CN116052126A - Method and device for detecting drivable area, vehicle and storage medium - Google Patents
Method and device for detecting drivable area, vehicle and storage medium Download PDFInfo
- Publication number
- CN116052126A CN116052126A CN202310085745.1A CN202310085745A CN116052126A CN 116052126 A CN116052126 A CN 116052126A CN 202310085745 A CN202310085745 A CN 202310085745A CN 116052126 A CN116052126 A CN 116052126A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- line
- lane
- information
- area
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method and a device for detecting a drivable area, a vehicle and a computer readable storage medium, and relates to the technical field of auxiliary driving, wherein the method comprises the following steps: acquiring lane line information and obstacle information in front of a host vehicle; determining a lane center line according to the lane line information; determining a drivable area in front of the host vehicle according to projections of the obstacles in the obstacle information on the target vertical line; dividing the drivable region according to the minimum transverse drivable region of the host vehicle to obtain a longitudinal drivable region in front of the host vehicle; the method and the device have the advantages that the division of the drivable area and the outline of the obstacle are strongly correlated, the flexibility of division of the drivable area is met, the problem of algorithm operation efficiency is solved, the problem of large calculation amount of grid area operation is solved, the area is divided by taking the center line of the lane as a reference line in a mode that the outline of the obstacle is projected to the perpendicular line of the center line, and curve and straight road scenes can be effectively met.
Description
Technical Field
The present invention relates to the field of assisted driving technologies, and in particular, to a method and apparatus for detecting a drivable region, a vehicle, and a computer readable storage medium.
Background
In advanced driving assistance systems (Advanced Driving Assistance System, ADAS) of vehicles, it is necessary to detect running environment information in front of the vehicle, such as a drivable region of the vehicle, in order to safely perform assisted driving. The travelable region is generally represented in two ways: collision free space and grid area; the collision free space is typically represented by its boundary, which encloses an area between the host vehicle and one or more detected objects. The grid area is formed by dividing an area in front of the vehicle into one grid area by a grid map, and then marking the grid where the obstacle is located with the obstacle.
In the prior art, the grid area is very important for selecting the size of the grid, the identification of the drivable area is inaccurate due to the fact that the grid is too large, the operation amount is large due to the fact that the grid is too small, and the performance requirement on a processor (such as a CPU) is high. Therefore, how to provide an accurate detection method for the drivable area, which solves the problem of large calculation amount of grid area operation, and gives consideration to the flexibility of the drivable area, is an urgent problem to be solved nowadays.
Disclosure of Invention
The invention aims to provide a method and a device for detecting a drivable area, a vehicle and a computer readable storage medium, so as to solve the problem of large calculation amount of grid area operation and give consideration to the flexibility of the drivable area.
In order to solve the above technical problems, the present invention provides a method for detecting a drivable area, including:
acquiring lane line information and obstacle information in front of a host vehicle; the lane line information comprises lane line data of a current lane where the host vehicle is located and lane line data of a neighboring lane of the current lane, and the obstacle information comprises obstacle transverse width and position information of each obstacle;
determining a lane center line according to the lane line information;
determining a drivable area in front of the host vehicle according to the projection of each obstacle in the obstacle information on a target vertical line; wherein the target vertical line is a vertical line on the lane central line;
and dividing the drivable region according to the minimum transverse drivable region of the host vehicle to obtain a longitudinal drivable region in front of the host vehicle.
Optionally, the determining the drivable area in front of the host vehicle according to the projection of each obstacle in the obstacle information on the target vertical line includes:
determining a travelable area according to the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle in the obstacle information on a target vertical line and the transverse width of the travelable area corresponding to the lane line information; wherein the position information includes the longitudinal position.
Optionally, the determining the drivable area according to the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle in the obstacle information on the target vertical line, and the lateral width of the drivable area corresponding to the lane line information includes:
sequencing the obstacles according to the longitudinal position of each obstacle in the obstacle information from small to large to obtain a queue corresponding to each obstacle;
according to the sequencing order of the queues, sequentially projecting obstacles on target line segments on the target vertical line to determine target non-projected line segments corresponding to the queues; the target line segments are projection line segments corresponding to the transverse width of the drivable area on the target vertical line, and target non-projection line segments corresponding to the queues are not overlapped;
and determining the drivable area according to the target non-projected line segments and the longitudinal positions corresponding to the queues.
Optionally, the determining the drivable area according to the target non-projected line segments and the longitudinal positions corresponding to the queues respectively includes:
if the current queue is the 1 st queue, determining a drivable area between the host vehicle and the 1 st queue according to the transverse width of the drivable area and the longitudinal position corresponding to the 1 st queue;
If the current queue is the ith queue, determining a travelable area between the ith queue and the ith queue according to the difference between a target non-projected line segment corresponding to the ith queue and a longitudinal position corresponding to the ith queue; wherein i is a positive integer greater than 1 and less than or equal to n, n being the number of queues;
if the current queue is the nth queue, determining a travelable area in front of the nth queue according to the target non-projected line segment and the longitudinal position corresponding to the nth queue.
Optionally, the sorting the obstacles according to the order from small to large according to the longitudinal position of each obstacle in the obstacle information, to obtain a queue corresponding to each obstacle, includes:
sequencing the obstacles according to the longitudinal position of each obstacle in the obstacle information from small to large to obtain an obstacle sequencing sequence;
and determining the corresponding queues of the obstacles in turn according to the obstacle ordering sequence and the longitudinal distance threshold of the queues.
Optionally, the step of sequentially performing obstacle projection on the target line segments on the target vertical line according to the sorting order of the queues, and determining the target non-projected line segments corresponding to each queue includes:
Projecting an obstacle in the current queue on the target vertical line, and determining an un-projected line segment corresponding to the current queue on the target vertical line; the projection line segment corresponding to the current queue is in the target line segment;
if an overlapped line segment exists between the non-projected line segment corresponding to the current queue and the current non-projected line segment in the target line segment, the overlapped line segment is used as a target non-projected line segment corresponding to the current queue, and the projected line segment corresponding to the current queue on the target vertical line is used for updating the current non-projected line segment;
and if no overlapped line segment exists between the non-projected line segment corresponding to the current queue and the current non-projected line segment in the target line segment, the target non-projected line segment corresponding to the current queue is empty.
Optionally, the dividing the drivable area according to the minimum lateral drivable area of the host vehicle, to obtain a longitudinal drivable area in front of the host vehicle, includes:
dividing the travelable area according to the minimum transverse travelable area and the obstacle longitudinal speed in the obstacle information to obtain a longitudinal travelable area in front of the host vehicle; wherein, the longitudinal travelable area is marked with the corresponding obstacle travel speed information.
The invention also provides a device for detecting the drivable area, which comprises:
the information acquisition module is used for acquiring lane line information and obstacle information in front of the host vehicle; the lane line information comprises lane line data of a current lane where the host vehicle is located and lane line data of a neighboring lane of the current lane, and the obstacle information comprises obstacle transverse width and position information of each obstacle;
the lane determining module is used for determining a lane center line according to the lane line information;
the area determining module is used for determining a travelable area in front of the host vehicle according to the projection of each obstacle in the obstacle information on a target vertical line; wherein the target vertical line is a vertical line on the lane central line;
the area dividing module is used for dividing the drivable area according to the minimum transverse drivable area of the host vehicle and obtaining the longitudinal drivable area in front of the host vehicle.
The invention also provides a vehicle comprising:
a memory for storing a computer program;
and a processor for implementing the method for detecting a travelable region as described above when executing the computer program.
Furthermore, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method for detecting a travelable region as described above.
The invention provides a detection method of a drivable area, which comprises the following steps: acquiring lane line information and obstacle information in front of a host vehicle; the lane line information comprises lane line data of a current lane where a host vehicle is located and lane line data of an adjacent lane of the current lane, and the obstacle information comprises obstacle transverse width and position information of each obstacle; determining a lane center line according to the lane line information; determining a drivable area in front of the host vehicle according to projections of the obstacles in the obstacle information on the target vertical line; the target vertical line is a vertical line on the lane central line; dividing the drivable region according to the minimum transverse drivable region of the host vehicle to obtain a longitudinal drivable region in front of the host vehicle;
therefore, the method and the device determine the drivable area in front of the host vehicle according to the transverse width of the drivable area and the projection of each obstacle on the target vertical line in the obstacle information, and strongly correlate the division of the drivable area with the contour of the obstacle, so that the method and the device not only meet the flexibility of division of the drivable area and have the problem of algorithm operation efficiency, solve the problem of large calculation amount of grid area operation, but also divide the area by taking the center line of the lane as a reference line and adopting the projection mode of the contour of the obstacle to the vertical line of the center line, thereby effectively meeting curve and straight road scenes and improving the detection applicability of the drivable area. In addition, the invention also provides a detection device for the drivable area, a vehicle and a computer readable storage medium, and the detection device has the same beneficial effects.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for detecting a travelable region according to an embodiment of the present invention;
FIG. 2 is a flowchart of another method for detecting a travelable region according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a driving area division of another driving area detection method according to an embodiment of the present invention;
FIG. 4 is an output schematic diagram of the longitudinal travelable regions of the travelable region division shown in FIG. 3;
FIG. 5 is a schematic diagram of a driving area division of another driving area detection method according to an embodiment of the present invention;
FIG. 6 is an output schematic diagram of the longitudinal travelable regions of the travelable region division shown in FIG. 5;
FIG. 7 is a schematic diagram of a driving area division of another driving area detection method according to an embodiment of the present invention;
FIG. 8 is an output schematic diagram of the longitudinal travelable regions of the travelable region division shown in FIG. 7;
FIG. 9 is a block diagram of a device for detecting a travelable region according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of a vehicle according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a flowchart of a method for detecting a travelable region according to an embodiment of the present invention. The method may include:
step 101: acquiring lane line information and obstacle information in front of a host vehicle; the lane line information comprises lane line data of a current lane where the host vehicle is located and lane line data of a neighboring lane of the current lane, and the obstacle information comprises obstacle transverse width and position information of each obstacle.
It is to be understood that the host vehicle in the present embodiment may be a vehicle that performs the detection of the drivable region. The lane line information in the embodiment may be information related to a lane line in front of the host vehicle, such as information related to a lane line in front of the traveling direction of the host vehicle collected by a sensing device provided on the host vehicle. For the specific content of the lane line information in the embodiment, the designer may set the lane line information according to the practical scenario and the user requirement, for example, the lane line information includes the lane line data of the current lane (i.e. the current lane) and the lane line data of the adjacent lane, so as to determine the maximum range in which the host vehicle can travel.
Correspondingly, the obstacle information in this embodiment may be information related to an obstacle (such as other vehicles) in front of the host vehicle, such as information related to an obstacle in front of the traveling direction of the host vehicle, which is collected by a sensing device provided on the host vehicle. For the specific content of the obstacle information in the embodiment, the designer may set the obstacle information according to the practical scene and the user requirement, for example, the obstacle information includes the lateral width of each obstacle, that is, the width of each obstacle on the lane where each obstacle is located; the obstacle information may also include position information of each obstacle, such as a longitudinal position with respect to the host vehicle; the obstacle information may also include obstacle travel speed information such as speed and acceleration of each obstacle. The present embodiment does not impose any limitation on this.
Accordingly, a sensing device, such as a camera, a range finder, and/or a velocimeter, for collecting lane information and obstacle information in front of the traveling direction of the host vehicle may be provided on the host vehicle.
It should be noted that, the method for detecting a drivable region provided in this embodiment may be applied to a host vehicle, for example, the processor of the host vehicle may execute the method provided in this embodiment, and detect and obtain a longitudinal drivable region in front of the host vehicle by using lane line information and obstacle information acquired by the sensing device of the host vehicle; the method for detecting the drivable region provided in the embodiment may also be applied to a server, for example, a processor of a cloud server communicatively connected to a host vehicle may execute the method provided in the embodiment, and detect and obtain the longitudinal drivable region in front of the host vehicle by using lane line information and obstacle information collected by sensing equipment of the host vehicle. The present embodiment does not impose any limitation on this.
Specifically, for the specific mode of the processor in this embodiment for obtaining the lane line information and the obstacle information in front of the host vehicle, the processor may be set by the designer according to the practical scenario and the user requirement, for example, the processor of the host vehicle may use the sensing device set on the host vehicle to obtain the lane line information and the obstacle information in front of the host vehicle in the same or similar manner as the lane line and the obstacle detection method in the prior art; or the processor of the cloud server may receive lane line information and obstacle information sent by the host vehicle in front of the host vehicle. The present embodiment does not impose any limitation on this.
Step 102: and determining the lane center line according to the lane line information.
The lane center line in this embodiment may be a center line of a lane in front of the host vehicle, such as a center line of a current lane in which the host vehicle is located.
It will be appreciated that the processor in this step may calculate the lane centerline from lane line information in front of the host vehicle. The specific manner of determining the lane center line by the processor according to the lane line information in this step may be set by the designer, for example, may be implemented in the same manner or in a similar manner to the lane center line detection method in the prior art, which is not limited in this embodiment.
Step 103: determining a drivable area in front of the host vehicle according to projections of the obstacles in the obstacle information on the target vertical line; the target vertical line is a vertical line on the lane central line.
It will be appreciated that the target vertical in this embodiment may be a vertical on the lane centerline, such as the centerline of the lane in which the host vehicle is currently located (i.e. the current lane); for example, the target vertical line may be a vertical line corresponding to each obstacle, or may be a vertical line corresponding to any obstacle or host vehicle. In the step, the processor can determine the drivable area in front of the host vehicle by utilizing the projection of the obstacle transverse width and the position information of each obstacle on the target vertical line, wherein the projection is obtained by the obstacle transverse width and the position information of each obstacle, the drivable area is divided by taking the lane central line as a reference line and adopting the projection mode of the obstacle contour to the vertical line of the lane central line, so that the curve and the straight road scene are effectively met, and the applicability of the drivable area detection is ensured.
Specifically, for the specific manner in which the processor determines the drivable area in front of the host vehicle according to the projection of each obstacle in the obstacle information on the target vertical line in this embodiment, the designer may set the specific manner by himself, for example, the position information of each obstacle in the obstacle information may be the longitudinal position of each obstacle, that is, the distance of each obstacle relative to the host vehicle in the driving direction, and the processor may determine the drivable area according to the lane line information, the longitudinal position of each obstacle in the obstacle information, and the projection of each obstacle in the obstacle information on the target vertical line.
For example, the processor may determine the drivable region according to a longitudinal position of each obstacle in the obstacle information, a projection of each obstacle in the obstacle information on the target vertical line, and a lateral width of the drivable region corresponding to the lane line information; that is, the processor may determine the sum of the lane center line and the width of each lane (i.e., the lateral width of the drivable zone) based on the lane line information, so as to make projections of each obstacle on the perpendicular line to the lane center line (i.e., the target perpendicular line) to determine the drivable zone within the range of the zone corresponding to the lateral width of the drivable zone. For example, the processor sorts the obstacles according to the longitudinal position of each obstacle in the obstacle information and the order from small to large to obtain the corresponding queue of each obstacle; according to the ordering sequence of the queues, sequentially projecting barriers on target line segments on the target vertical line, and determining target non-projected line segments corresponding to each queue; determining a drivable area according to the non-projected line segments and the longitudinal positions of the targets corresponding to the queues respectively; the target line segments are projection line segments corresponding to the transverse width of the drivable area on the target vertical line, and target non-projection line segments corresponding to the queues are not overlapped.
Step 104: the drivable region is divided according to the minimum lateral drivable region of the host vehicle, and a longitudinal drivable region in front of the host vehicle is obtained.
It will be appreciated that the minimum lateral travelable region in this step may be the minimum lateral region (e.g. lateral distance) that the host vehicle is capable of traveling in order to ensure that each longitudinal travelable region meets the minimum lateral travelable region. The longitudinal drivable region in the present embodiment may be a quadrangular region in the direction in which the host vehicle can travel (i.e., the longitudinal direction), such as a rectangular region when the lane center line is a straight line or an arc region when the lane center line is an arc; in this embodiment, no obstacle is present behind each longitudinal traveling area.
Specifically, the processor divides the drivable area according to the minimum transverse drivable area of the host vehicle, and the specific mode of obtaining the longitudinal drivable area in front of the host vehicle can be set by a designer according to a practical scene and user requirements, for example, the processor can divide the drivable area according to the minimum transverse drivable area only, so as to ensure that each longitudinal drivable area obtained by division can meet the minimum transverse drivable area; the processor may also divide the drivable region according to the minimum lateral drivable region and the longitudinal speed of the obstacle in the obstacle information, so as to adjust the lateral width of the longitudinal drivable region according to the longitudinal speed of the obstacle corresponding to the longitudinal drivable region on the basis of ensuring that each longitudinal drivable region obtained by the division can satisfy the minimum lateral drivable region, for example, the higher the longitudinal speed of the obstacle in front of the longitudinal drivable region, the wider or the narrower the lateral width of the longitudinal drivable region may be.
Further, each longitudinal drivable area in front of the host vehicle obtained in this step may be further marked with driving speed information, such as a speed (e.g., a longitudinal speed) and an acceleration, of an obstacle in front of each longitudinal drivable area, so that the obtained longitudinal drivable area can carry forward obstacle status information, and more sufficient information is provided for subsequent driving decisions and planning.
In the embodiment of the invention, the drivable area in front of the host vehicle is determined according to the transverse width of the drivable area and the projection of each obstacle in the obstacle information on the target vertical line, and the division of the drivable area and the obstacle profile are strongly correlated, so that the problem of algorithm operation efficiency is satisfied when the flexibility of the division of the drivable area is satisfied, the problem of large calculation amount of grid area operation is solved, the area is divided by taking the center line of the lane as a reference line and adopting the projection mode of the obstacle profile to the vertical line of the center line, the curve and straight-line scene can be effectively satisfied, and the detection applicability of the drivable area is improved.
Based on the above embodiment, the present invention also provides another method for detecting a drivable region. Specifically, referring to fig. 2, fig. 2 is a flowchart of another method for detecting a travelable region according to an embodiment of the present invention. The method may include:
Step 201: acquiring lane line information and obstacle information in front of a host vehicle; the lane line information comprises lane line data of a current lane where the host vehicle is located and lane line data of a neighboring lane of the current lane, and the obstacle information comprises obstacle transverse width and position information of each obstacle.
The present step is similar to step 101, and will not be described herein.
Step 202: and determining the lane center line and the transverse width of the drivable area according to the lane line information.
Specifically, in this step, the processor may calculate the center line of the current lane (i.e., the lane center line) according to the lane line data of the current lane in the obtained lane line information; according to the width of the current lane corresponding to the lane line data of the current lane and the width of the adjacent lane corresponding to the lane line data of the adjacent lane, the maximum transverse width (i.e. the transverse width of the drivable area) of the front part of the host vehicle is calculated, such as the sum of the width of the current lane and the width of each adjacent lane, such as the transverse width of the area 1 in fig. 3, 5 and 7, i.e. the sum of the width of each lane adjacent to the left and right of the current lane.
Step 203: and sequencing the obstacles according to the longitudinal positions of the obstacles in the obstacle information from small to large to obtain the corresponding queues of the obstacles.
It will be appreciated that in this step, the processor may rank the obstacles in front of the host vehicle from near to far (i.e., rank the obstacles in a rank order) according to the longitudinal position (e.g., ordinate) of the obstacles, and obtain the respective ranks of the obstacles, i.e., determine the respective obstacles of the ranks after the rank order.
Specifically, for the specific mode that the processor in this step sorts the obstacles according to the order from small to large according to the longitudinal position of each obstacle in the obstacle information to obtain the corresponding queue of each obstacle, the designer may set the specific mode by himself, for example, each queue may only correspond to one obstacle, that is, the processor in this step may sort the obstacles according to the order from small to large according to the longitudinal position of each obstacle in the obstacle information to obtain the corresponding queue of each obstacle after sorting; each queue can also correspond to at least one obstacle so as to put obstacles with similar longitudinal positions into the same queue and realize classification of the obstacles, for example, in the step, the processor can sort the obstacles according to the longitudinal positions of the obstacles in the obstacle information and the order from small to large to obtain the sorting order of the obstacles; and sequentially determining the corresponding queues of the obstacles according to the ordering sequence of the obstacles and the longitudinal distance threshold value of the queues, wherein the difference of the longitudinal positions between the obstacle with the largest longitudinal position and the obstacle with the smallest longitudinal position in the same queue is smaller than or equal to the longitudinal distance threshold value of the queues.
Correspondingly, in this embodiment, the identifier (e.g. ID number) of each queue may be a longitudinal position of an obstacle in the queue, for example, a longitudinal position of an obstacle with a minimum longitudinal position in the queue, for example, a longitudinal coordinate of the obstacle, so as to facilitate subsequent configuration of each queue corresponding to a target vertical line and/or determination of a drivable area.
Step 204: according to the ordering sequence of the queues, sequentially projecting barriers on target line segments on the target vertical line, and determining target non-projected line segments corresponding to each queue; the target line segments are projection line segments corresponding to the transverse width of the drivable area on the target vertical line, and target non-projection line segments corresponding to the queues are not overlapped.
It can be understood that the target line segment in this step may be a projected line segment corresponding to the lateral width of the drivable region on the target vertical line, that is, a projected line segment of all lanes corresponding to the lane line information on the target vertical line along the lane center line, where the length of the target line segment is equal to the lateral width of the drivable region; if the lane center line is a straight line, the target line segment may be the orthographic projection of all lanes on the target vertical line.
Specifically, each target non-projected line segment corresponding to each queue in this step may be an overlapping portion between a line segment that is not projected by an obstacle corresponding to the queue in the target line segment and a line segment that is not projected on the target line segment yet, for example, a target non-projected line segment corresponding to a queue in which an obstacle 1 is located in fig. 7 may be a projected line segment in a target line segment corresponding to a lateral width of a region 2 and a region 3, for example, a target non-projected line segment corresponding to a queue in which an obstacle 3 is located in fig. 5 may be a projected line segment in a target line segment corresponding to a lateral width of a region 3 and a lateral width of a region to the left of the obstacle 1 and a region to the right of the obstacle 2, for example, a target non-projected line segment in a target line segment corresponding to a lateral width of a region to the left of the obstacle 3 and a region to the right of the obstacle 1 in fig. 3.
Correspondingly, for the processor in the step, according to the ordering sequence of the queues, performing obstacle projection on target line segments on the target vertical line in sequence, and determining the specific mode of each corresponding target non-projected line segment of each queue, the specific mode can be set by a designer, for example, performing projection on the obstacle in the current queue on the target vertical line, and determining the non-projected line segment corresponding to the current queue on the target vertical line; if an overlapped line segment exists between the non-projected line segment corresponding to the current queue and the current non-projected line segment in the target line segment, the overlapped line segment is used as a target non-projected line segment corresponding to the current queue, and the projected line segment corresponding to the current queue on the target vertical line is used for updating the current non-projected line segment so as to remove the projected line segment corresponding to the current queue from the current non-projected line segment; if no overlapped line segment exists between the non-projected line segment corresponding to the current queue and the current non-projected line segment in the target line segment, the target non-projected line segment corresponding to the current queue is empty; the projected line segment corresponding to the current queue is in the target line segment, and the current queue is any queue.
Step 205: and determining the drivable area in front of the host vehicle according to the respective target non-projected line segments and the longitudinal positions corresponding to the queues.
Specifically, when the number of queues in this step is 1, the processor may determine a drivable area (i.e. a drivable sub-area) between the host vehicle and the 1 st queue according to the lateral width of the drivable area and the longitudinal position corresponding to the 1 st queue, such as the area 1 in fig. 7; according to the non-projected line segment and the longitudinal position of the target corresponding to the 1 st queue, a drivable area in front of the 1 st queue, namely a drivable area in front of the longitudinal position corresponding to the 1 st queue, such as an area 2 and an area 3 in fig. 7, is determined.
Correspondingly, when the number of the queues in the step is greater than or equal to 2, if the current queue is the 1 st queue, the processor can determine the drivable area between the host vehicle and the 1 st queue according to the transverse width of the drivable area and the corresponding longitudinal position of the 1 st queue; if the transverse width of the drivable area is taken as the transverse width of the drivable area, the longitudinal position is taken as the quadrangle of the longitudinal length of the drivable area; such as zone 1 corresponding to the queue in which obstacle 1 is located in fig. 3. If the current queue is the ith queue, the processor can determine a travelable area between the ith queue and the ith queue according to the difference between the target non-projected line segment corresponding to the ith queue and the longitudinal position corresponding to the ith queue; if the target non-projected line segment corresponding to the i-1 queue is taken as the transverse width of each drivable area, and the difference of the longitudinal positions is taken as the quadrangle of the longitudinal length of the drivable area; such as the area 2 corresponding to the queue in which the obstacle 2 is located and the corresponding area to the left of the obstacle 1 in fig. 3. If the current queue is the nth queue, the processor may determine a drivable area in front of the nth queue according to the target non-projected line segment and the longitudinal position corresponding to the nth queue, such as the area 3 corresponding to the queue in which the obstacle 3 is located, the corresponding area on the left side of the obstacle 1, and the corresponding area on the right side of the obstacle 2 in fig. 3; wherein i is a positive integer greater than 1 and less than or equal to n, n is the number of queues, and n is a positive integer greater than or equal to 2.
Step 206: dividing a drivable region according to the minimum transverse drivable region of the host vehicle and the obstacle longitudinal speed in the obstacle information, and acquiring a longitudinal drivable region in front of the host vehicle; wherein, the longitudinal travelable area is marked with the corresponding obstacle travel speed information.
It will be appreciated that the processor in this step may integrate the division of the longitudinal vehicle drivable zone in front of the host vehicle in the longitudinal (i.e. driving direction) direction, depending on the longitudinal speed of the obstacle and the minimum lateral drivable zone of the host vehicle.
Specifically, for the specific manner in this step that the processor divides the drivable area according to the minimum lateral drivable area of the host vehicle and the longitudinal speed of the obstacle in the obstacle information to obtain the longitudinal drivable area in front of the host vehicle, the designer may set the method by himself, for example, the processor may filter the drivable area with the lateral width smaller than the minimum lateral drivable area in all the drivable areas according to the minimum lateral drivable area of the host vehicle, to obtain the target drivable area, for example, the corresponding area on the left side of the obstacle 1 and the corresponding area on the right side of the obstacle 2 are filtered in fig. 3 and 4; adjusting the transverse width of each target travelable region according to the longitudinal speed of the obstacle in front of each target travelable region (namely the longitudinal speed of the obstacle); and merging the target drivable regions which are positioned at the same projection position (namely transverse position) on the target vertical line to obtain each longitudinal drivable region in front of the host vehicle, wherein projections of each longitudinal drivable region on the target vertical line are not overlapped.
Correspondingly, the longitudinal drivable area in front of the host vehicle in this step may be marked with respective corresponding obstacle travel speed information, such as the speed and acceleration of the obstacle ahead, to provide more sufficient information for subsequent travel decisions and plans.
In the embodiment of the invention, the longitudinal drivable area and the obstacle are strongly correlated by marking the respective corresponding obstacle driving speed information on the obtained longitudinal drivable area in front of the host vehicle, so that more sufficient information is provided for subsequent driving decision and planning; and the center line of the lane is used as a reference line, so that the vehicle can meet the line pressing driving scene of the vehicle without being limited by the lane when the driving area is divided.
Corresponding to the above method embodiments, the embodiments of the present invention further provide a device for detecting a drivable area, where a device for detecting a drivable area described below and a method for detecting a drivable area described above may be referred to correspondingly to each other.
Referring to fig. 9, fig. 9 is a block diagram of a detection device for a travelable region according to an embodiment of the present invention. The apparatus may include:
an information acquisition module 10 for acquiring lane line information and obstacle information in front of the host vehicle; the lane line information comprises lane line data of a current lane where a host vehicle is located and lane line data of an adjacent lane of the current lane, and the obstacle information comprises obstacle transverse width and position information of each obstacle;
A lane determining module 20 for determining a lane center line according to the lane line information;
a region determining module 30 for determining a drivable region in front of the host vehicle according to projections of the respective obstacles in the obstacle information on the target vertical line; the target vertical line is a vertical line on the lane central line;
the area dividing module 40 is configured to divide the drivable area according to the minimum lateral drivable area of the host vehicle, and obtain a longitudinal drivable area in front of the host vehicle.
Alternatively, the area determining module 30 may be specifically configured to determine the drivable area according to the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle in the obstacle information on the target vertical line, and the lateral width of the drivable area corresponding to the lane line information.
Alternatively, the area determining module 30 may include:
the sequencing sub-module is used for sequencing the obstacles according to the longitudinal positions of the obstacles in the obstacle information and the sequence from small to large to obtain the corresponding queues of the obstacles;
the projection sub-module is used for sequentially projecting obstacles on the target line segments on the target vertical line according to the ordering sequence of the queues and determining target non-projected line segments corresponding to each queue; the target line segments are projection line segments corresponding to the transverse width of the drivable area on the target vertical line, and target non-projection line segments corresponding to the queues are not overlapped;
And the region determination submodule is used for determining a drivable region according to the target non-projected line segments and the longitudinal positions corresponding to the queues respectively.
Alternatively, the region determination submodule may be specifically configured to: if the current queue is the 1 st queue, determining a travelable area between the host vehicle and the 1 st queue according to the transverse width of the travelable area and the longitudinal position corresponding to the 1 st queue; if the current queue is the ith queue, determining a travelable area between the ith queue and the ith queue according to the difference between the target non-projected line segment corresponding to the ith queue and the longitudinal position corresponding to the ith queue; wherein i is a positive integer greater than 1 and less than or equal to n, n being the number of queues; if the current queue is the nth queue, determining a travelable area in front of the nth queue according to the target non-projected line segment and the longitudinal position corresponding to the nth queue.
Alternatively, the sorting sub-module may include:
the obstacle sorting unit is used for sorting the obstacles according to the longitudinal positions of the obstacles in the obstacle information and the order from small to large to obtain an obstacle sorting order;
the queue classifying unit is used for sequentially determining the queues corresponding to the obstacles according to the ordering sequence of the obstacles and the longitudinal distance threshold value of the queues.
Alternatively, the projection submodule may include:
the projection unit is used for projecting the obstacle in the current queue on the target vertical line and determining an un-projected line segment corresponding to the current queue on the target vertical line; the projection line segment corresponding to the current queue is positioned in the target line segment;
the determining and updating unit is used for taking the overlapped line segment as a target non-projected line segment corresponding to the current queue if an overlapped line segment exists between the non-projected line segment corresponding to the current queue and the current non-projected line segment in the target line segment, and updating the current non-projected line segment by utilizing the projected line segment corresponding to the current queue on the target vertical line;
and the filtering and determining unit is used for determining that the target non-projected line segment corresponding to the current queue is empty if no overlapped line segment exists between the non-projected line segment corresponding to the current queue and the current non-projected line segment in the target line segment.
Alternatively, the area dividing module 40 may be specifically configured to divide the drivable area according to the minimum lateral drivable area and the obstacle longitudinal speed in the obstacle information, so as to obtain a longitudinal drivable area in front of the host vehicle; wherein, the longitudinal running areas are marked with the corresponding obstacle running speed information;
In this embodiment, the area determining module 30 determines the drivable area in front of the host vehicle according to the lateral width of the drivable area and the projection of each obstacle in the obstacle information on the target vertical line, and strongly correlates the division of the drivable area with the obstacle profile, so that the flexibility of division of the drivable area is satisfied, the problem of high calculation amount of grid area operation is solved, the area is divided by taking the lane central line as a reference line and adopting the projection mode of the obstacle profile to the vertical line of the central line, the curve and straight road scene can be effectively satisfied, and the applicability of detection of the drivable area is improved.
Corresponding to the above method embodiment, the present invention further provides a vehicle, and a vehicle described below and a method for detecting a drivable area described above may be referred to correspondingly.
Referring to fig. 10, fig. 10 is a schematic structural diagram of a vehicle according to an embodiment of the invention. The vehicle may include:
a memory D1 for storing a computer program;
and the processor D2 is configured to implement the steps of the method for detecting a drivable region provided in the method embodiment when executing the computer program.
Specifically, the vehicle provided in the present embodiment may be specifically the host vehicle in the above embodiment; the vehicle provided by the embodiment may further include a sensing device to collect lane line information and obstacle information in front of the vehicle.
Corresponding to the above method embodiments, the embodiments of the present invention further provide a computer readable storage medium, and a computer readable storage medium described below and a method for detecting a travelable region described above may be referred to correspondingly with each other.
An embodiment of the present invention provides a computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of the method for detecting a travelable region provided by the above-described method embodiment.
The computer readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, which may store various program codes.
In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. For the apparatus, the vehicle, and the computer-readable storage medium disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant points are referred to in the description of the method section.
The method, the device, the vehicle and the computer readable storage medium for detecting the drivable area provided by the invention are described in detail above. The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present invention and its core ideas. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the invention can be made without departing from the principles of the invention and these modifications and adaptations are intended to be within the scope of the invention as defined in the following claims.
Claims (10)
1. A method for detecting a drivable region, comprising:
acquiring lane line information and obstacle information in front of a host vehicle; the lane line information comprises lane line data of a current lane where the host vehicle is located and lane line data of a neighboring lane of the current lane, and the obstacle information comprises obstacle transverse width and position information of each obstacle;
determining a lane center line according to the lane line information;
determining a drivable area in front of the host vehicle according to the projection of each obstacle in the obstacle information on a target vertical line; wherein the target vertical line is a vertical line on the lane central line;
And dividing the drivable region according to the minimum transverse drivable region of the host vehicle to obtain a longitudinal drivable region in front of the host vehicle.
2. The method according to claim 1, wherein the determining the drivable area in front of the host vehicle based on the projection of each of the obstacles in the obstacle information on the target vertical line includes:
determining a travelable area according to the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle in the obstacle information on a target vertical line and the transverse width of the travelable area corresponding to the lane line information; wherein the position information includes the longitudinal position.
3. The method according to claim 2, wherein the determining the drivable region according to the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle in the obstacle information on a target vertical line, and the lateral width of the drivable region corresponding to the lane line information includes:
sequencing the obstacles according to the longitudinal position of each obstacle in the obstacle information from small to large to obtain a queue corresponding to each obstacle;
According to the sequencing order of the queues, sequentially projecting obstacles on target line segments on the target vertical line to determine target non-projected line segments corresponding to the queues; the target line segments are projection line segments corresponding to the transverse width of the drivable area on the target vertical line, and target non-projection line segments corresponding to the queues are not overlapped;
and determining the drivable area according to the target non-projected line segments and the longitudinal positions corresponding to the queues.
4. The method for detecting a travelable region according to claim 3, wherein the determining the travelable region according to the respective target non-projected line segments and the longitudinal positions of the queues comprises:
if the current queue is the 1 st queue, determining a drivable area between the host vehicle and the 1 st queue according to the transverse width of the drivable area and the longitudinal position corresponding to the 1 st queue;
if the current queue is the ith queue, determining a travelable area between the ith queue and the ith queue according to the difference between a target non-projected line segment corresponding to the ith queue and a longitudinal position corresponding to the ith queue; wherein i is a positive integer greater than 1 and less than or equal to n, n being the number of queues;
If the current queue is the nth queue, determining a travelable area in front of the nth queue according to the target non-projected line segment and the longitudinal position corresponding to the nth queue.
5. The method for detecting a travelable region according to claim 3, wherein the step of sorting the obstacles in order from small to large according to the longitudinal position of each obstacle in the obstacle information to obtain the respective corresponding queues of each obstacle comprises:
sequencing the obstacles according to the longitudinal position of each obstacle in the obstacle information from small to large to obtain an obstacle sequencing sequence;
and determining the corresponding queues of the obstacles in turn according to the obstacle ordering sequence and the longitudinal distance threshold of the queues.
6. The method for detecting a travelable region according to claim 5, wherein the sequentially projecting obstacles on the target line segments on the target vertical line according to the sorting order of the queues, determining target non-projected line segments corresponding to each of the queues, includes:
projecting an obstacle in the current queue on the target vertical line, and determining an un-projected line segment corresponding to the current queue on the target vertical line; the projection line segment corresponding to the current queue is in the target line segment;
If an overlapped line segment exists between the non-projected line segment corresponding to the current queue and the current non-projected line segment in the target line segment, the overlapped line segment is used as a target non-projected line segment corresponding to the current queue, and the projected line segment corresponding to the current queue on the target vertical line is used for updating the current non-projected line segment;
and if no overlapped line segment exists between the non-projected line segment corresponding to the current queue and the current non-projected line segment in the target line segment, the target non-projected line segment corresponding to the current queue is empty.
7. The method according to any one of claims 1 to 6, characterized in that the dividing the drivable area according to the minimum lateral drivable area of the host vehicle, obtaining a longitudinal drivable area in front of the host vehicle, includes:
dividing the travelable area according to the minimum transverse travelable area and the obstacle longitudinal speed in the obstacle information to obtain a longitudinal travelable area in front of the host vehicle; wherein, the longitudinal travelable area is marked with the corresponding obstacle travel speed information.
8. A detection device for a drivable area, comprising:
The information acquisition module is used for acquiring lane line information and obstacle information in front of the host vehicle; the lane line information comprises lane line data of a current lane where the host vehicle is located and lane line data of a neighboring lane of the current lane, and the obstacle information comprises obstacle transverse width and position information of each obstacle;
the lane determining module is used for determining a lane center line according to the lane line information;
the area determining module is used for determining a travelable area in front of the host vehicle according to the projection of each obstacle in the obstacle information on a target vertical line; wherein the target vertical line is a vertical line on the lane central line;
the area dividing module is used for dividing the drivable area according to the minimum transverse drivable area of the host vehicle and obtaining the longitudinal drivable area in front of the host vehicle.
9. A vehicle, characterized by comprising:
a memory for storing a computer program;
processor for implementing the method for detecting a travelable region as claimed in any one of claims 1-7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method for detecting a travelable region as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310085745.1A CN116052126A (en) | 2023-02-06 | 2023-02-06 | Method and device for detecting drivable area, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310085745.1A CN116052126A (en) | 2023-02-06 | 2023-02-06 | Method and device for detecting drivable area, vehicle and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116052126A true CN116052126A (en) | 2023-05-02 |
Family
ID=86123578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310085745.1A Pending CN116052126A (en) | 2023-02-06 | 2023-02-06 | Method and device for detecting drivable area, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116052126A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117011827A (en) * | 2023-07-11 | 2023-11-07 | 禾多科技（北京）有限公司 | Method, apparatus, device and computer readable medium for detecting longitudinal distance of obstacle |
-
2023
- 2023-02-06 CN CN202310085745.1A patent/CN116052126A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117011827A (en) * | 2023-07-11 | 2023-11-07 | 禾多科技（北京）有限公司 | Method, apparatus, device and computer readable medium for detecting longitudinal distance of obstacle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102541561B1 (en) | Method of providing information for driving vehicle and apparatus thereof | |
| CN110687539B (en) | Parking space detection method, device, medium and equipment | |
| CN112441022B (en) | Lane center line determining method and device | |
| RU2707409C1 (en) | Method and device for parking assistance | |
| US11932244B2 (en) | Apparatus and method for controlling autonomous driving of vehicle | |
| JP6654923B2 (en) | Map information output device | |
| CN107491065B (en) | Method and apparatus for detecting side surface of object using ground boundary information of obstacle | |
| CN110803163B (en) | Method and device for predicting vehicle running track and selecting vehicle following target | |
| JP2004032460A (en) | Image processing apparatus and method therefor | |
| CN112990087B (en) | Lane line detection method, device, equipment and readable storage medium | |
| CN116052126A (en) | Method and device for detecting drivable area, vehicle and storage medium | |
| KR102564856B1 (en) | Method and apparatus of detecting road line | |
| JP2019149071A (en) | Stereo camera device | |
| WO2021093335A1 (en) | Method for automatically labeling lane changing intention based on high-noise trajectory data of vehicle | |
| Revilloud et al. | A lane marker estimation method for improving lane detection | |
| CN112149471B (en) | Loop detection method and device based on semantic point cloud | |
| KR20220136679A (en) | Apparatus and method for controlling driving of vehicle | |
| JP5746996B2 (en) | Road environment recognition device | |
| US11884303B2 (en) | Apparatus and method for determining lane change of surrounding objects | |
| Chai et al. | Automatic vehicle classification and tracking method for vehicle movements at signalized intersections | |
| JP7344744B2 (en) | Roadside edge detection method and roadside edge detection device | |
| JP7344032B2 (en) | Image processing device | |
| KR20200087381A (en) | Backward vehicle detection apparatus and method | |
| CN113807193B (en) | Automatic extraction method and system for traffic road virtual line segments in laser point cloud | |
| JP7216526B2 (en) | Vehicle exterior environment recognition device and vehicle exterior environment recognition method |
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 |