Roadside sensing precision test method, device, equipment, medium and product

Abstract

The invention discloses a roadside sensing precision test method, device and equipment, a medium and a product. The method comprises the following steps: acquiring actual track information and sensing target track information of a test vehicle in a sensing area of roadside sensing equipment; matching the actual track information with the perceived target track information according to a track point transverse and longitudinal distance error condition to obtain a first target track; when the number of the first target tracks is 1, determining a perception precision test result corresponding to each test item according to a track point matching condition between the actual track information and the first target tracks; and when the number of the first target trajectories is greater than 1, determining a second target trajectory based on a trajectory intersection condition between the first target trajectories, and determining a perception precision test result corresponding to each test item according to a trajectory point matching condition between the actual trajectory information and the second target trajectory. The sensing precision condition of a complete test track can be measured more comprehensively, and the accuracy and reliability of sensing precision test are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent network connection technology, and in particular to a roadside perception accuracy testing method, device, equipment, medium and product. Background Art

[0002] With the rapid development and popularization of intelligent network technology, intelligent network vehicles have become an important part of the future intelligent transportation system. Vehicles need to rely on roadside sensing equipment when driving on the road, and the perception accuracy of roadside sensing equipment is an important basis for evaluating the perception performance of sensing equipment.

[0003] The existing roadside perception accuracy test method usually selects a test vehicle with high-precision positioning as the true value vehicle, and selects the perception target trajectory with the smallest error as the perception result corresponding to the test vehicle by matching multiple perception target trajectories perceived by the roadside perception equipment with the actual trajectory of the test vehicle, and calculates the roadside perception accuracy test result based on this. However, the above method does not take into account the possibility of jumps in the perception target identification (ID), that is, it can only match a section of the trajectory and calculate the perception accuracy corresponding to this section of the trajectory, and cannot fully measure the perception accuracy of the complete test trajectory. Summary of the invention

[0004] The present invention provides a roadside perception accuracy test method, device, equipment, medium and product, which takes into account the possibility of jump changes in perception target identification, adds a multi-perception target trajectory matching process, and can more comprehensively measure the perception accuracy of the complete test trajectory, thereby improving the accuracy and reliability of the roadside perception accuracy test results.

[0005] According to one aspect of the present invention, a roadside perception accuracy testing method is provided, the method comprising:

[0006] Obtaining the actual trajectory information and the perceived target trajectory information of the test vehicle within the perception area of ​​the roadside perception device;

[0007] The actual trajectory information and the perceived target trajectory information are matched according to the horizontal and vertical distance errors of the trajectory points to obtain a first target trajectory;

[0008] When the number of the first target trajectory is 1, determining the perception accuracy test result corresponding to each test item according to the trajectory point matching between the actual trajectory information and the first target trajectory;

[0009] When the number of first target trajectories is greater than 1, the second target trajectory is determined based on the trajectory intersection between the first target trajectories, and the perception accuracy test result corresponding to each test item is determined according to the actual trajectory information and the trajectory point matching between the second target trajectories.

[0010] According to another aspect of the present invention, a roadside perception accuracy testing device is provided, the device comprising:

[0011] A trajectory information acquisition module is used to obtain the actual trajectory information and the perception target trajectory information of the test vehicle in the perception area of ​​the roadside perception device;

[0012] A trajectory matching module is used to match the actual trajectory information and the perceived target trajectory information according to the horizontal and vertical distance errors of the trajectory points to obtain a first target trajectory;

[0013] A first result determination module, configured to determine the perception accuracy test result corresponding to each test item according to the matching of the track points between the actual track information and the first target track when the number of the first target track is 1;

[0014] The second result determination module is used to determine the second target trajectory based on the trajectory intersection between the first target trajectories when the number of the first target trajectories is greater than 1, and determine the perception accuracy test result corresponding to each test item according to the actual trajectory information and the trajectory point matching between the second target trajectory.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the roadside perception accuracy testing method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the roadside perception accuracy testing method described in any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the roadside perception accuracy testing method described in any embodiment of the present invention is implemented.

[0021] The technical solution of the embodiment of the present invention is to obtain the actual trajectory information and the perceived target trajectory information of the test vehicle in the perception area of ​​the roadside perception device; match the actual trajectory information and the perceived target trajectory information according to the horizontal and vertical distance errors of the trajectory points to obtain the first target trajectory; when the number of first target trajectories is 1, determine the perception accuracy test results corresponding to each test item based on the trajectory point matching between the actual trajectory information and the first target trajectory; when the number of first target trajectories is greater than 1, determine the second target trajectory based on the trajectory intersection between each first target trajectory, and determine the perception accuracy test results corresponding to each test item based on the trajectory point matching between the actual trajectory information and the second target trajectory. This technical solution takes into account the possibility of jumps in the perception target identification, adds a multi-perception target trajectory matching process, can more comprehensively measure the perception accuracy of the complete test trajectory, and improves the accuracy and reliability of the roadside perception accuracy test results.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a roadside perception accuracy testing method provided according to Embodiment 1 of the present invention;

[0025] Figure 2 is an example diagram of a target plane coordinate system provided according to the first embodiment of the present invention;

[0026] Figure 3 is an example diagram of trajectory intersection provided according to the first embodiment of the present invention;

[0027] Figure 4 is a flow chart of a roadside perception accuracy testing method provided according to Embodiment 2 of the present invention;

[0028] Figure 5 is a schematic diagram of the structure of a roadside perception accuracy testing device provided according to Embodiment 3 of the present invention;

[0029] Figure 6 It is a schematic diagram of the structure of an electronic device for implementing the roadside perception accuracy testing method of an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1 This is a flow chart of a roadside perception accuracy test method provided in the first embodiment of the present invention. This embodiment can be applied to the case where the perception accuracy of roadside perception equipment is tested in a vehicle-road-cloud integrated system. The method can be executed by a roadside perception accuracy test device. The roadside perception accuracy test device can be implemented in the form of hardware and / or software. The roadside perception accuracy test device can be configured in an electronic device. Figure 1 As shown, a roadside perception accuracy testing method provided in the first embodiment specifically includes the following steps:

[0034] S110, obtaining actual trajectory information and perception target trajectory information of the test vehicle within the perception area of ​​the roadside perception device.

[0035] The test vehicle may refer to a real vehicle used for roadside perception accuracy testing. The test vehicle may be an intelligent connected vehicle equipped with high-precision positioning equipment and an on-board unit (OBU). The high-precision positioning equipment may include but is not limited to: on-board RTK (Real Time Kinematic) and combined inertial navigation. Roadside perception equipment may refer to sensor equipment such as cameras and radars installed on the side of the road. It is understood that in the roadside perception system of the Internet of Vehicles, the roadside perception equipment usually shines on the front and rear of the vehicle to monitor and perceive passing vehicles.

[0036] The actual trajectory information can be understood as the real driving trajectory information corresponding to the test vehicle. The actual trajectory information contains the test true value information such as the timestamp, position, speed and heading angle of each actual trajectory point.

[0037] The perception target trajectory information can be understood as the driving trajectory information of each perception target perceived by the roadside perception device. The perception target trajectory information includes perception information such as the timestamp, position, speed, and heading angle of each perception target trajectory point corresponding to each perception target. Among them, the perception target can refer to each motor vehicle among the traffic participants perceived by the roadside perception device.

[0038] In an embodiment of the present invention, when it is necessary to test the perception accuracy of roadside perception equipment such as cameras and radars, the test vehicle can be controlled to pass through the perception area of ​​the corresponding roadside perception equipment, so as to obtain the actual trajectory information of the vehicle end and the perception target trajectory information of the roadside end; wherein, the actual trajectory information can be collected by the camera, radar and other vehicle-mounted sensors configured by the test vehicle itself, or it can be parsed from the Basic Safety Message (BSM) data stored in the OBU; the perception target trajectory information can be parsed from the Road Safety Message (RSM) data broadcast by the Road Side Unit (RSU).

[0039] S120, matching the actual trajectory information and the perceived target trajectory information according to the horizontal and vertical distance errors of the trajectory points to obtain a first target trajectory.

[0040] Among them, the horizontal and vertical distance errors of the trajectory points can be understood as the errors in the horizontal and vertical distances between the actual trajectory points in the actual trajectory information and the perceived target trajectory points of each perceived target in the perceived target trajectory information. The horizontal and vertical distance errors of the trajectory points can be used to screen out the perceived targets that match the test vehicle.

[0041] The first target trajectory can be understood as a number of perception target trajectories that are more closely matched with the actual trajectory of the test vehicle, which are screened out after matching the horizontal and vertical distance errors between the actual trajectory points and the perception target trajectory points of each perception target. It can be understood that since the roadside perception equipment may experience a perception target ID jump, the number of first target trajectories may be greater than 1.

[0042] In an embodiment of the present invention, after obtaining the actual trajectory information and the perceived target trajectory information, the actual trajectory points and the perceived target trajectory points of each perceived target can be matched according to the horizontal and vertical distance errors of the trajectory points, that is, according to the deviations in the horizontal distance and the vertical distance between the two trajectories, the first target trajectory can be screened out from the perceived target trajectories corresponding to each perceived target. Furthermore, in order to facilitate the determination of the horizontal / longitudinal distance between the actual trajectory points and the perceived target trajectory points, the embodiment of the present invention can automatically establish a corresponding plane coordinate system according to the position of the test vehicle before performing trajectory matching on the actual trajectory information and the perceived target trajectory information, and then convert each actual trajectory point and the perceived target trajectory point to the above-mentioned plane coordinate system, and use the converted actual trajectory point coordinates and the perceived target trajectory point coordinates to conveniently determine the horizontal / longitudinal distance corresponding to each trajectory point.

[0043] S130. When the number of the first target trajectory is 1, determine the perception accuracy test result corresponding to each test item according to the trajectory point matching between the actual trajectory information and the first target trajectory.

[0044] The track point matching situation may refer to the track point matching result between the actual track of the test vehicle and the first target track. The test items may include but are not limited to: perceived position accuracy, perceived speed accuracy, perceived heading angle accuracy, etc.

[0045] In an embodiment of the present invention, when the number of the first target track selected is 1, the track points can be matched between the actual track information and the first target track according to the timestamp, and the track point matching situation corresponding to the two tracks, that is, the track point matching pair result, can be determined, and then the corresponding average position error (including the average lateral position error and the average longitudinal position error), average speed error and average heading angle error and other test items of perception accuracy test results can be determined according to the track point matching pair result. Taking the calculation method of the average speed error as an example, the speed difference of each group of matching points in the track point matching pair result can be determined first, and then the speed difference of each group of matching points can be averaged to obtain the final average speed error, and the average speed error is used as the final perception speed accuracy test result.

[0046] S140: When the number of first target trajectories is greater than 1, determine the second target trajectory based on the trajectory intersection between the first target trajectories, and determine the perception accuracy test result corresponding to each test item according to the actual trajectory information and the trajectory point matching between the second target trajectories.

[0047] Among them, the trajectory intersection situation can be understood as the trajectory point coverage between the first target trajectories. The second target trajectory can be understood as the best perceived target trajectory determined based on the trajectory intersection situation between the first target trajectories, taking into account the perceived target ID jump. It can be understood that, according to different trajectory intersection situations, the best perceived target trajectory may be one of the above-mentioned first target trajectories, or it may be generated by merging several first target trajectories whose trajectories do not intersect with each other in the above-mentioned first target trajectories.

[0048] In an embodiment of the present invention, when the number of screened first target trajectories is greater than 1, that is, the roadside perception device may have a perception target ID jump, the first target trajectories can be sorted according to the trajectory matching error between each first target trajectory and the actual trajectory of the test vehicle (for example, the average longitudinal absolute distance error), and then traversed from the first target trajectory with the smallest trajectory matching error to determine the trajectory intersection between it and the remaining first target trajectories. If there is a trajectory intersection among the remaining first target trajectories, the first target trajectory is directly eliminated, and after the traversal is completed, the trajectories that do not intersect with each other are retained, that is, the second target trajectory is obtained; at this time, if the number of second target trajectories is 1, the perception accuracy test results corresponding to each test item are determined according to the trajectory point matching between the actual trajectory of the test vehicle and the second target trajectory; if the number of second target trajectories is greater than 1, the above-mentioned second target trajectories are merged, and then the perception accuracy test results corresponding to each test item are determined according to the trajectory point matching between the actual trajectory of the test vehicle and the merged trajectory.

[0049] The technical solution of the embodiment of the present invention is to obtain the actual trajectory information and the perceived target trajectory information of the test vehicle in the perception area of ​​the roadside perception device; match the actual trajectory information and the perceived target trajectory information according to the horizontal and vertical distance errors of the trajectory points to obtain the first target trajectory; when the number of first target trajectories is 1, determine the perception accuracy test results corresponding to each test item based on the trajectory point matching between the actual trajectory information and the first target trajectory; when the number of first target trajectories is greater than 1, determine the second target trajectory based on the trajectory intersection between each first target trajectory, and determine the perception accuracy test results corresponding to each test item based on the trajectory point matching between the actual trajectory information and the second target trajectory. This technical solution takes into account the possibility of jumps in the perception target identification, adds a multi-perception target trajectory matching process, can more comprehensively measure the perception accuracy of the complete test trajectory, and improves the accuracy and reliability of the roadside perception accuracy test results.

[0050] Furthermore, based on the above-mentioned embodiments of the invention, a roadside perception accuracy testing method provided in this embodiment further includes:

[0051] Receive and parse map message data sent by the roadside unit;

[0052] Match the target area map and upstream and downstream nodes in the map message data according to the actual track point position in the actual track information;

[0053] By traversing the lane point set between the upstream and downstream nodes in the target area map, the first lane edge, the second lane edge and the stop line are determined; wherein the first lane edge is the right lane edge of the rightmost lane based on the lane direction, and the second lane edge is the left lane edge of the leftmost lane based on the lane direction;

[0054] The intersection of the first lane edge and the stop line is taken as the origin of the coordinate system, and a point on the first lane edge is selected as a coordinate point in the x-axis direction of the coordinate system, and the intersection of the second lane edge and the stop line is selected as a coordinate point in the y-axis direction of the coordinate system to establish the corresponding target plane coordinate system.

[0055] Among them, the map (MAP) message data may include multiple regional map data (nodes), the regional map data is used to record the map data of the intersection or road section, the regional map data at least includes multiple directed sections from one regional map to another regional map, and the directed sections at least include multiple lane information; it can be understood that a single node can contain multiple links, a link is a directed section from one node to another node, and a link is uniquely identified by the node and upstreamNodeId; a link can be identified by points to identify the position and direction, and points are the points on the center line of the link, arranged from upstream to downstream. Lane information includes at least multiple identification points on the center line of the lane, and the identification points are used to identify the position and direction of the lane, arranged from upstream to downstream. It can be understood that a single link can have multiple lanes, a lane is a lane, a lane is uniquely identified by a laneId, a lane is identified by points to identify the position and direction, and points are points on the center line of the lane, arranged from upstream to downstream.

[0056] The target area map can be understood as an area map matched in the map message data according to the locations of the trajectory points of the test vehicle during the test time.

[0057] In an embodiment of the present invention, before performing trajectory matching on the actual trajectory information and the perceived target trajectory information, a corresponding plane coordinate system can be automatically established according to the position of the test vehicle. Specifically, the MAP message data broadcast by the roadside RSU can be received and parsed, and then the corresponding target area map and upstream and downstream nodes can be matched in the above MAP message data according to the trajectory point position of the test vehicle during the test time; then, by traversing multiple lane point sets between the upstream and downstream nodes in the target area map, the corresponding first lane edge line (point set), the second lane edge line (point set) and the stop line (point set) are determined, wherein, as Figure 2 As shown, the first lane edge is the right lane edge of the rightmost lane based on the lane direction, and the second lane edge is the left lane edge of the leftmost lane based on the lane direction; finally, the intersection of the first lane edge and the stop line can be selected as the origin O of the coordinate system, a point on the first lane edge can be selected as a coordinate point A in the x-axis direction of the coordinate system, and the intersection of the second lane edge and the stop line can be selected as a coordinate point B in the y-axis direction of the coordinate system, thereby establishing the corresponding target plane coordinate system. This embodiment can automatically determine the plane coordinate system according to the position of the test vehicle, reducing the steps that require manual participation and calibration, and reducing the labor cost of the test work; at the same time, the custom plane coordinate system can also make it easier to calculate the lateral and longitudinal distances of each track point in the subsequent calculation.

[0058] Further, based on the above-mentioned embodiment of the invention, S110 specifically includes the following steps:

[0059] S1101, when the test vehicle passes through the sensing area of ​​the roadside sensing device, reading the basic safety message data stored in the vehicle-mounted unit, and receiving the roadside safety message data sent by the roadside unit;

[0060] S1102, parsing the basic safety message data, obtaining and recording the actual trajectory information of the test vehicle corresponding to each actual trajectory point; wherein the actual trajectory information includes: the timestamp of the actual trajectory point, the position of the actual trajectory point, the speed of the actual trajectory point and the heading angle of the actual trajectory point;

[0061] S1103. Take motor vehicles among traffic participants as perception targets, parse the roadside safety message data to obtain the perception target trajectory information of each perception target corresponding to each perception target trajectory point and record it; wherein the perception target trajectory information includes: perception target identification, perception target trajectory point timestamp, perception target trajectory point position, perception target trajectory point speed and perception target trajectory point heading angle.

[0062] Among them, the basic safety message (BSM) data may include basic status information of the test vehicle, such as but not limited to the timestamp, (longitude and latitude) position, speed and heading angle of each actual trajectory point of the test vehicle.

[0063] Roadside safety message (RSM) data may be information collected and broadcast by RSU, which may be used to describe the real-time motion status of each traffic participant, wherein RSU is a device installed on the roadside that may communicate with the OBU in the test vehicle to provide real-time traffic information; in this embodiment, RSM message data may include but is not limited to the timestamp, (longitude and latitude) position, speed and heading angle of each perception target corresponding to each perception target trajectory point, and perception target identification (ID), etc.

[0064] In an embodiment of the present invention, when a test vehicle passes through the perception area of ​​a roadside perception device, the OBU reads the BSM message data recorded by itself and the RSM message data broadcast by the roadside RSU, and then parses the BSM message data to obtain the actual trajectory point timestamp, actual trajectory point position, actual trajectory point speed and actual trajectory point heading angle of each actual trajectory point, and stores the above actual trajectory information, for example, it can be stored in a table form; at the same time, by screening and parsing the perception targets whose traffic participants are classified as motor vehicles in the RSM message data, the perception target ID of each perception target and the perception target trajectory point timestamp, perception target trajectory point position, perception target trajectory point speed and perception target trajectory point heading angle corresponding to each perception target trajectory point can be obtained, and the above perception target trajectory information can be stored according to the perception target ID.

[0065] Further, based on the above-mentioned embodiment of the invention, S120 specifically includes the following steps:

[0066] S1201, respectively reading the actual trajectory point timestamp, the actual trajectory point position, the actual trajectory point speed and the actual trajectory point heading angle in the actual trajectory information, and reading the perceived target identifier, the perceived target trajectory point timestamp, the perceived target trajectory point position, the perceived target trajectory point speed and the perceived target trajectory point heading angle corresponding to each perceived target in the perceived target trajectory information;

[0067] S1202, respectively converting the positions of each actual trajectory point and each perceived target trajectory point into a target plane coordinate system to obtain the actual trajectory point coordinates corresponding to the test vehicle and the perceived target trajectory point coordinates corresponding to each perceived target;

[0068] S1203, determining the average value of the vertical distances between the coordinates of each actual trajectory point and the x-axis to obtain the actual average horizontal absolute distance, and determining the average value of the vertical distances between the coordinates of each perceived target trajectory point corresponding to each perceived target and the x-axis to obtain the perceived target average horizontal absolute distance corresponding to each perceived target;

[0069] S1204, respectively determining the difference between the average horizontal absolute distance of each perceived target and the actual average horizontal absolute distance, to obtain an average horizontal absolute distance difference;

[0070] S1205, traversing each perception target according to the perception target identifier, and determining the corresponding perception target whose average horizontal absolute distance difference is less than the first preset distance as a first-screening perception target;

[0071] S1206, according to the actual trajectory point timestamp and the perception target trajectory point timestamp of each first-screened perception target, the perception target trajectory point coordinates of each first-screened perception target are matched with the actual trajectory point coordinates to obtain first trajectory point matching pairs corresponding to the actual trajectory and each perception target trajectory;

[0072] S1207, traverse each primary screening perception target, determine the average longitudinal absolute distance error corresponding to each first trajectory point matching pair, determine the corresponding primary screening perception target whose average longitudinal absolute distance error is less than the second preset distance as the secondary screening perception target, and use the coordinates of each perception target trajectory point corresponding to the secondary screening perception target as the first target trajectory.

[0073] In the embodiment of the present invention, the process of acquiring the first target trajectory specifically includes:

[0074] 1) Read the timestamp, position, speed and heading angle of each actual trajectory point of the test vehicle obtained by the above analysis, as well as the timestamp, position, speed and heading angle of each perception target trajectory point of each perception target.

[0075] 2) Each actual trajectory point position and the perceived target trajectory point position are converted to the target plane coordinate system established above to obtain the actual trajectory point coordinates and the perceived target trajectory point coordinates after coordinate conversion.

[0076] 3) Calculate the vertical distance (i.e., horizontal distance) of each actual trajectory point coordinate from the x-axis respectively, and then average the vertical distances calculated for all actual trajectory point coordinates to obtain the corresponding actual average horizontal absolute distance; similarly, determine the average horizontal absolute distance of the perceived target corresponding to each perceived target in turn.

[0077] 4) Traverse each perception target according to the perception target ID, calculate the difference between the corresponding average horizontal absolute distance of the perception target and the actual average horizontal absolute distance, that is, the average horizontal absolute distance difference, and determine the corresponding perception target whose average horizontal absolute distance difference is less than the first preset distance as a screened perception target.

[0078] 5) According to the timestamp matching method, the actual trajectory of the test vehicle is matched with the perception target trajectory of each primary screened perception target respectively, and the first trajectory point matching pairs corresponding to the actual trajectory of the test vehicle and each perception target trajectory are obtained respectively.

[0079] 6) Traverse each first-screened perception target and calculate the average longitudinal absolute distance error of its corresponding first trajectory point matching pair, that is, first calculate the longitudinal absolute distance error of each group of matching points in the first trajectory point matching pair (the absolute value of the longitudinal distance difference between the actual trajectory point coordinates and the perception target trajectory point coordinates), and then average the longitudinal absolute distance errors corresponding to all groups of matching points in the first trajectory point matching pair to obtain the average longitudinal absolute distance error corresponding to each first-screened perception target; then determine the corresponding first-screened perception target whose average longitudinal absolute distance error is less than the second preset distance as the second-screened perception target, and use the trajectory point coordinates of each perception target corresponding to the second-screened perception target as the first target trajectory.

[0080] Further, based on the above-mentioned embodiment of the invention, after determining the first screening perception target, the method further includes:

[0081] The timestamps of the perception target trajectory points of each once-screened perception target are compensated according to the preset delay compensation time.

[0082] Among them, the preset delay compensation time can be understood as the compensation time set for the streaming delay of the roadside perception device. The preset delay compensation time can be specifically configured according to the device type and device parameters of the roadside perception device. For example, for a camera, the preset delay compensation time can be set to 100 milliseconds. Taking the roadside perception device as a camera as an example, the following delays will occur during the transmission of the perceived image data to the OBU: acquisition delay, encoding delay, network transmission delay, etc. If the corresponding perception target trajectory point timestamp is not compensated, the perception accuracy determined subsequently will be overestimated, making the perception accuracy test result unreasonable and unreliable.

[0083] In the embodiment of the present invention, considering the delay of the roadside sensing device, the preset delay compensation time can be used to compensate the timestamp of the perception target trajectory point of each once-screened perception target, that is, the preset delay compensation time is subtracted from the timestamp of each perception target trajectory point. This embodiment uses delay compensation to reasonably align timestamps, which is more in line with the RSU fusion OBU and perception PTC (Perception, Tracking, Control) logic, and will not overestimate the perception accuracy.

[0084] It can be understood that the delay compensation operation can be performed after determining a primary screening perception target, or it can be performed after parsing the perception target trajectory point timestamp in the RSM message data. This embodiment does not limit this, that is, not performing delay compensation will not affect the primary screening (i.e., lateral distance screening).

[0085] Further, based on the above-mentioned embodiment of the invention, S130 specifically includes the following steps:

[0086] S1301, extracting first trajectory point matching pairs corresponding to the coordinates of each actual trajectory point in the actual trajectory information and the first target trajectory;

[0087] S1302, based on the actual trajectory point position, the actual trajectory point speed and the actual trajectory point heading angle in the actual trajectory information, and the perceived target trajectory point position, the perceived target trajectory point speed and the perceived target trajectory point heading angle in the perceived target trajectory information corresponding to the first target trajectory, determine the average position error, the average speed error and the average heading angle error corresponding to the first trajectory point matching pair, and use the average position error, the average speed error and the average heading angle error as the perception accuracy test result.

[0088] In an embodiment of the present invention, when the number of first target trajectories screened out is 1, the first trajectory point matching pairs corresponding to the actual trajectory of the test vehicle determined above and the first target trajectory can be extracted, and then the corresponding average position error is determined as the perceived position accuracy test result based on the actual trajectory point position and the perceived target trajectory point position of each group of matching points in the first trajectory point matching pairs, the corresponding average speed error is determined as the perceived speed accuracy test result based on the actual trajectory point speed and the perceived target trajectory point speed of each group of matching points, and the corresponding average heading angle error is determined as the perceived heading angle accuracy test result based on the actual trajectory point heading angle and the perceived target trajectory point heading angle of each group of matching points.

[0089] Further, based on the above-mentioned embodiment of the invention, S140 specifically includes the following steps:

[0090] S1401, sorting the first target trajectories in ascending order according to the corresponding average longitudinal absolute distance errors, and starting from the first target trajectory corresponding to the smallest average longitudinal absolute distance error, eliminating all other first target trajectories that have an intersection area with the first target trajectory, and obtaining the second target trajectory after the traversal is completed;

[0091] S1402, when the number of second target trajectories is 1, extracting first trajectory point matching pairs corresponding to the coordinates of each actual trajectory point in the actual trajectory information and the second target trajectory, and taking the average position error, average speed error, and average heading angle error corresponding to the first trajectory point matching pairs as the perception accuracy test result;

[0092] S1403. When the number of second target trajectories is greater than 1, determine the second trajectory point matching pairs corresponding to the merged trajectory after the second target trajectories are merged and the coordinates of each actual trajectory point in the actual trajectory information, and use the average position error, average speed error and average heading angle error corresponding to the second trajectory point matching pairs as the perception accuracy test result.

[0093] In an embodiment of the present invention, when the number of the screened first target trajectories is greater than 1, that is, the roadside sensing device may have a sensing target ID jump, the first target trajectories can be sorted in ascending order according to the average longitudinal absolute distance error determined above, and the traversal starts from the corresponding first target trajectory with the smallest average longitudinal absolute distance error, and the sensing target trajectories of other IDs that have an intersecting area with its trajectory point are removed. After the traversal is completed, the trajectories that do not intersect with each other are retained, that is, the second target trajectory is obtained, wherein an example of determining whether the trajectories intersect is as follows: Figure 3 As shown; if the number of second target trajectories obtained is 1, the first trajectory point matching pairs corresponding to the actual trajectory of the test vehicle determined above and the second target trajectory are extracted, and then the average position error, average speed error and average heading angle error corresponding to the first trajectory point matching pairs are used as the final perceived position accuracy test results, perceived speed accuracy test results and perceived heading angle accuracy test results; if the number of second target trajectories is greater than 1, all second target trajectories are merged, and then the merged trajectory is matched with the actual trajectory of the test vehicle according to the timestamp to obtain the corresponding second trajectory point matching pairs, and finally the average position error, average speed error and average heading angle error corresponding to the second trajectory point matching pairs are used as the final perceived position accuracy test results, perceived speed accuracy test results and perceived heading angle accuracy test results.

[0094] Embodiment 2

[0095] Figure 4 This is a flow chart of a roadside perception accuracy test method provided in the second embodiment of the present invention. Based on the above embodiment, this embodiment provides an implementation of a roadside perception accuracy test method, which can realize the roadside perception accuracy test based on vehicle-road-cloud. Figure 4 As shown, a roadside perception accuracy test method provided by Embodiment 2 of the present invention is applied to an OBU configured in a test vehicle, and specifically includes the following steps:

[0096] S201. Obtain BSM message data, RSM message data, and MAP message data when a test vehicle passes through a perception area of ​​a roadside perception device.

[0097] In the embodiment of the present invention, the BSM message data, the RSM message data and the MAP message data may be stored in the form of logs.

[0098] S202: parse the BSM message data and the RSM message data to obtain actual trajectory information and perceived target trajectory information.

[0099] S203, parsing the MAP message data to obtain a lane point set, and determining a target plane coordinate system according to the OBU track point position and the lane point set.

[0100] In the embodiment of the present invention, the OBU trajectory point is the actual driving trajectory point of the test vehicle.

[0101] S204, converting the position of each OBU trajectory point to the target plane coordinate system, and determining the average of the vertical distances of the OBU trajectory point coordinates after the coordinate conversion from the x-axis to obtain the actual average horizontal absolute distance.

[0102] S205: convert the perceived target trajectory point position of each perceived target into a target plane coordinate system, and determine an average lateral absolute distance of the perceived target corresponding to each perceived target after the coordinate conversion.

[0103] S206, traverse each perception target, determine the difference between the corresponding average horizontal absolute distance of the perception target and the actual average horizontal absolute distance, and obtain the average horizontal absolute distance difference.

[0104] S207: Determine whether the average horizontal absolute distance difference is less than a first preset distance.

[0105] In the embodiment of the present invention, if the average horizontal absolute distance difference is less than the first preset distance (eg, 0.5 cm), S208 is executed, otherwise S209 is executed.

[0106] S208. Determine the perception target trajectory that meets the conditions as a first-screening perception target, perform delay compensation on the perception target timestamp corresponding to the first-screening perception target, and perform trajectory point matching on the OBU trajectory and the perception target trajectory of the first-screening perception target according to the aligned timestamps to obtain a first trajectory point matching pair.

[0107] It can be understood that by using the lateral distance error for trajectory screening, it is possible to screen out the perceived targets that are in the same lane as the test vehicle.

[0108] S209: Eliminate the perception targets that do not meet the conditions and make a judgment on the next perception target.

[0109] S210: Based on the first track point matching pair, determine the average longitudinal absolute distance error corresponding to the first screening perception target.

[0110] S211. Determine the corresponding first-screened perception target whose average longitudinal absolute distance error is less than the second preset distance as the second-screened perception target, and use the coordinates of each perception target trajectory point corresponding to the second-screened perception target as the first target trajectory.

[0111] S212: Determine whether the number of first target tracks is greater than 1.

[0112] In the embodiment of the present invention, if the number of the first target tracks is greater than 1, S213 is executed, otherwise S214 is executed.

[0113] S213, starting from the first target trajectory corresponding to the smallest average longitudinal absolute distance error, removing other perceived target trajectories that have an intersecting area with the first target trajectory, and obtaining the second target trajectory after the traversal is completed.

[0114] S214. Determine a corresponding perception accuracy test result based on a first track point matching pair corresponding to the OBU track and the first target track.

[0115] In the embodiment of the present invention, the perception accuracy test results may include: perception position accuracy test results, perception speed accuracy test results and perception heading angle accuracy test results.

[0116] S215: Determine whether the number of second target tracks is greater than 1.

[0117] In the embodiment of the present invention, if the number of the second target tracks is greater than 1, S216 and S218 are executed, otherwise S217 is executed.

[0118] S216: Merge all second target trajectories to obtain a merged trajectory.

[0119] S217: Determine a corresponding perception accuracy test result based on a first track point matching pair corresponding to the OBU track and the second target track.

[0120] S218. Determine a corresponding perception accuracy test result based on the second trajectory point matching pair corresponding to the OBU trajectory and the merged trajectory.

[0121] The technical solution of the embodiment of the present invention has at least the following technical effects:

[0122] 1) It can fully combine the characteristics of intelligent networking, automatically collect V2X (Vehicle to Everything) messages, and automatically determine the plane coordinate system according to the position of the test vehicle, reducing the steps that require manual participation and calibration, and reducing the labor cost of the test work; at the same time, the custom-constructed plane coordinate system can also make it easier to calculate the lateral and longitudinal distances of each trajectory point.

[0123] 2) Taking into account the delay of the roadside sensing device, a delay compensation process is added to properly align the timestamps, which is more in line with the RSU fusion OBU and perception PTC logic and will not overestimate the perception accuracy.

[0124] 3) Taking into account the possibility of jumps in the perception target identification, adding a multi-perception target trajectory matching process can more comprehensively measure the perception accuracy of the complete test trajectory, thereby improving the accuracy and reliability of the roadside perception accuracy test results.

[0125] 4) In the roadside perception system of the Internet of Vehicles, sensors such as cameras and radars are usually placed on the roadside, shining towards the front and rear of the vehicle to monitor and sense passing vehicles. The layout and angle of these sensors tend to focus more on monitoring the lateral movement of the vehicle, so the lateral error is often smaller. The difficulty of matching is mainly reflected in the matching of longitudinal points. Therefore, this solution excludes the influence of lateral distance and only uses longitudinal distance for trajectory matching, making the final roadside perception accuracy test results more accurate.

[0126] Embodiment 3

[0127] Figure 5 This is a schematic diagram of the structure of a roadside perception accuracy test device provided by Embodiment 3 of the present invention. Figure 5 As shown, the device comprises:

[0128] The trajectory information acquisition module 31 is used to obtain the actual trajectory information and the perception target trajectory information of the test vehicle in the perception area of ​​the roadside perception device;

[0129] A trajectory matching module 32 is used to match the actual trajectory information and the perceived target trajectory information according to the horizontal and vertical distance errors of the trajectory points to obtain a first target trajectory;

[0130] A first result determination module 33, configured to determine the perception accuracy test result corresponding to each test item according to the matching of the track points between the actual track information and the first target track when the number of the first target track is 1;

[0131] The second result determination module 34 is used to determine the second target trajectory based on the trajectory intersection between the first target trajectories when the number of the first target trajectories is greater than 1, and determine the perception accuracy test result corresponding to each test item according to the actual trajectory information and the trajectory point matching between the second target trajectories.

[0132] Furthermore, based on the above-mentioned embodiment of the invention, the roadside perception accuracy testing device further includes:

[0133] A map message parsing module, used to receive and parse the map message data sent by the roadside unit;

[0134] A map matching module is used to match the target area map and upstream and downstream nodes in the map message data according to the actual track point position in the actual track information;

[0135] The lane edge and stop line determination module is used to determine the first lane edge, the second lane edge and the stop line by traversing the lane point set between the upstream and downstream nodes in the target area map; wherein the first lane edge is the right lane edge of the rightmost lane based on the lane direction, and the second lane edge is the left lane edge of the leftmost lane based on the lane direction;

[0136] A coordinate system establishment module is used to use the intersection of the first lane edge and the stop line as the origin of the coordinate system, select a point on the first lane edge as a coordinate point in the x-axis direction of the coordinate system, and select the intersection of the second lane edge and the stop line as a coordinate point in the y-axis direction of the coordinate system to establish a corresponding target plane coordinate system.

[0137] Further, based on the above-mentioned embodiment of the invention, the trajectory information acquisition module 31 includes:

[0138] A message reading unit, used to read the basic safety message data stored in the vehicle-mounted unit and receive the roadside safety message data sent by the roadside unit when the test vehicle passes through the sensing area of ​​the roadside sensing device;

[0139] A basic safety message parsing unit is used to parse the basic safety message data, obtain the actual track information of each actual track point of the test vehicle and record it; wherein the actual track information includes: the timestamp of the actual track point, the position of the actual track point, the speed of the actual track point and the heading angle of the actual track point;

[0140] The roadside safety message parsing unit is used to take motor vehicles among traffic participants as perception targets, parse the roadside safety message data to obtain and record the perception target trajectory information of each perception target trajectory point corresponding to each perception target; wherein the perception target trajectory information includes: perception target identification, perception target trajectory point timestamp, perception target trajectory point position, perception target trajectory point speed and perception target trajectory point heading angle.

[0141] Further, based on the above-mentioned embodiment of the invention, the trajectory matching module 32 includes:

[0142] A trajectory information reading unit is used to read the actual trajectory point timestamp, actual trajectory point position, actual trajectory point speed and actual trajectory point heading angle in the actual trajectory information, and read the perception target identifier, perception target trajectory point timestamp, perception target trajectory point position, perception target trajectory point speed and perception target trajectory point heading angle corresponding to each perception target in the perception target trajectory information;

[0143] A trajectory point conversion unit is used to convert each actual trajectory point position and each perceived target trajectory point position into a target plane coordinate system to obtain the actual trajectory point coordinates corresponding to the test vehicle and the perceived target trajectory point coordinates corresponding to each perceived target;

[0144] The average horizontal absolute distance determination unit is used to determine the average value of the vertical distances between the coordinates of each actual trajectory point and the x-axis to obtain the actual average horizontal absolute distance, and to determine the average value of the vertical distances between the coordinates of each perceived target trajectory point corresponding to each perceived target and the x-axis to obtain the perceived target average horizontal absolute distance corresponding to each perceived target;

[0145] an average horizontal absolute distance difference determination unit, used to respectively determine the difference between the average horizontal absolute distance of each perceived target and the actual average horizontal absolute distance of each perceived target, to obtain an average horizontal absolute distance difference;

[0146] A primary screening unit, used to traverse each perception target according to the perception target identifier, and determine the corresponding perception target whose average horizontal absolute distance difference is less than the first preset distance as the primary screening perception target;

[0147] A first trajectory matching unit is used to match the coordinates of the perceived target trajectory points of each first-screened perceived target with the coordinates of the actual trajectory points according to the actual trajectory point timestamp and the perceived target trajectory point timestamp of each first-screened perceived target, and obtain first trajectory point matching pairs corresponding to the actual trajectory and each perceived target trajectory;

[0148] The secondary screening unit is used to traverse each primary screening perception target, determine the average longitudinal absolute distance error of each first trajectory point matching pair, determine the corresponding primary screening perception target whose average longitudinal absolute distance error is less than the second preset distance as the secondary screening perception target, and use the coordinates of each perception target trajectory point corresponding to the secondary screening perception target as the first target trajectory.

[0149] Further, based on the above-mentioned embodiment of the invention, the trajectory matching module 32 further includes:

[0150] The delay compensation unit is used to compensate the timestamp of the perception target trajectory point of each once-screened perception target according to a preset delay compensation time after determining the once-screened perception target.

[0151] Further, based on the above-mentioned embodiment of the invention, the first result determination module 33 includes:

[0152] A first trajectory point matching pair extraction unit, used to extract first trajectory point matching pairs corresponding to the coordinates of each actual trajectory point in the actual trajectory information and the first target trajectory;

[0153] The first perception accuracy test result determination unit is used to determine the average position error, average speed error and average heading angle error corresponding to the first trajectory point matching pair based on the actual trajectory point position, actual trajectory point speed and actual trajectory point heading angle in the actual trajectory information, and the perceived target trajectory point position, perceived target trajectory point speed and perceived target trajectory point heading angle in the perceived target trajectory information corresponding to the first target trajectory, and use the average position error, average speed error and average heading angle error as the perception accuracy test result.

[0154] Further, based on the above-mentioned embodiment of the invention, the second result determination module 34 includes:

[0155] A second target trajectory determination unit is used to sort the first target trajectories in ascending order according to the corresponding average longitudinal absolute distance errors, and start traversing from the corresponding first target trajectory with the smallest average longitudinal absolute distance error, eliminate all other first target trajectories that have an intersection area with the first target trajectory, and obtain the second target trajectory after the traversal is completed;

[0156] A second perception accuracy test result determination unit is used to extract, when the number of second target trajectories is 1, first trajectory point matching pairs corresponding to the coordinates of each actual trajectory point in the actual trajectory information and the second target trajectory, and use the average position error, average speed error and average heading angle error corresponding to the first trajectory point matching pairs as the perception accuracy test result;

[0157] The third perception accuracy test result determination unit is used to determine the second trajectory point matching pairs corresponding to the merged trajectory after the second target trajectories are merged and the coordinates of each actual trajectory point in the actual trajectory information when the number of second target trajectories is greater than 1, and use the average position error, average speed error and average heading angle error corresponding to the second trajectory point matching pairs as the perception accuracy test result.

[0158] The roadside perception accuracy testing device provided in the embodiment of the present invention can execute the roadside perception accuracy testing method provided in any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method.

[0159] Embodiment 4

[0160] Figure 6A schematic diagram of the structure of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0161] like Figure 6 As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0162] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0163] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the roadside perception accuracy test method.

[0164] In some embodiments, the roadside perception accuracy test method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the roadside perception accuracy test method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to perform the roadside perception accuracy test method in any other appropriate manner (e.g., by means of firmware).

[0165] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0166] In some embodiments, the roadside perception accuracy test method may be implemented as a computer program, which is invisibly included in a computer program product. When the computer program is executed by a processor, the roadside perception accuracy test method of the present invention is implemented. The computer program product can be understood as a software product that mainly implements its solution through a computer program. The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0167] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0168] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0169] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0170] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0171] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0172] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A roadside perception accuracy testing method, characterized in that: The method comprises: Obtain the actual trajectory information and the perceived target trajectory information of the test vehicle within the perception area of ​​the roadside perception device; Matching the actual trajectory information and the perceived target trajectory information according to the horizontal and vertical distance errors of the trajectory points to obtain a first target trajectory; When the number of the first target trajectory is 1, determining the perception accuracy test result corresponding to each test item according to the trajectory point matching between the actual trajectory information and the first target trajectory; When the number of the first target trajectories is greater than 1, the second target trajectory is determined based on the trajectory intersection between the first target trajectories, and the perception accuracy test result corresponding to each test item is determined according to the trajectory point matching between the actual trajectory information and the second target trajectory.

2. The method according to claim 1, characterized in that Also includes: Receive and parse map message data sent by the roadside unit; Matching a target area map and upstream and downstream nodes in the map message data according to the actual track point position in the actual track information; By traversing the lane point set between the upstream and downstream nodes in the target area map, a first lane edge, a second lane edge and a stop line are determined; wherein the first lane edge is a right lane edge of the rightmost lane based on the lane direction, and the second lane edge is a left lane edge of the leftmost lane based on the lane direction; The intersection of the first lane edge and the stop line is taken as the origin of the coordinate system, and a point on the first lane edge is selected as a coordinate point in the x-axis direction of the coordinate system, and the intersection of the second lane edge and the stop line is selected as a coordinate point in the y-axis direction of the coordinate system to establish a corresponding target plane coordinate system.

3. The method according to claim 1, characterized in that: The obtaining of the actual trajectory information and the perceived target trajectory information of the test vehicle in the perception area of ​​the roadside perception device includes: When the test vehicle passes through the sensing area of ​​the roadside sensing device, reading the basic safety message data stored in the vehicle-mounted unit, and receiving the roadside safety message data sent by the roadside unit; Parsing the basic safety message data, obtaining and recording the actual trajectory information of each actual trajectory point of the test vehicle; wherein the actual trajectory information includes: the timestamp of the actual trajectory point, the position of the actual trajectory point, the speed of the actual trajectory point and the heading angle of the actual trajectory point; The motor vehicles among the traffic participants are taken as the perception targets, and the perception target trajectory information of each perception target corresponding to each perception target trajectory point is parsed from the roadside safety message data and recorded; wherein the perception target trajectory information includes: perception target identification, perception target trajectory point timestamp, perception target trajectory point position, perception target trajectory point speed and perception target trajectory point heading angle.

4. The method according to claim 2, characterized in that: The matching of the actual trajectory information and the perceived target trajectory information according to the horizontal and vertical distance errors of the trajectory points to obtain a first target trajectory includes: Respectively read the actual trajectory point timestamp, actual trajectory point position, actual trajectory point speed and actual trajectory point heading angle in the actual trajectory information, and read the perceived target identifier, perceived target trajectory point timestamp, perceived target trajectory point position, perceived target trajectory point speed and perceived target trajectory point heading angle corresponding to each perceived target in the perceived target trajectory information; Respectively converting the positions of the actual track points and the positions of the perceived target track points into the target plane coordinate system to obtain the actual track point coordinates corresponding to the test vehicle and the perceived target track point coordinates corresponding to the perceived targets; Determine the average value of the vertical distances of the actual trajectory point coordinates from the x-axis to obtain the actual average horizontal absolute distance, and determine the average value of the vertical distances of the trajectory point coordinates of each perceived target corresponding to each perceived target from the x-axis to obtain the perceived target average horizontal absolute distance corresponding to each perceived target; Respectively determining the difference between the perceived target average horizontal absolute distance and the actual average horizontal absolute distance of each perceived target to obtain an average horizontal absolute distance difference; Traversing the perception targets according to the perception target identifiers, determining the corresponding perception targets whose average horizontal absolute distance difference is less than the first preset distance as the first screening perception targets; According to the actual trajectory point timestamp and the perceived target trajectory point timestamp of each of the first-screened perceived targets, the perceived target trajectory point coordinates of each of the first-screened perceived targets are respectively matched with the actual trajectory point coordinates to obtain first trajectory point matching pairs corresponding to the actual trajectory and each perceived target trajectory; Traverse each of the first-screened perception targets, determine the average longitudinal absolute distance error corresponding to each of the first trajectory point matching pairs, determine the corresponding first-screened perception target whose average longitudinal absolute distance error is less than the second preset distance as the second-screened perception target, and use the coordinates of each perception target trajectory point corresponding to the second-screened perception target as the first target trajectory.

5. The method according to claim 4, characterized in that After determining the primary screening perception target, the method further includes: The timestamps of the perception target trajectory points of each of the once-screened perception targets are compensated according to the preset delay compensation time.

6. The method according to claim 1, characterized in that The determining, according to the matching of the track points between the actual track information and the first target track, the perception accuracy test result corresponding to each test item includes: Extracting first trajectory point matching pairs corresponding to the coordinates of each actual trajectory point of the actual trajectory information and the first target trajectory; Based on the actual trajectory point position, the actual trajectory point speed and the actual trajectory point heading angle in the actual trajectory information, and the perceived target trajectory point position, the perceived target trajectory point speed and the perceived target trajectory point heading angle in the perceived target trajectory information corresponding to the first target trajectory, the average position error, the average speed error and the average heading angle error corresponding to the first trajectory point matching pair are determined, and the average position error, the average speed error and the average heading angle error are used as the perception accuracy test result.

7. The method according to claim 1, characterized in that The determining of the second target trajectory based on the trajectory intersection between the first target trajectories, and determining the perception accuracy test result corresponding to each test item according to the trajectory point matching between the actual trajectory information and the second target trajectory, includes: The first target trajectories are sorted in ascending order according to the corresponding average longitudinal absolute distance errors, and the traversal is started from the corresponding first target trajectory with the smallest average longitudinal absolute distance error, and all other first target trajectories that have an intersection area with the first target trajectory are eliminated. After the traversal is completed, the second target trajectory is obtained; When the number of the second target trajectory is 1, extracting first trajectory point matching pairs corresponding to the coordinates of each actual trajectory point of the actual trajectory information and the second target trajectory, and taking the average position error, average speed error and average heading angle error corresponding to the first trajectory point matching pairs as the perception accuracy test result; When the number of the second target trajectories is greater than 1, determine the second trajectory point matching pairs corresponding to the merged trajectory after the second target trajectories are merged and the coordinates of each actual trajectory point of the actual trajectory information, and use the average position error, average speed error and average heading angle error corresponding to the second trajectory point matching pairs as the perception accuracy test result.

8. A roadside perception accuracy testing device, characterized in that: The device comprises: A trajectory information acquisition module is used to obtain the actual trajectory information and the perception target trajectory information of the test vehicle in the perception area of ​​the roadside perception device; A trajectory matching module, used to match the actual trajectory information and the perceived target trajectory information according to the horizontal and vertical distance errors of the trajectory points to obtain a first target trajectory; A first result determination module, configured to determine a perception accuracy test result corresponding to each test item according to a track point matching condition between the actual track information and the first target track when the number of the first target track is 1; a second result determination module, for determining a second target trajectory based on a trajectory intersection between the first target trajectories when the number of the first target trajectories is greater than 1, and determining a perception accuracy test result corresponding to each test item according to a trajectory point matching situation between the actual trajectory information and the second target trajectory.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the roadside perception accuracy testing method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the roadside perception accuracy testing method according to any one of claims 1 to 7 when executed.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the roadside perception accuracy testing method according to any one of claims 1 to 7 is implemented.

Images