CN113968229A - Road area determination method and device and electronic equipment - Google Patents
Road area determination method and device and electronic equipment Download PDFInfo
- Publication number
- CN113968229A CN113968229A CN202111439468.7A CN202111439468A CN113968229A CN 113968229 A CN113968229 A CN 113968229A CN 202111439468 A CN202111439468 A CN 202111439468A CN 113968229 A CN113968229 A CN 113968229A
- Authority
- CN
- China
- Prior art keywords
- road
- marker
- markers
- group
- information
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 239000003550 marker Substances 0.000 claims abstract description 253
- 238000012545 processing Methods 0.000 claims description 26
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 238000002372 labelling Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 239000013598 vector Substances 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 206010039203 Road traffic accident Diseases 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 238000012805 post-processing Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 239000003292 glue Substances 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000002390 adhesive tape Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method and a device for determining a road area and electronic equipment, and relates to the technical field of automatic driving, wherein the method comprises the following steps: acquiring road network information of a target road based on preset map information; the road network information comprises an indication line of a specified road structure on a target road; detecting a marker on a target road, and determining characteristic information of the marker according to the relative position between the marker and the indicating line; classifying the markers based on the characteristic information of the markers to obtain at least one marker group; the marker classes in each marker set are the same; and for each marker group, determining a road area corresponding to the marker group according to the position of the marker in the group on the target road. By the method, the vehicle can automatically identify the road areas formed by the markers, so that the vehicle is controlled to avoid the road areas, the vehicle is prevented from passing through the markers, and the driving safety of the automatic driving vehicle is improved.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a road area determining method and device and electronic equipment.
Background
In a road on which vehicles travel, temporary areas where vehicles cannot pass, such as a road maintenance area, an area to be cleaned, a traffic accident area, etc., often occur. These zones may be marked by markers such as traffic cones, guardrails, water horses, warning lines, etc. that border the zone. These markers are usually loosely placed, with a large distance between two adjacent markers. For an autonomous vehicle, the vehicle can recognize the markers placed in the road, but it is difficult to recognize the areas formed by the markers, so that the vehicle can avoid the markers, but cannot avoid the areas, for example, the vehicle may pass between the markers and enter the areas to drive, so that the driving risk of the autonomous vehicle is high.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus and an electronic device for determining a road area, so as to prevent a vehicle from passing between markers and reduce the driving risk of an autonomous vehicle.
In a first aspect, an embodiment of the present invention provides a method for determining a road area, where the method includes: acquiring road network information of a target road based on preset map information; the road network information comprises an indication line of a specified road structure on a target road; detecting a marker on a target road, and determining characteristic information of the marker according to the relative position between the marker and the indicating line; classifying the markers based on the characteristic information of the markers to obtain at least one marker group; the marker classes in each marker set are the same; and for each marker group, determining a road area corresponding to the marker group according to the position of the marker in the group on the target road.
The step of obtaining the road network information of the target road based on the preset map information includes: determining a road in the specified range as a target road by taking the position of the current vehicle as a reference; acquiring marking information on a target road from the map information; the marking information comprises lane information, road edge information and stop line information; and generating an indicating line for specifying a road structure based on the labeling information, and determining the indicating line for specifying the road structure as the road network information of the target road.
The specified road structure comprises lanes; the lane information in the labeling information comprises lane central lines and the connection relation between the lane central lines; the step of generating an indication line specifying a road structure based on the labeling information includes: and connecting the lane central lines based on the connection relation to obtain the lane indicating lines.
The step of determining the feature information of the marker based on the relative position between the marker and the lane indication line includes: and determining the shortest distance between the marker and each indicating line aiming at each marker, and taking the shortest distance between the marker and each indicating line as the characteristic information of the marker.
The step of classifying the markers based on the feature information of the markers to obtain at least one marker group includes: and performing first clustering processing on the markers in a mean shift mode based on the characteristic information of the markers to obtain at least one marker group.
After the step of classifying the markers based on the feature information of the markers to obtain at least one marker group, the method further includes: for each marker group, judging whether the marker in the marker group blocks a specified lane on a target road; the designated lanes comprise lanes which are in the same driving direction and are parallel to each other on the target road; and if the specified lane on the target road is blocked, deleting the marker group.
After the step of classifying the markers based on the feature information of the markers to obtain at least one marker group, the method further includes: aiming at each marker group, carrying out second clustering treatment on the markers in the marker group according to the distance between the markers in the marker group to obtain at least one marker group; the marker classes in each marker subset are the same; and determining at least one group of marker subgroups corresponding to each marker group as the updated at least one marker group.
The step of determining the road region corresponding to the group of markers based on the position of the markers in the group on the target road includes: according to the position of the marker in the group on the target road, carrying out line connection processing on the marker to obtain a boundary line of the road area; the area surrounded by the boundary line is determined as a road area.
The step of obtaining the boundary line of the road area by performing the link processing on the markers according to the positions of the markers in the group on the target road includes: sequencing the markers along the vehicle running direction of the lane where the markers are located to obtain a sequencing result; and performing line connection processing on the markers based on the sequencing result to obtain a boundary line of the road area.
The road areas comprise a plurality of road areas; after the step of determining the road region corresponding to the set of markers according to the positions of the markers in the set on the target road, the method further comprises: performing third clustering processing on the road areas according to the road network information of the target road to obtain at least one area group; the road region categories in each region group are the same; and merging the road areas in the same area group to obtain a merged road area.
The road areas comprise a plurality of road areas; after the step of determining the road region corresponding to the set of markers according to the positions of the markers in the set on the target road, the method further comprises: obstacle information on the target road is generated based on the road area, and the travel route of the current vehicle is controlled based on the obstacle information.
In a second aspect, an embodiment of the present invention further provides an apparatus for determining a road area, where the apparatus includes: the information acquisition module is used for acquiring road network information of a target road based on preset map information; the road network information comprises an indication line of a specified road structure on a target road; the detection module is used for detecting the marker on the target road and determining the characteristic information of the marker according to the relative position between the marker and the indicating line; the classification module is used for classifying the markers based on the characteristic information of the markers to obtain at least one marker group; the marker classes in each marker set are the same; and the area determining module is used for determining the road area corresponding to the group of the markers according to the positions of the markers in the group on the target road aiming at each marker group.
In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a memory, where the memory stores machine executable instructions capable of being executed by the processor, and the processor executes the machine executable instructions to implement the method for determining a road area.
In a fourth aspect, embodiments of the present invention provide a machine-readable storage medium storing machine-executable instructions which, when invoked and executed by a processor, cause the processor to implement the above-mentioned method for determining a road region.
The embodiment of the invention has the following beneficial effects:
the method, the device and the electronic equipment for determining the road area acquire the road network information of the target road based on the preset map information; the road network information comprises an indication line of a specified road structure on a target road; detecting a marker on a target road, and determining characteristic information of the marker according to the relative position between the marker and the indicating line; classifying the markers based on the characteristic information of the markers to obtain at least one marker group; the marker classes in each marker set are the same; and for each marker group, determining a road area corresponding to the marker group according to the position of the marker in the group on the target road. In the above manner, after the road network information of the road is acquired from the road map, the feature information of the markers on the road is determined based on the road network information, and then the markers are classified based on the feature information, so as to finally obtain the road regions.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for determining a road area according to an embodiment of the present invention;
fig. 2 is a schematic diagram of obtaining road network information of a target road according to an embodiment of the present invention;
fig. 3 is a schematic diagram of determining characteristic information of a marker according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a marker classification process according to an embodiment of the present invention;
fig. 5 is a schematic diagram illustrating a road region corresponding to a determined marker set according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an apparatus for determining a road area according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, temporary impassable areas often exist on the road where vehicles run, the areas are generally bounded by traffic cones, guardrails, water horses, guard lines, adhesive tapes and the like, and the structures of the areas are relatively loose, for example, gaps which can be penetrated by vehicles usually exist on the boundaries of temporary construction operation areas, but the conventional detection method in an automatic driving system is difficult to identify the temporary impassable areas as a whole, and the vehicles are in danger of changing lanes and penetrating the gaps of obstacles.
Based on the above, the road area determination method, the road area determination device and the electronic device provided by the embodiments of the present invention may be applied to an autonomous vehicle, and may also be applied to scenes such as vehicle navigation and map recognition.
To facilitate understanding of the present embodiment, a method for determining a road area disclosed in the present embodiment of the invention is first described in detail, where the method for determining a road area includes the following steps:
step S102, acquiring road network information of a target road based on preset map information; the road network information comprises an indication line of a specified road structure on a target road;
the map information may be obtained from a mapping system. The method comprises the steps that a high-precision map can be preset in an automatic driving vehicle system, the map is different from a common navigation electronic map, the absolute coordinate precision of the high-precision map is higher, the map layer of the high-precision map comprises a lane-level road network map layer, the lane-level road network map layer mainly describes accurate three-dimensional representation of a road network and stores the three-dimensional representation as structured data, and the data mainly comprises road data and fixed object information around a lane; wherein the road data includes: the geometry of the road surface, lane line type, etc., for example: solid, dashed, single, double; lane line colors, for example: white, yellow, etc.; the road data may also include data attributes for each lane, such as: slope, curvature, course, elevation, etc.; the fixed object information around the lane includes: the map information has high precision and good real-time performance, and also contains detailed lane models, road component information and some road attribute information related to traffic safety, such as: the area where the GPS signal disappears, the road construction state, and the like.
Acquiring road network information of a target road based on the map information, wherein the road network information comprises an indicating line of a specified road structure on the target road; the specified road structure may include one or more of a lane, a curb, and a stop line. The road network information may further include road traffic information, weather information, construction work information, traffic accident information, information on serious damage of road facilities, and the like. According to the related icon labels in the map information, the road network information of the target road can be identified and extracted from the map information. The target road here is understood to be a road within a specified range ahead during the travel of the vehicle.
Step S104, detecting a marker on the target road, and determining characteristic information of the marker according to the relative position between the marker and the indicating line;
in real road conditions, temporary impassable areas such as road maintenance areas, areas to be cleaned, traffic accident areas and the like often appear on roads, the areas are marked by markers such as traffic cones, guardrails, water horses, warning line glue and the like, when an automatic driving vehicle runs on the roads, the markers on a target road need to be detected so as to select a correct and safe route, and the detection of the markers on the target road can be realized in various ways, such as: the method comprises the steps of collecting a road image of a current road through a camera, identifying a marker from the road image through an image identification algorithm, or collecting radar data of the current road through a laser radar, and identifying the position of a marker through processing the radar data.
Usually, a plurality of markers are required for forming a road area, and the markers of the same road area are regularly arranged, for example, arranged around one or more indication lines, or arranged along a certain indication line. Based on this, in the present embodiment, the characteristic information of each marker is determined according to the relative position between the marker and the indication line. For example, the characteristic information of the marker is determined according to the distance between the marker and each of the indication lines in the vicinity, or the characteristic information of the marker is determined according to the relative direction between the marker and each of the indication lines.
In a specific implementation manner, after a marker on a target road is detected, according to a position of an indicator in road network information, a shortest distance from the marker to each indicator is determined, and a feature vector is established, where a dimension of the feature vector is equal to the number of the indicators in the road network information, for example: when a certain marker is located at a position with three indicating lines, determining the shortest distances d1, d2 and d3 from the marker to the three indicating lines, constructing a feature vector based on a central line by using the shortest distances [ d1, d2 and d3], when a plurality of markers exist, and so on, establishing the feature vector by using the same method for each marker, and combining the detected feature vectors of at least one marker to determine the feature information of the marker.
Step S106, classifying the markers based on the characteristic information of the markers to obtain at least one marker group; the marker classes in each marker set are the same;
for example, the markers with similar characteristic information can be understood as the markers which are closer to each other, or the markers which are arranged along the same indication line. Therefore, the markers whose characteristic information is closer are generally markers for forming the same road area. Based on this, the markers with similar characteristic information can enter the same marker group, or the characteristic information of the markers of the same marker group is relatively close.
In an optional manner, clustering processing may be performed on the markers in a mean shift manner to obtain at least one marker group. Mean shift clustering is an algorithm based on sliding windows that attempts to find dense regions of data points; the method is based on a centroid algorithm, and realizes the positioning of the central point of each group or each class by updating the candidate point of the central point to the mean value of the points in a sliding window. These candidate windows are then filtered in a post-processing stage to eliminate approximate duplicates, forming a final set of center points and their corresponding groups. When the markers are classified by the mean shift algorithm, the marker class in each marker group is the same.
Each marker group corresponds to a temporary impassable road area, post-processing is needed after the marker group is obtained, and in a scene with more complex road network information, clustering error results are easy to occur, such as: and (4) the clustering result cannot cover a complete road area, the marker in the group blocks a specified road on a target road, and the like, and the marker group is deleted according to the clustering error result.
In addition, it is necessary to perform a second clustering on the marker groups that are clustered correctly, further cluster the similar markers in each marker group according to the distance between the markers to obtain a marker group, and update the original marker group with the marker group to narrow the range of the target region.
Step S108, aiming at each marker group, determining a road area corresponding to the marker group according to the position of the marker in the group on the target road.
Specifically, the markers are classified based on the mean shift method to obtain a marker group, and after the wrong clustering result is deleted, the positions of the markers in the group on the road are determined. There are various implementations of determining the location of markers within a group on a road, for example: a coordinate system may be established in the road network information, the position of the marker may be represented by coordinates, the position of the marker may be sensed by a sensor, and the like, and then the markers in the group are sequentially connected according to their positions on the road, so as to obtain a boundary line of the road area, where the area surrounded by the boundary line is the road area corresponding to the group.
In another alternative, the markers are processed by a data-driven machine learning algorithm, specifically, the machine learning model may analyze the markers in the marker group by an unsupervised learning method to find the position relationship between the markers, and then draw a road region on the target road based on the position relationship between the markers.
The method, the device and the electronic equipment for determining the road area acquire the road network information of the target road based on the preset map information; wherein, the road network information comprises an indication line of a specified road structure on the target road; detecting a marker on the target road, and determining characteristic information of the marker according to the relative position between the marker and the indication line; classifying the markers based on the characteristic information of the markers to obtain at least one marker group; the markers in each of the marker sets are of the same type; and for each marker group, determining the road area corresponding to the marker group according to the position of the marker in the group on the target road. According to the method, after the road network information of the road is acquired from the road map, the characteristic information of the markers on the road is determined based on the road network information, the markers are classified based on the characteristic information, and finally the road regions are obtained.
The following embodiments provide a specific implementation manner for obtaining road network information of a target road.
Specifically, a road in a specified range is determined as a target road by taking the position of the current vehicle as a reference; acquiring the marking information on the target road from the map information; the marking information comprises lane information, road edge information and stop line information; and generating an indicating line for specifying a road structure based on the labeling information, and determining the indicating line for specifying the road structure as the road network information of the target road.
The current position of the vehicle may be determined by a variety of positioning methods, for example: navigation and Positioning are carried out through a GPS (Global Positioning System) or IMU (Inertial Measurement Unit) sensor, and Positioning is carried out through laser radar point cloud characteristics or environment characteristics of a high-precision map; the road characteristic identification through the camera is referred to the GPS positioning data for positioning and the like. A road within a specified range ahead of the vehicle may be determined as the target road according to the traveling direction of the current vehicle.
A complete road is usually composed of many separate road segments, each of which may have many different geometries, which may be represented by road reference lines, including: geometric elements such as straight lines, curves and arcs are added on the basis of the road reference line, and the lane line and other characteristics on the road are added to form a section of road. A specified range may be preset in an autonomous vehicle system to determine a target road, for example: when the specified range is 2 kilometers, the road with the current position of the automatic driving vehicle within 2 kilometers as the center is the target road.
After a target road is determined, acquiring marking information on the target road from the map information; the marking information comprises lane information, road edge information, stop line information, flow guide line information and the like; the marking information is composed of various elements such as lines, arrows, characters, elevation marks, prominent road signs and contour marks marked on the road surface, and transmits traffic information such as indication, limitation, warning and the like to a driver. For example: on roads near schools, whistling prohibition marks are arranged to warn passing vehicles that whistling is prohibited.
After the labeled information on the target road is acquired, the system generates an indicating line for specifying a road structure through a preset data format, wherein the indicating line is used for indicating a vehicle to run in a correct direction and comprises the following steps: straight line indicator, left turn indicator, right turn indicator, etc.
Considering that the arrangement of the markers on the boundary of the road area is mostly related to the road network structure, for example, the arrangement of the traffic cones on the boundary of the construction area generally extends along the road direction, in the above embodiment, the labeled information such as the motor lane, the stop line, the road edge, etc. within a certain range with the current position of the automatic driving vehicle as the center is obtained based on the semantic map service, and the labeled information can better describe the approximate road network structure within the driving range of the current vehicle as the reference for the road area estimation.
The following embodiments provide an implementation of an indicator line specifying a road structure.
In a specific implementation manner, the specified road structure includes a lane; the lane information in the marking information comprises lane central lines and the connection relation between the lane central lines; and connecting the lane center lines based on the connection relation to obtain the indication line of the lane.
There are various types of lanes, for example: the lane type can be judged by the driver through the marking information on the road, and the driver can select the correct lane to drive. In one embodiment, the lane information in the labeling information includes lane center lines, which are provided on the lane center lines, not limited to the geometric center lines of roads, and are used to segment the markings of the traffic flow traveling in the same direction. Wherein, the lane central line includes: a central dotted line, a central single solid line, a central double solid line, and a central dashed solid line. The lane information also comprises a connection relation between lane central lines, the connection relation expresses the connectivity between lanes, and the navigation application can know which of the preorder and the successor of the current lane through the lane connection relation stored in the data, so that the functions of lane guidance, lane calculation and the like are completed by utilizing the information.
In real road conditions, each road is divided into multiple lane sections, each lane section can have different lane line numbers and lane line widths, referring to fig. 2, taking an intersection as an example, multiple motor lane sections exist, each motor lane center line has an entrance and an exit, the entrance and the exit are taken as motor lane connection points, each motor lane connection point can be connected with a connection point of at least one section of motor lane center line, the connection relation of the lane center lines can be obtained by combining traffic rules and labeled information on the road, and then the lane center lines are connected according to the connection relation, so as to generate lane indication lines, for example: straight line indicator, left turn indicator, right turn indicator, etc.
The following embodiments provide a specific implementation of determining characteristic information of a marker.
Specifically, for each marker, the shortest distance between the marker and each indication line is determined, and the shortest distance between the marker and each indication line is used as the characteristic information of the marker. The above marker includes: traffic cones, guardrails, water horses, warning line glue and the like, and when temporary impassable areas such as maintenance areas, areas to be cleaned, traffic accident areas and the like appear on a road, the area boundaries are usually marked by the markers. After the automatic driving vehicle detects the marker, the shortest distance between the marker and each indicating line is calculated, and then the characteristic information of the marker is determined.
For ease of understanding, fig. 3 shows an example of determining characteristic information of a single marker. The road network information includes 9 sections of lane lines, and in one mode, based on the traffic rules and the connection relations, 4 indication lines can be obtained, which are respectively expressed as: an indicator line C0: L4- > L2- > L0, an indicator line C1: L4- > L5- > L6, an indicator line C2: L4- > L7- > L8, and an indicator line C3: L1- > L3- > L8. Due to the fact that repeated lane lines exist in the structure of the indication lines, actually only the shortest distances from the obstacles to L3 and L4 need to be calculated to obtain d0 and d1, and then the feature vectors based on the center lines are constructed according to the shortest distances, in the figure, the shortest distances from the markers to C0, C1, C2 and C3 are d1, d1, d1 and d0 respectively, so that the feature vectors of the markers are [ d1, d1, d1 and d0 ]. By analogy, feature vectors are constructed in the same way for each marker, the dimensions of the feature vectors being equal to the number of centerlines present in the local road network. Similarly, according to the information of the curb, the stop line and the like existing in the local map information, a feature vector can be constructed and combined into the feature information of the final marker.
The following example provides a specific implementation of the classification process for markers, as shown in fig. 4.
And performing first clustering processing on the markers in a mean shift mode based on the characteristic information of the markers to obtain at least one marker group. Specifically, a certain marker is randomly selected as a center, a circular sliding window with a radius r as a core is used as a center, and the mean shift algorithm is a hill-climbing algorithm and comprises the steps of iteratively moving to a higher-density area in each step until convergence; in each iteration, the sliding window moves to a higher density region by moving the center point to the mean of the points within the window. The density within the sliding window is proportional to the number of points within it. Naturally, by moving towards the mean of the points within the window, it will gradually move towards regions of higher point density; the sliding window continues to move as a mean until there is no direction to accommodate more points within the kernel. Move this circle until the density no longer increases; the foregoing process is accomplished through a number of sliding windows until all points are within one window. When multiple sliding windows overlap, the window containing the most points is retained. And then clustering according to the sliding window where the data points are located to obtain at least one marker group.
In one mode, after at least one marker group is obtained, whether a marker in the marker group blocks a designated lane on the target road or not is judged for each marker group; the designated lanes comprise lanes which are in the same driving direction and are parallel to each other on the target road; and if the specified lane on the target road is blocked, deleting the marker group.
In a scene with complex road network information, markers in a certain marker group may block all lanes in a certain driving direction, and in an actual road scene, the situation is usually not allowed to occur in order to keep normal traffic running. In view of the above situation, it is necessary to determine whether the designated lanes on the target road are blocked by the markers in the marker group, where the designated lanes include lanes in the same driving direction and parallel to each other on the target road, and if the designated lanes on the target road are blocked, the marker group may be regarded as a wrongly-classified marker group and is not trusted. The marker set is the error data, and the marker set is deleted.
In another mode, after at least one marker group is obtained, for each marker group, second clustering treatment is performed on the markers in the marker group according to the distance between the markers in the marker group, so as to obtain at least one marker group; the marker classes in each marker subset are the same; and determining the at least one group of marker groups corresponding to each marker group as the updated at least one marker group. When the marker group is determined to be a correct result, in order to make the region range of the marker group more accurate, a second clustering process is required to be performed according to the distance between markers in each marker group, and similar markers are clustered to obtain at least one group of marker groups, so as to perform more detailed classification on the markers in the same marker group. For example: on a certain lane, scattered roads needing to be maintained exist at a plurality of positions, each road needing to be maintained is provided with at least one marker as an area boundary, a plurality of marker groups needing to be maintained on the lane can be obtained through first clustering processing, in order to enable the area to be more accurate, the markers in the same marker group need to be clustered for the second time, and therefore the finally obtained road area is smaller and finer. Specifically, each marker group at least obtains one marker group, and the original marker group is updated by at least one marker group corresponding to each marker group. The range of the target region is narrowed down through the second clustering, so that the range of the target region is more accurate.
The following embodiments provide a way of generating a road region, as shown in fig. 5.
According to the position of the marker in the group on the target road, carrying out line connection processing on the marker to obtain a boundary line of a road area; the area surrounded by the boundary line is determined as a road area. For the markers in the updated marker group, determining the position of each marker on the road, and there are various implementations of determining the position of the marker on the road, for example: establishing a coordinate system in the road network information, and expressing the position of each marker by using coordinates; the position of the marker on the road can also be sensed by a sensor. And sequentially connecting the markers in the group according to the positions of the markers on the road in sequence to obtain a boundary line of a road area. The boundary line may be regular or irregular. The area surrounded by the boundary line is the road area. A plurality of road regions can be obtained by connecting the markers in each marker group by the above method.
The following provides a way of generating a road region boundary line.
Sequencing the markers along the vehicle running direction of the lane where the markers are located to obtain a sequencing result; and performing line connection processing on the markers based on the sequencing result to obtain a boundary line of the road area.
Specifically, after the position of the marker on the road is determined, the driving direction of the vehicle in the lane where the marker is located is also determined, the markers are sorted along the driving direction of the vehicle to obtain a sorting result, and the markers are sequentially connected in sequence based on the sorting result to further obtain the boundary line of the road area. Therefore, the markers can be connected in the same area, and damage caused when a vehicle enters a gap in the middle of the markers is avoided. In an actual road scene, the placement of the markers is usually gradually changed along the vehicle driving direction, so that the driver gradually adjusts the driving lane.
In one implementation, the road area includes a plurality of road areas; performing third clustering processing on the road areas according to the road network information of the target road to obtain at least one area group; the road region categories in each region group are the same; and merging the road areas in the same area group to obtain a merged road area. Since the vehicle passes through a plurality of roads during traveling, it is necessary to perform a third clustering process on a plurality of road regions that the vehicle may select, based on the road network information, with respect to the destination of the vehicle. For example: the method comprises the steps that a plurality of temporary impassable road areas exist at an intersection exit and after a right turn, the position of each marker in a marker group at the intersection on a road is determined based on the method, a road area corresponding to the marker group is obtained, an automatic driving vehicle can select to avoid the road area, at the moment, the subsequent road, namely, the right turn road area needs to be subjected to third clustering processing according to road network information on a target road, at least one area group is obtained, wherein the road areas in each area group are the same in type, and the road areas in the same area group are combined to obtain a road area with connectivity. Therefore, the vehicles can avoid the impassable area on the temporary impassable roads.
In another implementation, the road area includes a plurality of road areas; and generating obstacle information on the target road based on the road area, and controlling the running route of the current vehicle based on the obstacle information. After the road area is obtained, obstacle information on the target road is generated in the map information or the navigation information, and before the vehicle runs to the road area, the route can be adjusted in time based on the obstacle information, the vehicle is controlled to select the correct running route, accidents caused by wrong decision making are avoided, and the driving safety is improved.
According to the method for determining the road area, the road obstacles identified by the detection module in the automatic driving system are connected into the road area through clustering and rule-based post-processing based on the priori knowledge and semantic map labeling, gaps among the obstacles are filled and output to the decision module, and therefore danger caused by the fact that vehicles drive into the road area is avoided. According to the method, the characteristics of the construction area in the automatic driving scene are analyzed, based on the obstacle detection and semantic map service in the automatic driving system, the estimation of the road area boundary is realized by using a method based on the prior rule, the capability of the automatic driving system for processing similar scenes can be improved, and the wrong driving path is avoided.
For the above method embodiment, referring to fig. 6, a road area determining apparatus includes:
an information obtaining module 60, configured to obtain road network information of a target road based on preset map information; wherein, the road network information comprises an indication line of a specified road structure on the target road;
a detection module 62, configured to detect a marker on the target road, and determine feature information of the marker according to a relative position between the marker and the indication line;
a classification module 64, configured to perform classification processing on the markers based on the feature information of the markers to obtain at least one marker group; the markers in each of the marker sets are of the same type;
and an area determining module 66, configured to determine, for each of the marker groups, a road area corresponding to the marker group according to a position of the marker in the group on the target road.
The device for determining the road area acquires road network information of a target road based on preset map information; the road network information comprises an indication line of a specified road structure on a target road; detecting a marker on a target road, and determining characteristic information of the marker according to the relative position between the marker and the indicating line; classifying the markers based on the characteristic information of the markers to obtain at least one marker group; the marker classes in each marker set are the same; and for each marker group, determining a road area corresponding to the marker group according to the position of the marker in the group on the target road. In the above manner, after the road network information of the road is acquired from the road map, the feature information of the markers on the road is determined based on the road network information, and then the markers are classified based on the feature information, so as to finally obtain the road regions.
The information obtaining module is further configured to: determining a road in the specified range as a target road by taking the position of the current vehicle as a reference; acquiring marking information on a target road from the map information; the marking information comprises lane information, road edge information and stop line information; and generating an indicating line for specifying a road structure based on the labeling information, and determining the indicating line for specifying the road structure as the road network information of the target road.
The specified road structure comprises lanes; the lane information in the marking information comprises lane central lines and the connection relation between the lane central lines; the information obtaining module is further configured to: and connecting the lane central lines based on the connection relation to obtain the lane indicating lines.
The detection module is further configured to: and determining the shortest distance between the marker and each indication line aiming at each marker, and taking the shortest distance between the marker and each indication line as the characteristic information of the marker.
The classification module is further configured to: and performing first clustering processing on the markers in a mean shift mode based on the characteristic information of the markers to obtain at least one marker group.
The above-mentioned device still includes: a determination module configured to: for each marker group, judging whether the marker in the marker group blocks the designated lane on the target road; the designated lanes comprise lanes which are in the same driving direction and are parallel to each other on the target road; and if the specified lane on the target road is blocked, deleting the marker group.
The above-mentioned device still includes: an update module to: for each marker group, carrying out second clustering treatment on the markers in the marker group according to the distance between the markers in the marker group to obtain at least one marker group; the marker classes in each marker subset are the same; and determining the at least one marker group corresponding to each marker group as the updated at least one marker group.
The area determining module is further configured to: according to the position of the marker in the group on the target road, carrying out line connection processing on the marker to obtain a boundary line of a road area; the area surrounded by the boundary line is determined as a road area.
The area determining module is further configured to: sequencing the markers along the vehicle running direction of the lane where the markers are located to obtain a sequencing result; and performing line connection processing on the markers based on the sequencing result to obtain a boundary line of the road area.
The road areas comprise a plurality of road areas; the above-mentioned device still includes: a merging module to: performing third clustering processing on a plurality of road areas according to the road network information of the target road to obtain at least one area group; the road region categories in each region group are the same; and merging the road areas in the same area group to obtain a merged road area.
The road areas comprise a plurality of road areas; the above-mentioned device still includes: an obstacle information generation module to: and generating obstacle information on the target road based on the road area, and controlling the running route of the current vehicle based on the obstacle information.
The embodiment also provides an electronic device, which comprises a processor and a memory, wherein the memory stores machine executable instructions capable of being executed by the processor, and the processor executes the machine executable instructions to realize the method for determining the road area.
Referring to fig. 7, the electronic device includes a processor 100 and a memory 101, where the memory 101 stores machine executable instructions capable of being executed by the processor 100, and the processor 100 executes the machine executable instructions to implement the above-mentioned road area determination method.
Further, the electronic device shown in fig. 7 further includes a bus 102 and a communication interface 103, and the processor 100, the communication interface 103, and the memory 101 are connected through the bus 102.
The Memory 101 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used. The bus 102 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 7, but this does not indicate only one bus or one type of bus.
Embodiments of the present invention further provide a machine-readable storage medium, where machine-executable instructions are stored, and when the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to implement the method for determining a road area.
The method, the apparatus, and the computer program product of the electronic device for determining a road area provided in the embodiments of the present invention include a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiments, and specific implementation may refer to the method embodiments, and will not be described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood in specific cases for those skilled in the art.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that the following embodiments are merely illustrative of the present invention, and not restrictive, and the scope of the present invention is not limited thereto: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (14)
1. A method of determining a road region, the method comprising:
acquiring road network information of a target road based on preset map information; wherein the road network information comprises an indicator line of a specified road structure on the target road;
detecting a marker on the target road, and determining characteristic information of the marker according to the relative position between the marker and the indicating line;
classifying the markers based on the characteristic information of the markers to obtain at least one marker group; the marker classes in each of the marker sets are the same;
and for each marker group, determining a road area corresponding to the marker group according to the position of the marker in the group on the target road.
2. The method according to claim 1, wherein the step of obtaining road network information of the target road based on the preset map information comprises:
determining a road in the specified range as a target road by taking the position of the current vehicle as a reference;
acquiring marking information on the target road from the map information; the marking information comprises lane information, road edge information and stop line information;
and generating an indicating line of the specified road structure based on the labeling information, and determining the indicating line of the specified road structure as the road network information of the target road.
3. The method of claim 2, wherein the specified road structure comprises a lane; the lane information in the marking information comprises lane central lines and the connection relation between the lane central lines;
the step of generating an indication line of the specified road structure based on the labeling information includes: and connecting the lane central lines based on the connection relation to obtain an indication line of the lane.
4. The method according to claim 1, characterized in that the step of determining feature information of the marker from the relative position between the marker and the lane indication line comprises:
and determining the shortest distance between the marker and each indicating line for each marker, and taking the shortest distance between the marker and each indicating line as the characteristic information of the marker.
5. The method according to claim 1, wherein the step of classifying the markers based on the feature information of the markers to obtain at least one marker group comprises:
and performing first clustering processing on the markers in a mean shift mode based on the characteristic information of the markers to obtain at least one marker group.
6. The method of claim 1, wherein after the step of classifying the markers based on the feature information of the markers to obtain at least one marker group, the method further comprises:
for each marker group, judging whether the marker in the marker group blocks the designated lane on the target road; the designated lanes comprise lanes which are in the same driving direction on the target road and are parallel to each other;
and if the specified lane on the target road is blocked, deleting the marker group.
7. The method of claim 1, wherein after the step of classifying the markers based on the feature information of the markers to obtain at least one marker group, the method further comprises:
for each marker group, carrying out second clustering treatment on the markers in the marker group according to the distance between the markers in the marker group to obtain at least one marker group; the marker classes in each of the marker sub-groups are the same;
and determining the at least one group of marker subsets corresponding to each marker group as the updated at least one marker group.
8. The method of claim 1, wherein the step of determining the road region corresponding to the set of markers based on the position of the markers in the set on the target road comprises:
according to the position of the marker in the group on the target road, carrying out line connection processing on the marker to obtain a boundary line of a road area;
and determining the surrounding area of the boundary line as the road area.
9. The method according to claim 8, wherein the step of performing a link processing on the markers in the group according to the positions of the markers on the target road to obtain the boundary lines of the road area comprises:
sequencing the markers along the vehicle running direction of the lane where the markers are located to obtain a sequencing result;
and performing line connection processing on the markers based on the sequencing result to obtain a boundary line of the road area.
10. The method of claim 1, wherein the road region comprises a plurality; after the step of determining the road region corresponding to the group of markers according to the positions of the markers in the group on the target road, the method further includes:
performing third clustering processing on the road areas according to the road network information of the target road to obtain at least one area group; the road region types in each region group are the same;
and merging the road areas in the same area group to obtain a merged road area.
11. The method of claim 1, wherein the road region comprises a plurality; after the step of determining the road region corresponding to the group of markers according to the positions of the markers in the group on the target road, the method further includes:
and generating obstacle information on the target road based on the road area, and controlling the running route of the current vehicle based on the obstacle information.
12. An apparatus for determining a road area, the apparatus comprising:
the information acquisition module is used for acquiring road network information of a target road based on preset map information; wherein the road network information comprises an indicator line of a specified road structure on the target road;
the detection module is used for detecting a marker on the target road and determining the characteristic information of the marker according to the relative position between the marker and the indicating line;
the classification module is used for classifying the markers based on the characteristic information of the markers to obtain at least one marker group; the marker classes in each of the marker sets are the same;
and the region determining module is used for determining the road region corresponding to each marker group according to the position of the marker in the group on the target road.
13. An electronic device comprising a processor and a memory, the memory storing machine executable instructions executable by the processor, the processor executing the machine executable instructions to implement the method of determining a road region of any of claims 1-11.
14. A machine-readable storage medium having stored thereon machine-executable instructions which, when invoked and executed by a processor, cause the processor to carry out the method of determining a roadway area of any one of claims 1-11.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111439468.7A CN113968229A (en) | 2021-11-30 | 2021-11-30 | Road area determination method and device and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111439468.7A CN113968229A (en) | 2021-11-30 | 2021-11-30 | Road area determination method and device and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113968229A true CN113968229A (en) | 2022-01-25 |
Family
ID=79590389
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111439468.7A Pending CN113968229A (en) | 2021-11-30 | 2021-11-30 | Road area determination method and device and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113968229A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115050003A (en) * | 2022-05-30 | 2022-09-13 | 广州文远知行科技有限公司 | Traffic cone line detection method, device, equipment and storage medium |
CN117826174A (en) * | 2024-02-04 | 2024-04-05 | 名商科技有限公司 | Driving dynamic positioning method and system |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140063232A1 (en) * | 2012-09-05 | 2014-03-06 | Google Inc. | Construction Zone Sign Detection |
WO2014115563A1 (en) * | 2013-01-28 | 2014-07-31 | 日本電気株式会社 | Driving support device, driving support method, and recording medium storing driving support program |
US20140309833A1 (en) * | 2013-04-10 | 2014-10-16 | Google Inc. | Mapping active and inactive construction zones for autonomous driving |
CN110926487A (en) * | 2018-09-19 | 2020-03-27 | 阿里巴巴集团控股有限公司 | Driving assistance method, driving assistance system, computing device, and storage medium |
CN111380543A (en) * | 2018-12-29 | 2020-07-07 | 沈阳美行科技有限公司 | Map data generation method and device |
CN111967384A (en) * | 2020-08-17 | 2020-11-20 | 上海眼控科技股份有限公司 | Vehicle information processing method, device, equipment and computer readable storage medium |
US20200401823A1 (en) * | 2019-06-19 | 2020-12-24 | DeepMap Inc. | Lidar-based detection of traffic signs for navigation of autonomous vehicles |
CN112668153A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device and equipment for generating automatic driving simulation scene |
CN113178091A (en) * | 2021-05-12 | 2021-07-27 | 中移智行网络科技有限公司 | Safe driving area method, device and network equipment |
-
2021
- 2021-11-30 CN CN202111439468.7A patent/CN113968229A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140063232A1 (en) * | 2012-09-05 | 2014-03-06 | Google Inc. | Construction Zone Sign Detection |
WO2014115563A1 (en) * | 2013-01-28 | 2014-07-31 | 日本電気株式会社 | Driving support device, driving support method, and recording medium storing driving support program |
US20140309833A1 (en) * | 2013-04-10 | 2014-10-16 | Google Inc. | Mapping active and inactive construction zones for autonomous driving |
CN110926487A (en) * | 2018-09-19 | 2020-03-27 | 阿里巴巴集团控股有限公司 | Driving assistance method, driving assistance system, computing device, and storage medium |
CN111380543A (en) * | 2018-12-29 | 2020-07-07 | 沈阳美行科技有限公司 | Map data generation method and device |
US20200401823A1 (en) * | 2019-06-19 | 2020-12-24 | DeepMap Inc. | Lidar-based detection of traffic signs for navigation of autonomous vehicles |
CN111967384A (en) * | 2020-08-17 | 2020-11-20 | 上海眼控科技股份有限公司 | Vehicle information processing method, device, equipment and computer readable storage medium |
CN112668153A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device and equipment for generating automatic driving simulation scene |
CN113178091A (en) * | 2021-05-12 | 2021-07-27 | 中移智行网络科技有限公司 | Safe driving area method, device and network equipment |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115050003A (en) * | 2022-05-30 | 2022-09-13 | 广州文远知行科技有限公司 | Traffic cone line detection method, device, equipment and storage medium |
CN117826174A (en) * | 2024-02-04 | 2024-04-05 | 名商科技有限公司 | Driving dynamic positioning method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102083909B1 (en) | Automatic extraction method for lane data information for autonomous driving vehicles based on point cloud map | |
CN109641589B (en) | Route planning for autonomous vehicles | |
US10431094B2 (en) | Object detection method and object detection apparatus | |
KR102595897B1 (en) | Method and apparatus of determining road line | |
RU2661963C1 (en) | Device for calculating route of motion | |
KR102069666B1 (en) | Real time driving route setting method for autonomous driving vehicles based on point cloud map | |
JP6654923B2 (en) | Map information output device | |
CN113968229A (en) | Road area determination method and device and electronic equipment | |
TWI493513B (en) | Lane departure warning system and lane identification apparatus and related method thereof | |
CN112325896B (en) | Navigation method, navigation device, intelligent driving equipment and storage medium | |
KR20170097435A (en) | Apparatus and method for decision making for right turn in intersection for autonomous driving system | |
CN107003136B (en) | Information processing apparatus | |
CN113597396A (en) | On-road positioning method and apparatus using road surface characteristics | |
JP5499815B2 (en) | Driving road estimation system | |
CN112781600A (en) | Vehicle navigation method, device and storage medium | |
JP2021082286A (en) | System and method for improving lane change detection, and non-temporary computer-readable medium | |
CN113156923B (en) | Road data generation, navigation and running control method, device, equipment and medium | |
CN114763999A (en) | Map generation device, map generation method, and computer program for map generation | |
JP2016180797A (en) | Road information generation device and program | |
CN115257815A (en) | Planning method and device for automatically driving automobile to turn right and terminal equipment | |
KR20220136679A (en) | Apparatus and method for controlling driving of vehicle | |
CN113178091A (en) | Safe driving area method, device and network equipment | |
JP5888275B2 (en) | Road edge detection system, method and program | |
JP2018025898A (en) | Indication recognition device and vehicle control device | |
JP2017072550A (en) | Own vehicle location recognition device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220125 |
|
RJ01 | Rejection of invention patent application after publication |