the form of a software business unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes. .
本领域技术人员应该可以意识到，在上述一个或多个示例中，本发明所描述的业务可以用硬件、软件、固件或它们的任意组合来实现。当使用软件实现时，可以将这些业务存储在计算机可读介质中或者作为计算机可读介质上的一个或多个指令或代码进行传输。计算机可读介质包括计算机存储介质和通信介质，其中通信介质包括便于从一个地方向另一个地方传送计算机程序的任何介质。存储介质可以是通用或专用计算机能够存取的任何可用介质。Those skilled in the art should be aware that, in one or more of the foregoing examples, the services described in the present invention can be implemented by hardware, software, firmware, or any combination thereof. When implemented by software, these services can be stored in a computer-readable medium or transmitted as one or more instructions or codes on the computer-readable medium. The computer-readable medium includes a computer storage medium and a communication medium, where the communication medium includes any medium that facilitates the transfer of a computer program from one place to another. The storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.
以上的具体实施方式，对本发明的目的、技术方案和有益效果进行了进一步详细说明，所应理解的是，以上仅为本发明的具体实施方式而已。The above specific implementations further describe the objectives, technical solutions, and beneficial effects of the present invention in further detail. It should be understood that the above are only specific implementations of the present invention.
以上，以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。Above, the above embodiments are only used to illustrate the technical solutions of the present application, not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, a person of ordinary skill in the art should understand that it can still implement the foregoing various implementations. The technical solutions described in the examples are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims (18)

  1. 一种车道中心线确定方法，其特征在于，所述方法包括：A method for determining the centerline of a lane, wherein the method includes:
    获取位于目标车辆周围的车辆的行驶轨迹点，行驶轨迹点表示车辆行驶过程中的位置信息；Obtain the driving trajectory points of the vehicles located around the target vehicle, and the driving trajectory points represent the position information of the vehicle during driving;
    根据每两个在时间上相邻且属于同一个车辆的行驶轨迹点分别确定对应的直线；Determine the corresponding straight line according to every two trajectory points that are adjacent in time and belong to the same vehicle;
    根据各条直线对应的方程参数确定目标方程参数；Determine the target equation parameters according to the equation parameters corresponding to each straight line;
    根据所述目标方程参数确定车道中心线。Determine the lane centerline according to the target equation parameters.
  2. 根据权利要求1所述的方法，其特征在于，各条直线对应的方程参数包括斜率，所述目标方程参数包括目标斜率，所述根据各条直线对应的方程参数确定目标方程参数包括：The method according to claim 1, wherein the equation parameter corresponding to each straight line comprises a slope, the target equation parameter comprises a target slope, and the determining the target equation parameter according to the equation parameter corresponding to each straight line comprises:
    将各条直线对应的方程参数包括的斜率的均值确定为所述目标斜率。The average value of the slope included in the equation parameter corresponding to each straight line is determined as the target slope.
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述目标方程参数确定车道中心线包括：The method according to claim 2, wherein the determining the center line of the lane according to the target equation parameters comprises:
    获取所述目标车辆的位置信息；Acquiring location information of the target vehicle;
    根据所述目标斜率和所述目标车辆的位置信息确定所述目标车辆所在车道的车道中心线。Determine the lane center line of the lane where the target vehicle is located according to the target slope and the location information of the target vehicle.
  4. 根据权利要求3所述的方法，其特征在于，所述方法还包括：The method according to claim 3, wherein the method further comprises:
    根据所述目标车辆所在车道的车道中心线以及预设车道宽度，得到所述目标车辆所在车道相邻车道的车道中心线。According to the lane center line of the lane where the target vehicle is located and the preset lane width, the lane center lines of the adjacent lanes of the lane where the target vehicle is located are obtained.
  5. 根据权利要求1所述的方法，其特征在于，各条直线对应的方程参数包括斜率和截距，所述目标方程参数包括目标斜率和目标截距，所述根据各条直线对应的方程参数确定目标方程参数包括：The method according to claim 1, wherein the equation parameters corresponding to each straight line include slope and intercept, the target equation parameters include target slope and target intercept, and the equation parameters are determined according to the corresponding equation parameters of each straight line. The target equation parameters include:
    将各条直线对应的方程参数包括的斜率的均值确定为所述目标斜率；Determining the mean value of the slope included in the equation parameter corresponding to each straight line as the target slope;
    对各条直线对应的方程参数包括的截距进行聚类得到所述目标截距；Clustering the intercept included in the equation parameters corresponding to each straight line to obtain the target intercept;
    所述根据所述目标方程参数确定车道中心线包括：The determining the lane center line according to the target equation parameters includes:
    将根据所述目标斜率和所述目标截距确定的直线作为车道中心线。A straight line determined according to the target slope and the target intercept is used as the center line of the lane.
  6. 根据权利要求5所述的方法，其特征在于，所述对各条直线对应的方程参数包括的截距进行聚类得到所述目标截距包括：The method according to claim 5, wherein the clustering the intercept included in the equation parameter corresponding to each straight line to obtain the target intercept comprises:
    选取所述各条直线对应的方程参数中未被标记的其中一个截距作为初始中心点；Selecting one of the unmarked intercepts in the equation parameters corresponding to each straight line as the initial center point;
    从所述各条直线对应的方程参数中确定与所述初始中心点的差值的绝对值小于或等于第一阈值的截距，并对所述与所述初始中心点的差值的绝对值小于或等于第一阈值的截距和所述初始中心点进行标记；Determine the intercept that the absolute value of the difference with the initial center point is less than or equal to the first threshold from the equation parameters corresponding to each straight line, and compare the absolute value of the difference with the initial center point Marking an intercept less than or equal to the first threshold and the initial center point;
    将所述初始中心点与所述各条直线对应的方程参数中每个截距之间的差值之和确定为移动距离，并将所述初始中心点与所述移动距离之和作为新的初始中心点执行上述步骤，以进行迭代，直到所述移动距离小于或等于第二阈值，并将在所述移动距离小于或等于第二阈值时对应的初始中心点作为候选中心点加入候选中心点集；The sum of the difference between each intercept in the equation parameters corresponding to the initial center point and each of the straight lines is determined as the moving distance, and the sum of the initial center point and the moving distance is taken as the new The initial center point performs the above steps to iterate until the moving distance is less than or equal to the second threshold, and when the moving distance is less than or equal to the second threshold, the corresponding initial center point is added as a candidate center point to the candidate center point set;
    再次执行上述步骤以进行迭代，得到新的候选中心点；Perform the above steps again to iterate and obtain a new candidate center point;
    在迭代的过程中，若所述新的候选中心点与候选中心集中的候选中心点之间的差值均 大于或等于第三阈值，则将所述新的候选中心点加入所述候选中心点集，否则丢弃所述候选中心集中与所述新的候选中心点之间的差值小于所述第三阈值的候选中心点，并将所述新的候选中心点加入所述候选中心点集中；In the iterative process, if the difference between the new candidate center point and the candidate center points in the candidate center set is greater than or equal to the third threshold, the new candidate center point is added to the candidate center point Otherwise, discard the candidate center points whose difference between the candidate center point and the new candidate center point is less than the third threshold, and add the new candidate center point to the candidate center point set;
    将所述候选中心点集中的候选中心点确定为所述目标截距。The candidate center point in the set of candidate center points is determined as the target intercept.
  7. 根据权利要求1-6任一项所述的方法，其特征在于，所述根据所述目标方程参数确定车道中心线包括：The method according to any one of claims 1 to 6, wherein the determining the lane center line according to the target equation parameters comprises:
    获取最近一次用于确定车道中心线的最终方程参数，并根据所述最近一次用于确定车道中心线的最终方程参数和本次确定的目标方程参数，确定本次的最终方程参数；Acquire the last equation parameter used to determine the lane centerline the last time, and determine the final equation parameter this time according to the last equation parameter used to determine the lane centerline and the target equation parameter determined this time;
    根据本次的最终方程参数确定车道中心线。Determine the lane centerline according to the final equation parameters this time.
  8. 根据权利要求5-6任一项所述的方法，其特征在于，若所述车道中心线为多条，则所述方法还包括：The method according to any one of claims 5-6, wherein if there are multiple lane centerlines, the method further comprises:
    将所述多条车道中心线中相邻两条车道中心线的宽度在预设宽度范围内的车道中心线确定为目标车道中心线。The centerline of the lane in which the centerlines of two adjacent lanes of the plurality of lane centerlines have a width within a preset width range is determined as the centerline of the target lane.
  9. 一种车道中心线确定装置，其特征在于，所述装置包括：A device for determining the centerline of a lane, characterized in that the device comprises:
    获取单元，用于获取位于目标车辆周围的车辆的行驶轨迹点，行驶轨迹点表示车辆行驶过程中的位置信息；The acquiring unit is used to acquire the driving track points of the vehicles located around the target vehicle, and the driving track points represent position information during the driving of the vehicle;
    第一确定单元，用于根据每两个在时间上相邻且属于同一个车辆的行驶轨迹点分别确定对应的直线；The first determining unit is configured to determine a corresponding straight line according to every two driving trajectory points that are adjacent in time and belong to the same vehicle;
    第二确定单元，用于根据各条直线对应的方程参数确定目标方程参数；The second determining unit is used to determine the target equation parameter according to the equation parameter corresponding to each straight line;
    第三确定单元，用于根据所述目标方程参数确定车道中心线。The third determining unit is used to determine the center line of the lane according to the target equation parameters.
  10. 根据权利要求9所述的装置，其特征在于，各条直线对应的方程参数包括斜率，所述目标方程参数包括目标斜率，所述第二确定单元具体用于：The device according to claim 9, wherein the equation parameter corresponding to each straight line includes a slope, the target equation parameter includes a target slope, and the second determining unit is specifically configured to:
    将所述方程参数中各个斜率的均值确定为所述目标斜率。The average value of each slope in the equation parameters is determined as the target slope.
  11. 根据权利要求10所述的装置，其特征在于，所述第三确定单元包括：The device according to claim 10, wherein the third determining unit comprises:
    位置信息获取子单元，用于获取所述目标车辆的位置信息；A location information acquisition sub-unit for acquiring the location information of the target vehicle;
    第三确定子单元，用于根据所述目标斜率和所述目标车辆的位置信息确定所述目标车辆所在车道的车道中心线。The third determining subunit is configured to determine the lane center line of the lane where the target vehicle is located according to the target slope and the position information of the target vehicle.
  12. 根据权利要求11所述的装置，其特征在于，所述装置还包括：The device according to claim 11, wherein the device further comprises:
    获得单元，用于根据所述目标车辆所在车道的车道中心线以及预设车道宽度，得到所述目标车辆所在车道相邻车道的车道中心线。The obtaining unit is configured to obtain the lane center lines of the adjacent lanes of the lane where the target vehicle is located according to the lane centerline of the lane where the target vehicle is located and the preset lane width.
  13. 根据权利要求9所述的装置，其特征在于，各条直线对应的方程参数包括斜率和截距，所述目标方程参数包括目标斜率和目标截距，所述第二确定单元包括：The device according to claim 9, wherein the equation parameters corresponding to each straight line include a slope and an intercept, the target equation parameters include a target slope and a target intercept, and the second determining unit includes:
    目标斜率确定子单元，用于将各条直线对应的方程参数包括的斜率的均值确定为所述目标斜率；The target slope determination subunit is used to determine the average value of the slope included in the equation parameters corresponding to each straight line as the target slope;
    目标截距获得子单元，用于对各条直线对应的方程参数包括的截距进行聚类得到所述目标截距；The target intercept obtaining subunit is used to cluster the intercepts included in the equation parameters corresponding to each straight line to obtain the target intercept;
    所述第三确定单元具体用于：The third determining unit is specifically configured to:
    将根据所述目标斜率和所述目标截距确定的直线作为车道中心线。A straight line determined according to the target slope and the target intercept is used as the center line of the lane.
  14. 根据权利要求13所述的装置，其特征在于，所述目标截距获得子单元包括：The apparatus according to claim 13, wherein the target intercept obtaining subunit comprises:
    选取子单元，用于选取所述各条直线对应的方程参数中未被标记的其中一个截距作为初始中心点；A selection subunit for selecting one of the unmarked intercepts in the equation parameters corresponding to each straight line as the initial center point;
    标记子单元，用于从所述各条直线对应的方程参数中确定与所述初始中心点的差值的绝对值小于或等于第一阈值的截距，并对所述与所述初始中心点的差值的绝对值小于或等于第一阈值的截距和所述初始中心点进行标记；The marking subunit is used to determine from the equation parameters corresponding to each straight line that the absolute value of the difference with the initial center point is less than or equal to the intercept of the first threshold, and to compare the difference with the initial center point The intercept with the absolute value of the difference less than or equal to the first threshold and the initial center point for marking;
    第一迭代子单元，用于将所述初始中心点与所述各条直线对应的方程参数中每个截距之间的差值之和确定为移动距离，并将所述初始中心点与所述移动距离之和作为新的初始中心点执行上述步骤，以进行迭代，直到所述移动距离小于或等于第二阈值，并将在所述移动距离小于或等于第二阈值时对应的初始中心点作为候选中心点加入候选中心点集；The first iterative subunit is used to determine the sum of the difference between each intercept in the equation parameters corresponding to the initial center point and each of the straight lines as the moving distance, and to compare the initial center point with the The sum of the moving distances is used as the new initial center point. The above steps are performed to iterate until the moving distance is less than or equal to the second threshold, and the corresponding initial center point is set when the moving distance is less than or equal to the second threshold. Join the candidate center point set as a candidate center point;
    第二迭代子单元，用于再次执行上述步骤以进行迭代，得到新的候选中心点；The second iteration subunit is used to perform the above steps again to iterate to obtain a new candidate center point;
    中心点确定子单元，用于在迭代的过程中，若所述新的候选中心点与候选中心集中的候选中心点之间的差值均大于或等于第三阈值，则将所述新的候选中心点加入所述候选中心点集，否则丢弃所述候选中心集中与所述新的候选中心点之间的差值小于所述第三阈值的候选中心点，并将所述新的候选中心点加入所述候选中心点集中；The center point determination subunit is used to, in the iterative process, if the difference between the new candidate center point and the candidate center points in the candidate center set is greater than or equal to the third threshold, then the new candidate The center point is added to the candidate center point set, otherwise, the candidate center point whose difference between the candidate center set and the new candidate center point is less than the third threshold is discarded, and the new candidate center point is discarded. Join the candidate center point collection;
    目标截距确定子单元，用于将所述候选中心点集中的候选中心点确定为所述目标截距。The target intercept determination subunit is configured to determine the candidate center point in the candidate center point set as the target intercept.
  15. 根据权利要求9-14任一项所述的装置，其特征在于，所述第三确定单元包括：The device according to any one of claims 9-14, wherein the third determining unit comprises:
    方程参数确定子单元，用于获取最近一次用于确定车道中心线的最终方程参数，并根据所述最近一次用于确定车道中心线的最终方程参数和本次确定的目标方程参数，确定本次的最终方程参数；The equation parameter determination subunit is used to obtain the last final equation parameter used to determine the lane center line, and determine this time according to the last final equation parameter used to determine the lane center line and the target equation parameter determined this time The final equation parameters;
    车道中心线确定子单元，用于根据本次的最终方程参数确定车道中心线。The lane centerline determination subunit is used to determine the lane centerline according to the final equation parameters this time.
  16. 根据权利要求13-14任一项所述的装置，其特征在于，若所述车道中心线为多条，则所述装置还包括：The device according to any one of claims 13-14, wherein if there are multiple lane centerlines, the device further comprises:
    第四确定单元，用于将所述多条车道中心线中相邻两条车道中心线的宽度在预设宽度范围内的车道中心线确定为目标车道中心线。The fourth determining unit is configured to determine the centerline of the lane in which the centerlines of two adjacent lanes of the plurality of lane centerlines have a width within a preset width range as the centerline of the target lane.
  17. 一种车道中心线确定设备，其特征在于，所述设备包括存储器、处理器；A device for determining the centerline of a lane, wherein the device includes a memory and a processor;
    所述存储器，用于存储指令；The memory is used to store instructions;
    所述处理器，用于执行所述存储器中的所述指令，执行权利要求1-8任意一项所述的方法。The processor is configured to execute the instructions in the memory, and execute the method according to any one of claims 1-8.
  18. 一种计算机可读存储介质，包括指令，当其在计算机上运行时，使得所述计算机执行以上权利要求1-8任意一项所述的方法。A computer-readable storage medium, including instructions, which when run on a computer, cause the computer to execute the method of any one of claims 1-8.
PCT/CN2020/100046 2019-09-02 2020-07-03 Method and device for determining lane centerline WO2021042856A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910823629.9 2019-09-02
CN201910823629.9A CN112441022B (en) 2019-09-02 2019-09-02 Lane center line determining method and device

Publications (1)

Publication Number Publication Date
WO2021042856A1 true WO2021042856A1 (en) 2021-03-11

Family

ID=74734980

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/100046 WO2021042856A1 (en) 2019-09-02 2020-07-03 Method and device for determining lane centerline

Country Status (2)

Country Link
CN (1) CN112441022B (en)
WO (1) WO2021042856A1 (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113848899A (en) * 2021-09-22 2021-12-28 中国第一汽车股份有限公司 Vehicle transverse control method, device, equipment and storage medium
CN114291086A (en) * 2021-12-31 2022-04-08 高德软件有限公司 Lane center line generation method and device and computer storage medium
CN114291116A (en) * 2022-01-24 2022-04-08 广州小鹏自动驾驶科技有限公司 Method and device for predicting track of surrounding vehicle, vehicle and storage medium
CN115457767A (en) * 2022-08-30 2022-12-09 同济大学 Lane information extraction method based on crowdsourcing motor vehicle track
CN116101327A (en) * 2023-04-14 2023-05-12 北京集度科技有限公司 Driving path planning method, device, vehicle and storage medium
CN117036541A (en) * 2023-09-18 2023-11-10 腾讯科技（深圳）有限公司 Lane center line generation method, lane center line generation device, electronic equipment and storage medium
CN117128976A (en) * 2023-10-26 2023-11-28 小米汽车科技有限公司 Method and device for acquiring road center line, vehicle and storage medium

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113721602B (en) * 2021-07-28 2024-04-05 广州小鹏汽车科技有限公司 Reference line processing method, device, equipment and storage medium
CN114771518B (en) * 2022-04-06 2023-08-01 北京百度网讯科技有限公司 Lane center guide wire generation method and device, electronic equipment and medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106056100A (en) * 2016-06-28 2016-10-26 重庆邮电大学 Vehicle auxiliary positioning method based on lane detection and object tracking
US20170259819A1 (en) * 2016-03-14 2017-09-14 Honda Motor Co., Ltd. Vehicle control system, vehicle control method, and vehicle control program
CN107229908A (en) * 2017-05-16 2017-10-03 浙江理工大学 A kind of method for detecting lane lines
CN109816981A (en) * 2019-02-20 2019-05-28 百度在线网络技术（北京）有限公司 A kind of automatic Pilot method, apparatus and storage medium
CN109871752A (en) * 2019-01-04 2019-06-11 北京航空航天大学 A method of lane line is extracted based on monitor video detection wagon flow

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102010020984A1 (en) * 2010-04-20 2011-10-20 Conti Temic Microelectronic Gmbh Method for determining the road course for a motor vehicle
CN109829351B (en) * 2017-11-23 2021-06-01 华为技术有限公司 Method and device for detecting lane information and computer readable storage medium
CN108898672A (en) * 2018-04-27 2018-11-27 厦门维斯云景信息科技有限公司 A kind of semi-automatic cloud method making three-dimensional high-definition mileage chart lane line
CN109271857A (en) * 2018-08-10 2019-01-25 广州小鹏汽车科技有限公司 A kind of puppet lane line elimination method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170259819A1 (en) * 2016-03-14 2017-09-14 Honda Motor Co., Ltd. Vehicle control system, vehicle control method, and vehicle control program
CN106056100A (en) * 2016-06-28 2016-10-26 重庆邮电大学 Vehicle auxiliary positioning method based on lane detection and object tracking
CN107229908A (en) * 2017-05-16 2017-10-03 浙江理工大学 A kind of method for detecting lane lines
CN109871752A (en) * 2019-01-04 2019-06-11 北京航空航天大学 A method of lane line is extracted based on monitor video detection wagon flow
CN109816981A (en) * 2019-02-20 2019-05-28 百度在线网络技术（北京）有限公司 A kind of automatic Pilot method, apparatus and storage medium

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113848899A (en) * 2021-09-22 2021-12-28 中国第一汽车股份有限公司 Vehicle transverse control method, device, equipment and storage medium
CN114291086A (en) * 2021-12-31 2022-04-08 高德软件有限公司 Lane center line generation method and device and computer storage medium
CN114291086B (en) * 2021-12-31 2023-05-23 高德软件有限公司 Lane center line generation method and device and computer storage medium
CN114291116A (en) * 2022-01-24 2022-04-08 广州小鹏自动驾驶科技有限公司 Method and device for predicting track of surrounding vehicle, vehicle and storage medium
CN114291116B (en) * 2022-01-24 2023-05-16 广州小鹏自动驾驶科技有限公司 Surrounding vehicle track prediction method and device, vehicle and storage medium
CN115457767A (en) * 2022-08-30 2022-12-09 同济大学 Lane information extraction method based on crowdsourcing motor vehicle track
CN115457767B (en) * 2022-08-30 2023-08-29 同济大学 Lane information extraction method based on crowdsourcing machine motor car track
CN116101327A (en) * 2023-04-14 2023-05-12 北京集度科技有限公司 Driving path planning method, device, vehicle and storage medium
CN117036541A (en) * 2023-09-18 2023-11-10 腾讯科技（深圳）有限公司 Lane center line generation method, lane center line generation device, electronic equipment and storage medium
CN117036541B (en) * 2023-09-18 2024-01-12 腾讯科技（深圳）有限公司 Lane center line generation method, lane center line generation device, electronic equipment and storage medium
CN117128976A (en) * 2023-10-26 2023-11-28 小米汽车科技有限公司 Method and device for acquiring road center line, vehicle and storage medium
CN117128976B (en) * 2023-10-26 2024-03-12 小米汽车科技有限公司 Method and device for acquiring road center line, vehicle and storage medium

Also Published As

Publication number Publication date
CN112441022A (en) 2021-03-05
CN112441022B (en) 2023-02-03

Similar Documents

Publication Publication Date Title
WO2021042856A1 (en) Method and device for determining lane centerline
CN106407893B (en) A kind of method, apparatus and equipment detecting lane line
CN109829351B (en) Method and device for detecting lane information and computer readable storage medium
CN111540201B (en) Vehicle queuing length real-time estimation method and system based on roadside laser radar
CN110929655B (en) Lane line identification method in driving process, terminal device and storage medium
JP2018194912A (en) Obstacle on-road detection device, method and program
CN103310435B (en) Combine vertical projection and optimal path the method split characters on license plate
CN113297881B (en) Target detection method and related device
JP2018147399A (en) Target detection device
CN112927283A (en) Distance measuring method and device, storage medium and electronic equipment
CN107480592B (en) Multi-lane detection method and tracking method
Alpar et al. Intelligent collision warning using license plate segmentation
CN114662600A (en) Lane line detection method and device and storage medium
EP3522073A1 (en) Method and apparatus for detecting road surface marking
CN112902911B (en) Ranging method, device, equipment and storage medium based on monocular camera
CN113176562A (en) Multi-target tracking method and device, electronic equipment and readable storage medium
CN112949489A (en) Road boundary identification method and device, electronic equipment and storage medium
JP6962726B2 (en) Track recognition device
JP2020020690A (en) Vehicle position estimating device
CN115526053A (en) Road modeling method, device and equipment
JP5682302B2 (en) Traveling road estimation device, method and program
Lu et al. A vision-based system for the prevention of car collisions at night
CN115717899B (en) Curve path selection method and device
CN113920163B (en) Moving target detection method based on combination of traditional and deep learning
WO2021166893A1 (en) Target object recognition device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20861729

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20861729

Country of ref document: EP

Kind code of ref document: A1