Lane line identification evaluation method and device and vehicle

By calculating the target time distance and sampling points, the lane line identification results are directly evaluated, which solves the problem of high cost of lane line detection and evaluation, and achieves evaluation without external sensors, improving the real-time and accuracy of the evaluation.

CN118968438AActive Publication Date: 2024-11-15GUANGZHOU AUTOMOBILE GROUP CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202410852415.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-27
Publication Date
2024-11-15
Estimated Expiration
2044-06-27

AI Technical Summary

Technical Problem

In autonomous driving technology, lane line detection is costly to evaluate lane line detection, and additional sensors are required to obtain reference recognition results for comparison, which increases system complexity and cost.

Method used

By acquiring the lane line identification results and vehicle speed of at least two frames, calculating the target time distance based on the preset target time, determining the target sampling point, and then evaluating the lane line identification results without relying on parameters collected by external sensors.

Benefits of technology

It reduces the cost of lane line identification evaluation, improves the real-time and accuracy of evaluation, avoids dependence on external sensors, and simplifies system design.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118968438A_ABST
    Figure CN118968438A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a lane line identification evaluation method and device and a vehicle. The method comprises the following steps: acquiring at least two frames of lane line recognition results and acquiring a vehicle speed corresponding to each frame of lane line recognition result; based on preset target time and the vehicle speed corresponding to each frame of lane line recognition result, obtaining a target time distance corresponding to each frame of lane line recognition result; according to the lane line recognition result of each frame and the target time distance corresponding to the lane line recognition result of each frame, obtaining a target sampling point corresponding to the lane line recognition result of each frame; and obtaining an evaluation result of the lane line recognition result based on the target sampling point corresponding to each frame of lane line recognition result. By means of the mode, evaluation can be completed without depending on parameters collected by an external sensor, and the evaluation cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and more specifically, to a lane line recognition evaluation method, device and vehicle. Background Art

[0002] Lane detection plays a particularly important role in autonomous driving technology. In related technologies, lane recognition results are evaluated to determine their accuracy. However, in related technologies, in addition to the lane recognition that originally needs to be evaluated, other sensors need to be configured on the vehicle to identify reference recognition results and compare the reference recognition results with the lane recognition results that need to be evaluated. Therefore, the evaluation cost needs to be improved. Summary of the invention

[0003] In view of the above problems, the present application proposes a lane line recognition evaluation method, device and vehicle to improve the above problems.

[0004] In a first aspect, the present application provides a method for evaluating lane line recognition, the method comprising: obtaining lane line recognition results of at least two frames and obtaining the vehicle speed corresponding to the lane line recognition results of each frame; based on a preset target time and the vehicle speed corresponding to the lane line recognition results of each frame, obtaining a target time distance corresponding to the lane line recognition results of each frame, the target time distance being the longitudinal distance traveled by the vehicle at the preset target time; according to the lane line recognition results of each frame and the target time distance corresponding to the lane line recognition results of each frame, obtaining a target sampling point corresponding to the lane line recognition results of each frame, the target sampling point being the nearest neighbor sampling point corresponding to the target time distance; based on the target sampling point corresponding to the lane line recognition results of each frame, obtaining an evaluation result of the lane line recognition result.

[0005] In a second aspect, the present application provides a lane line recognition evaluation device, the device comprising: a lane line recognition result acquisition unit, used to acquire lane line recognition results of at least two frames and to acquire the vehicle speed corresponding to the lane line recognition result of each frame; a target time distance acquisition unit, used to obtain the target time distance corresponding to the lane line recognition result of each frame based on a preset target time and the vehicle speed corresponding to the lane line recognition result of each frame, the target time distance being the longitudinal distance traveled by the vehicle at the preset target time; a target sampling point acquisition unit, used to obtain the target sampling point corresponding to the lane line recognition result of each frame based on the lane line recognition result of each frame and the target time distance corresponding to the lane line recognition result of each frame, the target sampling point being the nearest neighbor sampling point corresponding to the target time distance; an evaluation result acquisition unit, used to obtain the evaluation result of the lane line recognition result based on the target sampling point corresponding to the lane line recognition result of each frame.

[0006] In a third aspect, the present application provides a vehicle comprising one or more processors and a memory; one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the above-mentioned method.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium, in which program code is stored, wherein the above method is executed when the program code is run.

[0008] The present application provides a lane line recognition evaluation method, device, vehicle and storage medium. After obtaining at least two frames of lane line recognition results and obtaining the vehicle speed corresponding to each frame of the lane line recognition results, based on the preset target time and the vehicle speed corresponding to each frame of the lane line recognition results, the target time distance corresponding to each frame of the lane line recognition results is obtained. According to each frame of the lane line recognition results and the target time distance corresponding to each frame of the lane line recognition results, the target sampling point corresponding to each frame of the lane line recognition results is obtained. Based on the target sampling point corresponding to each frame of the lane line recognition results, the evaluation result of the lane line recognition result is obtained. Through the above method, after obtaining at least two frames of lane line recognition results and obtaining the vehicle speed corresponding to each frame of the lane line recognition results, based on the preset target time and the vehicle speed corresponding to each frame of the lane line recognition results, the target time distance corresponding to each frame of the lane line recognition results is obtained, thereby obtaining the target sampling point corresponding to each frame of the lane line recognition results. The evaluation result of the lane line recognition result can be obtained based on the target sampling point corresponding to each frame of the lane line recognition results, and the evaluation can be completed without relying on the parameters collected by the external sensor, thereby reducing the evaluation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A flow chart of a lane line recognition evaluation method proposed in an embodiment of the present application;

[0011] Figure 2 A schematic diagram showing a lane line recognition result proposed in this application is shown;

[0012] Figure 3 A flow chart of a lane line recognition evaluation method proposed in another embodiment of the present application is shown;

[0013] Figure 4 A schematic diagram of determining a target sampling point proposed in the present application is shown;

[0014] Figure 5 A structural block diagram of a lane line recognition evaluation device proposed in an embodiment of the present application is shown;

[0015] Figure 6 A structural block diagram of a vehicle proposed in this application is shown. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0017] In an embodiment of the present application, the inventor proposes a lane line recognition evaluation method, device, and vehicle. After obtaining at least two frames of lane line recognition results and obtaining the vehicle speed corresponding to each frame of the lane line recognition results, based on the preset target time and the vehicle speed corresponding to each frame of the lane line recognition results, the target time distance corresponding to each frame of the lane line recognition results is obtained. According to each frame of the lane line recognition results and the target time distance corresponding to each frame of the lane line recognition results, the target sampling point corresponding to each frame of the lane line recognition results is obtained. Based on the target sampling point corresponding to each frame of the lane line recognition results, the evaluation result of the lane line recognition result is obtained. Through the above method, after obtaining at least two frames of lane line recognition results and obtaining the vehicle speed corresponding to each frame of the lane line recognition results, based on the preset target time and the vehicle speed corresponding to each frame of the lane line recognition results, the target time distance corresponding to each frame of the lane line recognition results is obtained, thereby obtaining the target sampling point corresponding to each frame of the lane line recognition results, so that the evaluation result of the lane line recognition result can be obtained based on the target sampling point corresponding to each frame of the lane line recognition results, and the evaluation can be completed without relying on the parameters collected by the external sensor, thereby reducing the evaluation cost.

[0018] See also Figure 1 , an embodiment of the present application provides a lane line recognition evaluation method, the method comprising:

[0019] S110: Obtain lane line recognition results of at least two frames and obtain the vehicle speed corresponding to the lane line recognition results of each frame.

[0020] Among them, Figure 2 As shown, the lane line recognition result may include multiple lane lines, each lane line includes multiple sampling points and position information of the multiple sampling points.

[0021] As a method, the vehicle can be equipped with an image acquisition device (camera, radar, etc.), which can collect environmental information during the vehicle's driving process, such as lane lines, road signs, traffic lights, etc. at a certain acquisition frequency, thereby obtaining at least two frames of images. Based on the at least two frames of images and the lane line recognition algorithm, at least two frames of lane line recognition results can be obtained.

[0022] In an embodiment of the present application, in order to improve the real-time performance of the evaluation, the lane line recognition results of at least two frames may refer to the lane line recognition results of two consecutive frames.

[0023] In order to determine the evaluation results of lane line recognition results within a period of time while saving computing resources, the lane line recognition results of at least two frames may refer to two frames of lane line recognition results separated by a preset number of frames. For example, the lane line recognition results of the first frame and the lane line recognition results of the fifth frame may be used as the lane line recognition results of at least two frames.

[0024] In order to improve the evaluation accuracy, a sliding time window mechanism can be used to obtain the lane line recognition results of two consecutive sliding time windows, thereby obtaining two consecutive groups of lane line recognition results, each group of lane line recognition results includes a continuous number of frames of lane line recognition results, and the two consecutive groups of lane line recognition results are used as the lane line recognition results of at least two frames. Exemplarily, the size of the sliding time window can be 3 frames, the first group of lane line recognition results can include the lane line recognition results of the 1st to 3rd frames, and the second group of lane line recognition results can include the lane line recognition results of the 2nd to 4th frames; or, the first group of lane line recognition results can include the lane line recognition results of the 1st to 3rd frames, and the second group of lane line recognition results can include the lane line recognition results of the 4th to 6th frames.

[0025] Optionally, when at least two frames of lane line recognition results refer to two frames of lane line recognition results with a preset number of frames between them, the number of interval frames between the two frames can be determined based on actual needs, wherein the higher the real-time requirement, the smaller the interval frame number can be; and the higher the requirement for saving resources, the larger the interval frame number can be.

[0026] S120: Based on the preset target time and the vehicle speed corresponding to the lane line recognition result of each frame, a target time distance corresponding to the lane line recognition result of each frame is obtained, where the target time distance is the longitudinal distance traveled by the vehicle at the preset target time.

[0027] There may be multiple preset target times, and the time intervals between adjacent preset target times may be the same. For example, the multiple preset target times may be 0 seconds, 0.5 seconds, 1 second, and 1.5 seconds. The time intervals between adjacent preset target times may also be different. The preset target times are sorted from small to large, and the time intervals between preset target times that are ranked later are larger. For example, the multiple preset target times may be 0 seconds, 0.5 seconds, 1.5 seconds, and 3 seconds.

[0028] As a method, while obtaining the lane line recognition result of each frame, the vehicle speed can be obtained through an acceleration sensor, etc., and based on multiple preset target times and the vehicle speed corresponding to the lane line recognition result of each frame, multiple target time distances corresponding to the lane line recognition result of each frame are obtained, wherein one preset target time corresponds to one target time distance.

[0029] Exemplarily, for a frame of lane line recognition results, multiple preset target times can be 0 seconds, 0.5 seconds, 1 second, and 1.5 seconds, the vehicle speed can be V, and the target time distance can be 0*V, 0.5*V, 1*V, and 1.5*V.

[0030] S130: According to the lane line recognition result of each frame and the target time distance corresponding to the lane line recognition result of each frame, a target sampling point corresponding to the lane line recognition result of each frame is obtained, and the target sampling point is a nearest neighbor sampling point corresponding to the target time distance.

[0031] The nearest neighbor sampling point corresponding to the target time distance can be understood as the sampling point closest to the straight line where the end point corresponding to the target time distance is located. For the same lane line, one target time distance can correspond to one target sampling point.

[0032] As a method, the target sampling point corresponding to each frame of lane line recognition result can be obtained based on each frame of lane line recognition result and multiple target time distances corresponding to each frame of lane line recognition result.

[0033] S140: Obtaining an evaluation result of the lane line recognition result based on the target sampling points corresponding to the lane line recognition result of each frame.

[0034] As a method, based on the target sampling points corresponding to the lane line recognition results of each frame, the lateral difference between the target sampling points at the same target time distance in the lane line recognition results of different frames can be obtained; based on the lateral difference and the time interval between the lane line recognition results of different frames, the evaluation result is obtained, and the evaluation result can characterize the lateral position change rate of the target sampling point.

[0035] The position information of each target sampling point can be represented by a set of coordinates (x, y) in the vehicle coordinate system, wherein the X-axis direction can represent the longitudinal driving direction of the vehicle, which is equivalent to the extension direction of the lane line, and the Y-axis direction can represent the lateral driving direction of the vehicle. The lateral difference can refer to the distance between the two target sampling points in the Y-axis direction.

[0036] Optionally, each frame of lane line recognition result may correspond to a timestamp, and the time interval between the lane line recognition results of different frames may be obtained through the timestamps corresponding to the lane line recognition results of different frames.

[0037] Exemplarily, the time interval between lane line recognition results of different frames may be t. For the same lane line in the lane line recognition results of different frames, the target sampling points corresponding to the target time distance 0.5*V may be (x1, y1) and (x2, y2), respectively. The lateral difference between the target sampling points may be y2-y1. The lateral position change rate of the pair of target sampling points may be |(y2-y1) / t|. The evaluation result may be obtained by averaging the lateral position change rates of multiple pairs of target sampling points in the lane line recognition results of different frames.

[0038] In the embodiment of the present application, the evaluation result can reflect the changes in the lane line recognition results at two different times, so that the stability of the lane line recognition result can be obtained through the evaluation result. The smaller the evaluation result, the higher the stability, indicating that the lane line recognition result is more accurate.

[0039] It should be noted that when obtaining two consecutive sets of lane line recognition results, the multiple frames of lane line recognition results in each set of lane line recognition results can be first sorted in chronological order of acquisition time, and then based on the target sampling points corresponding to every two frames of lane line recognition results in the same position in the two groups, multiple reference evaluation results can be obtained. Each reference evaluation result can be the evaluation result of the corresponding two frames of lane line recognition results, and then the average of the multiple reference evaluation results is used as the evaluation result of the two consecutive sets of lane line recognition results.

[0040] The present embodiment provides a lane line recognition evaluation method. After obtaining at least two frames of lane line recognition results and obtaining the vehicle speed corresponding to each frame of the lane line recognition results, based on the preset target time and the vehicle speed corresponding to each frame of the lane line recognition results, the target time distance corresponding to each frame of the lane line recognition results is obtained. According to each frame of the lane line recognition results and the target time distance corresponding to each frame of the lane line recognition results, the target sampling point corresponding to each frame of the lane line recognition results is obtained. Based on the target sampling point corresponding to each frame of the lane line recognition results, the evaluation result of the lane line recognition result is obtained. Through the above method, after obtaining at least two frames of lane line recognition results and obtaining the vehicle speed corresponding to each frame of the lane line recognition results, based on the preset target time and the vehicle speed corresponding to each frame of the lane line recognition results, the target time distance corresponding to each frame of the lane line recognition results is obtained, thereby obtaining the target sampling point corresponding to each frame of the lane line recognition results. The evaluation result of the lane line recognition result can be obtained based on the target sampling point corresponding to each frame of the lane line recognition results. The evaluation can be completed without relying on the parameters collected by the external sensor, thereby reducing the evaluation cost.

[0041] See also Figure 3 , an embodiment of the present application provides a lane line recognition evaluation method, the method comprising:

[0042] S210: Obtain lane line recognition results of at least two frames and obtain the vehicle speed corresponding to the lane line recognition results of each frame.

[0043] S220: Based on the preset target time and the vehicle speed corresponding to the lane line recognition result of each frame, a target time distance corresponding to the lane line recognition result of each frame is obtained, where the target time distance is the longitudinal distance traveled by the vehicle at the preset target time.

[0044] S230: According to the lane line recognition result of each frame, a plurality of sampling points included in the target lane line in the lane line recognition result of each frame are obtained.

[0045] The target lane line may refer to a lane line of the type adjacent to the left lane line (ID may be 0) or from the left lane line (ID may be 1) or from the right lane line (ID may be 2) or adjacent to the right lane line (ID may be 3), such as Figure 4 As shown, there are 4 target lane lines on the current road. The adjacent left lane line may refer to the lane line in the left lane of the lane where the vehicle is located, which is far away from the vehicle; the from-left lane line may refer to the left lane line of the lane where the vehicle is located; the from-right lane line may refer to the right lane line of the lane where the vehicle is located; and the adjacent right lane line may refer to the lane line in the right lane of the lane where the vehicle is located, which is far away from the vehicle.

[0046] As a method, each lane line can be divided into multiple lane line segments according to a fixed length; based on the sampling points included in each lane line segment, the cluster center of each lane line segment is obtained to obtain multiple cluster centers contained in each lane line; the vehicle position corresponding to each frame of lane line recognition result is obtained; based on the distances between the multiple cluster centers contained in each lane line and the vehicle position, the type of each lane line is obtained; and the lane line of the type adjacent to the left lane line, the lane line from the left lane line, the lane line from the right lane line, or the adjacent to the right lane line is taken as the target lane line to obtain multiple sampling points contained in the target lane line.

[0047] Optionally, based on the coordinate values ​​of the sampling points included in each lane line segment in the X direction and the Y direction, the mean coordinate values ​​of the sampling points included in each lane line segment in the X direction and the Y direction are obtained, and the mean coordinate values ​​of the sampling points included in each lane line segment in the X direction and the Y direction are used as the coordinate values ​​of the cluster center of each lane line segment in the X direction and the Y direction.

[0048] For example, please refer to Figure 4 , Figure 4 The center left lane line can be divided into multiple lane line segments. The first lane line segment can have 3 sampling points, namely (x1, y1), (x2, y2), and (x3, y3). Then the cluster center of the first lane line segment can be ((x1+x2+x3) / 3, (y1+y2+y3) / 3).

[0049] Optionally, the types corresponding to the multiple cluster centers included in each lane line can be obtained based on the distances between the multiple cluster centers included in each lane line and the vehicle position, and the type that appears most frequently among the types corresponding to the multiple cluster centers included in each lane line is used as the type of each lane line.

[0050] The vehicle position may refer to the coordinate value of the vehicle in the vehicle coordinate system. The distance between the cluster center and the vehicle position may refer to the difference between the cluster center and the vehicle position in the Y-axis direction, that is, the Y-axis coordinate value of the cluster center minus the Y-axis coordinate value of the vehicle.

[0051] Exemplarily, a lane line may have 5 cluster centers, and the types of the 5 cluster centers may be respectively from-left lane line, from-left lane line, adjacent-left lane line, from-left lane line, and from-left lane line. Then the type of the lane line is from-left lane line.

[0052] Optionally, if the distances between the cluster centers and the vehicle positions are respectively greater than or equal to a first distance threshold and less than a second distance threshold, the type of the cluster centers is determined to be adjacent to the right lane line; if the distances between the cluster centers and the vehicle positions are respectively greater than or equal to a second distance threshold and less than a third distance threshold, the type of the cluster centers is determined to be from the right lane line; if the distances between the cluster centers and the vehicle positions are respectively greater than or equal to a fourth distance threshold and less than a fifth distance threshold, the type of the cluster centers is determined to be from the left lane line; if the distances between the cluster centers and the vehicle positions are respectively greater than or equal to a fifth distance threshold and less than a sixth distance threshold, the type of the cluster centers is determined to be adjacent to the left lane line, wherein the first distance threshold, the second distance threshold and the third distance threshold are all less than 0, and the first distance threshold is less than the second distance threshold, and the second distance threshold is less than the third distance threshold; the fourth distance threshold, the fifth distance threshold and the sixth distance threshold are all greater than 0, and the fourth distance threshold is less than the fifth distance threshold, and the fifth distance threshold is less than the sixth distance threshold, and the above distance thresholds can be determined based on the lane line width.

[0053] In an embodiment of the present application, by using the type that appears most frequently among the types corresponding to the multiple cluster centers contained in each lane line as the type of each lane line, misjudgment of the lane line type can be avoided and the accuracy of the acquired target lane line can be improved.

[0054] S240: Based on the target time distance corresponding to the lane line recognition result of each frame, an end point corresponding to the target time distance is obtained.

[0055] As a method, after obtaining the target time distance corresponding to the lane line recognition result, the vehicle position can be used as the starting point to obtain the end point corresponding to the target time distance based on the starting point and the target time distance.

[0056] For example, Figure 4 Points A, B, C, and D in the figure can be the end points corresponding to the target distance.

[0057] S250: Obtain the target sampling point based on the multiple sampling points and the end point.

[0058] As a method, multiple target straight lines can be obtained, each of which can be the straight line where the end point of the corresponding target time distance is located, and each target straight line is perpendicular to the longitudinal driving direction of the vehicle; based on the distance between each target straight line and multiple sampling points included in the target lane line in the corresponding lane line recognition result, the sampling point closest to each target straight line is obtained, and the sampling point closest to each target straight line is used as the target sampling point.

[0059] Optionally, in order to improve the efficiency of obtaining the target sampling point, the sampling point closest to the target straight line may be obtained by a longitudinal binary search method.

[0060] For example, Figure 4 As shown, the straight lines where points A, B, C, and D are located can be straight line 1, straight line 2, straight line 3, and straight line 4, respectively. Through the distances between multiple sampling points and straight line 1, straight line 2, straight line 3, and straight line 4, the sampling points closest to straight line 1, straight line 2, straight line 3, and straight line 4 are obtained, that is, the target sampling points corresponding to straight line 1, straight line 2, straight line 3, and straight line 4 are obtained on each target lane.

[0061] S260: Obtaining an evaluation result of the lane line recognition result based on the target sampling points corresponding to the lane line recognition result of each frame.

[0062] As a method, when the lane line recognition results of all frames contain 4 target lane lines and 4 target time distances, there can be 4 target sampling points for one target lane line in each frame of lane line recognition results, which is equivalent to a total of 16 sampling points. By calculating the lateral differences between the target sampling points under the same target time distance and the same target lane line in the lane line recognition results of different frames, 16 lateral differences can be obtained, thereby obtaining 16 reference evaluation results, and the average of the 16 reference sampling results is used as the evaluation result of the lane line recognition result.

[0063] The present embodiment provides a lane line recognition evaluation method. Through the above-mentioned method, after obtaining at least two frames of lane line recognition results and obtaining the vehicle speed corresponding to each frame of lane line recognition results, the target time distance corresponding to each frame of lane line recognition results can be obtained based on the preset target time and the vehicle speed corresponding to each frame of lane line recognition results, thereby obtaining the target sampling point corresponding to each frame of lane line recognition results. Therefore, based on the target sampling point corresponding to each frame of lane line recognition results, the evaluation result of the lane line recognition result can be obtained. The evaluation can be completed without relying on parameters collected by external sensors, thereby reducing the evaluation cost. Furthermore, in this embodiment, by determining the category of the lane line in each frame of lane line recognition results and each category can correspond to an ID, the target lane line in each frame of lane line recognition results is obtained, and then the change trend of the same lane line in the time series can be tracked through the ID of the lane line. However, the logic of assigning lane line IDs in general lane line recognition tasks is a simpler sequential assignment, and there is no logical association between the previous and next IDs in the time series. In addition, when the recognition task is polluted by noise or the lane line shape actually changes, the lane line ID may jump, resulting in errors in the matching of the target sampling points. Therefore, by associating the lane lines in the time series through the relationship between the cluster center of each lane line and the vehicle position, the accuracy of the target lane line can be improved, thereby avoiding the jump of evaluation results caused by changes in the actual number and shape of lane lines during the evaluation process, thereby improving the evaluation accuracy.

[0064] See also Figure 5 The present application provides a lane line recognition evaluation device 400, the device 400 comprising:

[0065] A lane line recognition result acquisition unit 410 is used to acquire lane line recognition results of at least two frames and acquire the vehicle speed corresponding to the lane line recognition results of each frame;

[0066] A target time distance acquisition unit 420 is used to obtain a target time distance corresponding to each frame of the lane line recognition result based on a preset target time and a vehicle speed corresponding to each frame of the lane line recognition result, wherein the target time distance is a longitudinal distance traveled by the vehicle at the preset target time;

[0067] A target sampling point acquisition unit 430 is used to obtain a target sampling point corresponding to each lane line recognition result according to each frame of the lane line recognition result and the target time distance corresponding to each frame of the lane line recognition result, wherein the target sampling point is the nearest neighbor sampling point corresponding to the target time distance;

[0068] The evaluation result acquisition unit 440 is used to obtain the evaluation result of the lane line recognition result based on the target sampling points corresponding to the lane line recognition result of each frame.

[0069] As a method, the lane line recognition result acquisition unit 410 is specifically used to obtain lane line recognition results of two consecutive frames; or, to obtain two frames of lane line recognition results with an interval of a preset number of frames; or, to obtain two consecutive groups of lane line recognition results, each group of lane line recognition results includes multiple consecutive frames of lane line recognition results.

[0070] As a method, the lane line recognition result includes multiple lane lines, each lane line includes multiple sampling points, and the target time distance acquisition unit 420 is specifically used to obtain multiple sampling points contained in the target lane line in each frame of the lane line recognition result according to the lane line recognition result of each frame; based on the target time distance corresponding to the lane line recognition result of each frame, obtain the end point corresponding to the target time distance; based on the multiple sampling points and the end point, obtain the target sampling point.

[0071] As another way, there are multiple preset target times, and the target time distance acquisition unit 420 is specifically used to obtain multiple target time distances corresponding to each frame of the lane line recognition result based on the multiple preset target times and the vehicle speed corresponding to each frame of the lane line recognition result, wherein one preset target time corresponds to one target time distance. The target sampling point acquisition unit 430 is specifically used to obtain the target sampling point corresponding to each frame of the lane line recognition result according to each frame of the lane line recognition result and the multiple target time distances corresponding to each frame of the lane line recognition result.

[0072] As a method, the target sampling point acquisition unit 430 is specifically used to obtain multiple sampling points contained in the target lane line in each frame of the lane line recognition result according to the lane line recognition result of each frame; based on the target time distance corresponding to the lane line recognition result of each frame, obtain the end point corresponding to the target time distance; based on the multiple sampling points and the end point, obtain the target sampling point.

[0073] Optionally, the target sampling point acquisition unit 430 is specifically used to divide each lane line into multiple lane line segments according to a fixed length; based on the sampling points included in each lane line segment, obtain the cluster center of each lane line segment to obtain the multiple cluster centers contained in each lane line; obtain the vehicle position corresponding to the lane line recognition result of each frame; based on the distances between the multiple cluster centers contained in each lane line and the vehicle position, obtain the type of each lane line; take the lane line of the type adjacent to the left lane line or the lane line from the left lane line or the lane line from the right lane line or the lane line adjacent to the right lane line as the target lane line to obtain the multiple sampling points contained in the target lane line.

[0074] Optionally, the target sampling point acquisition unit 430 is specifically used to acquire multiple target straight lines, each of which is a straight line at the end point of the corresponding target time distance, and each of which is perpendicular to the longitudinal driving direction of the vehicle; based on the distances between each of the target straight lines and multiple sampling points included in the target lane line in the corresponding lane line recognition result, the sampling point closest to each of the target straight lines is obtained, and the sampling point closest to each of the target straight lines is used as the target sampling point.

[0075] As a method, the evaluation result acquisition unit 440 is specifically used to obtain the lateral difference between the target sampling points at the same target time distance in the lane line recognition results of different frames based on the target sampling points corresponding to the lane line recognition results of each frame; based on the lateral difference and the time interval between the lane line recognition results of different frames, the evaluation result is obtained, and the evaluation result characterizes the lateral position change rate of the target sampling point.

[0076] The following will be combined Figure 6 A vehicle provided in the present application is described.

[0077] See also Figure 6 Based on the above lane line recognition evaluation method and device, the embodiment of the present application also provides another vehicle 100 that can execute the above lane line recognition evaluation method. The vehicle 100 includes a processor 102 and a memory 104. The memory 104 stores a program that can execute the content of the above embodiment, and the backup processor 102 can execute the program stored in the memory 104.

[0078] Among them, the processor 102 may include one or more processing cores. The processor 102 uses various interfaces and lines to connect various parts in the entire vehicle 100, and executes various functions and processes data of the vehicle 100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 104, and calling data stored in the memory 104. Optionally, the processor 102 can be implemented in at least one hardware form of a network processor (Neural network Processing Unit, NPU), a digital signal processing (Digital Signal Processing, DSP), a field programmable gate array (Field-Programmable Gate Array, FPGA), and a programmable logic array (Programmable Logic Array, PLA). The processor 102 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU), a network processor (Neural network Processing Unit, NPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing display content; the NPU is responsible for processing multimedia data such as video and images; and the modem is used to process wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 102, but may be implemented separately through a communication chip.

[0079] The memory 104 may include a random access memory (RAM), and may also include a read-only memory (RAM) and a double data rate synchronous dynamic random access memory (DDR). The memory 104 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 104 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data created by the vehicle 100 during use (such as a phone book, audio and video data, chat record data), etc.

[0080] An embodiment of the present application provides a computer-readable storage medium in which a program code is stored, and the program code can be called by a processor to execute the method described in the above method embodiment.

[0081] The computer readable storage medium may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable storage medium includes a non-transitory computer-readable storage medium. The computer readable storage medium has storage space for program codes that execute any of the method steps in the above method. These program codes can be read from or written to one or more computer program products. The program code can be compressed, for example, in an appropriate form.

[0082] In summary, the present application provides a lane line recognition evaluation method, device, and vehicle. After obtaining at least two frames of lane line recognition results and obtaining the vehicle speed corresponding to each frame of the lane line recognition results, based on the preset target time and the vehicle speed corresponding to each frame of the lane line recognition results, the target time distance corresponding to each frame of the lane line recognition results is obtained. According to each frame of the lane line recognition results and the target time distance corresponding to each frame of the lane line recognition results, the target sampling point corresponding to each frame of the lane line recognition results is obtained. Based on the target sampling point corresponding to each frame of the lane line recognition results, the evaluation result of the lane line recognition result is obtained. Through the above-mentioned method, after obtaining at least two frames of lane line recognition results and obtaining the vehicle speed corresponding to each frame of the lane line recognition results, based on the preset target time and the vehicle speed corresponding to each frame of the lane line recognition results, the target time distance corresponding to each frame of the lane line recognition results is obtained, thereby obtaining the target sampling point corresponding to each frame of the lane line recognition results. The evaluation result of the lane line recognition result can be obtained based on the target sampling point corresponding to each frame of the lane line recognition results, and the evaluation can be completed without relying on the parameters collected by the external sensor, thereby reducing the evaluation cost.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A lane line recognition evaluation method, characterized in that: The method comprises: Obtaining lane line recognition results of at least two frames and obtaining a vehicle speed corresponding to the lane line recognition results of each frame; Based on the preset target time and the vehicle speed corresponding to each frame of the lane line recognition result, a target time distance corresponding to each frame of the lane line recognition result is obtained, where the target time distance is the longitudinal distance traveled by the vehicle at the preset target time; According to the lane line recognition result of each frame and the target time distance corresponding to the lane line recognition result of each frame, a target sampling point corresponding to the lane line recognition result of each frame is obtained, and the target sampling point is a nearest neighbor sampling point corresponding to the target time distance; Based on the target sampling points corresponding to the lane line recognition results of each frame, an evaluation result of the lane line recognition result is obtained.

2. The method according to claim 1, characterized in that The lane line recognition result includes multiple lane lines, each lane line includes multiple sampling points, and obtaining the target sampling points corresponding to each frame of the lane line recognition result according to each frame of the lane line recognition result and the target time distance corresponding to each frame of the lane line recognition result includes: According to the lane line recognition result of each frame, a plurality of sampling points included in the target lane line in the lane line recognition result of each frame are obtained; Based on the target time distance corresponding to the lane line recognition result of each frame, an end point corresponding to the target time distance is obtained; The target sampling point is obtained based on the multiple sampling points and the end point.

3. The method according to claim 2, characterized in that The method of obtaining a plurality of sampling points contained in the target lane line in each frame of the lane line recognition result according to each frame of the lane line recognition result includes: Divide each lane line into multiple lane line segments according to a fixed length; Based on the sampling points included in each lane line segment, a cluster center of each lane line segment is obtained to obtain a plurality of cluster centers included in each lane line segment; Obtaining the vehicle position corresponding to the lane line recognition result of each frame; Obtaining the type of each lane line based on the distances between a plurality of cluster centers included in each lane line and the vehicle position; A lane line of a type adjacent to a left lane line, a lane line from a left lane line, a lane line from a right lane line, or an adjacent to a right lane line is taken as the target lane line to obtain a plurality of sampling points included in the target lane line.

4. The method according to claim 2, characterized in that: There are multiple target time distances, and obtaining the target sampling point based on the multiple sampling points and the end point includes: Acquire multiple target straight lines, each of which is a straight line corresponding to the end point of the target time distance, and each of which is perpendicular to the longitudinal driving direction of the vehicle; Based on the distances between each target straight line and a plurality of sampling points included in the target lane line in the corresponding lane line recognition result, the sampling point closest to each target straight line is obtained, and the sampling point closest to each target straight line is used as the target sampling point.

5. The method according to claim 1, characterized in that The evaluation result of the lane line recognition result is obtained based on the target sampling point corresponding to the lane line recognition result of each frame, including: Based on the target sampling points corresponding to the lane line recognition results of each frame, a lateral difference between the target sampling points at the same target time distance in the lane line recognition results of different frames is obtained; Based on the lateral difference and the time interval between the lane line recognition results of different frames, the evaluation result is obtained, and the evaluation result represents the lateral position change rate of the target sampling point.

6. The method according to claim 1, characterized in that There are multiple preset target times, and obtaining the target time distance corresponding to each frame of the lane line recognition result based on the preset target time and the vehicle speed corresponding to each frame of the lane line recognition result includes: Based on the multiple preset target times and the vehicle speed corresponding to each frame of the lane line recognition result, a plurality of target time distances corresponding to each frame of the lane line recognition result are obtained, wherein one preset target time corresponds to one target time distance; The obtaining, according to the lane line recognition result of each frame and the target time distance corresponding to the lane line recognition result of each frame, the target sampling point corresponding to the lane line recognition result of each frame includes: According to the lane line recognition result of each frame and the multiple target time distances corresponding to the lane line recognition result of each frame, the target sampling point corresponding to the lane line recognition result of each frame is obtained.

7. The method according to any one of claims 1 to 6, characterized in that: The obtaining of at least two frames of lane line recognition results includes: Get the lane line recognition results of two consecutive frames; or, Obtain two frames of lane line recognition results with a preset frame interval; or, Two consecutive groups of lane line recognition results are obtained, each group of lane line recognition results includes consecutive multiple frames of lane line recognition results.

8. A lane line recognition evaluation device, characterized in that: The device comprises: A lane line recognition result acquisition unit, used to acquire lane line recognition results of at least two frames and acquire the vehicle speed corresponding to the lane line recognition results of each frame; A target time distance acquisition unit is used to obtain a target time distance corresponding to each frame of the lane line recognition result based on a preset target time and a vehicle speed corresponding to each frame of the lane line recognition result, wherein the target time distance is a longitudinal distance traveled by the vehicle at the preset target time; A target sampling point acquisition unit is used to obtain a target sampling point corresponding to each lane line recognition result according to each frame of the lane line recognition result and the target time distance corresponding to each frame of the lane line recognition result, wherein the target sampling point is the nearest neighbor sampling point corresponding to the target time distance; The evaluation result acquisition unit is used to obtain the evaluation result of the lane line recognition result based on the target sampling point corresponding to the lane line recognition result of each frame.

9. A vehicle, characterized in that: comprising one or more processors and memory; One or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, wherein when the program code is run, the method according to any one of claims 1 to 7 is executed.

Citation Information

Patent Citations

  • Vehicle control method, device and storage medium

    CN112849144A

  • Lane line identification evaluation method and device, electronic equipment and storage medium

    CN116994119A

  • Curve radius estimation method and system, medium, electronic equipment, vehicle machine and vehicle

    CN117584982A

  • Method and System for Synthesizing a Lane Image

    US20170330043A1