An evaluation method, device and test system for a roadside perception system

Abstract

The present invention provides an evaluation method, device and test system for a roadside perception system. The method includes: obtaining N trajectory segments in the to-be-tested road section according to the perception data in the to-be-tested road section output by the roadside perception system; associating and matching the N trajectory segments with M targets in the to-be-tested road section, where M belongs to positive integers; N≥M; determining an evaluation result corresponding to each target according to at least one of the trajectory segments associated and matched with each target; and determining the evaluation result of the roadside perception system according to the evaluation results corresponding to the M targets. The solution of the present invention can automatically complete the perception ability evaluation of the roadside perception system by obtaining real-time perception data, saving labor costs.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to an evaluation method, device and test system for a roadside perception system. Background Art

[0002] Vehicle-road collaboration is a technical solution that realizes vehicle-to-vehicle and vehicle-to-road collaborative applications by providing low-latency, highly reliable communication connections based on full perception and calculation of roads and vehicles. In the vehicle-road collaboration solution, the perception and computing capability of the roadside perception system is one of the key technologies. Its perception capability needs to be tested before it is put into use to ensure the accuracy and reliability of the data output. At present, the main existing testing method is to manually drive the vehicle, collect true values ​​based on driving routes in different test scenarios in the test field, and then manually determine the data indicators by analyzing the logs output by each sensor algorithm. This test method of manually outputting test reports consumes a lot of manpower and time costs, and seriously affects the overall test cycle. Summary of the invention

[0003] The present invention provides a method, device and test system for evaluating a roadside perception system, which solves the problem of high labor cost in the existing evaluation method of the roadside perception system.

[0004] In a first aspect, an embodiment of the present invention provides a method for evaluating a roadside perception system, comprising:

[0005] According to the perception data in the road section to be tested output by the roadside perception system, N trajectory segments in the road section to be tested are obtained, where N is a positive integer;

[0006] Associating and matching the N trajectory segments with the M targets in the road section to be tested, where M is a positive integer; N≥M;

[0007] Determine an evaluation result corresponding to each target according to at least one trajectory segment associated with each target;

[0008] The evaluation result of the roadside perception system is determined according to the evaluation results corresponding to the M targets.

[0009] Optionally, associating and matching the N trajectory segments with the M targets in the road section to be tested includes:

[0010] Determine P trajectory segments that meet a preset screening condition from the N trajectory segments; wherein each of the P trajectory segments is associated and matched with a target in a one-to-one correspondence, and the preset screening condition is related to the starting position and the ending position of the road section to be tested;

[0011] Regarding N - P of the N trajectory segments that do not meet the preset screening criteria as a second trajectory set; and,

[0012] Based on the timestamps and position information of the start and end frames of each of the trajectory segments in the second trajectory set, associatively matching the N - P trajectory segments with M - P targets; N≥M≥P, and P is a positive integer; where each target is associatively matched with at least one of the trajectory segments in the second trajectory set.

[0013] Optionally, the preset screening criteria include:

[0014] The first distance is less than or equal to the first threshold;

[0015] The second distance is less than or equal to the second threshold;

[0016] Wherein, the first distance is the distance between the starting point of the trajectory segment and the starting position of the section to be measured, and the second distance is the distance between the ending point of the trajectory segment and the ending position of the section to be measured.

[0017] Optionally, the associatively matching the N - P trajectory segments with M - P targets based on the timestamps and position information of the start and end frames of each of the trajectory segments in the second trajectory set includes:

[0018] Sorting each of the trajectory segments in the second trajectory set in chronological order according to the timestamps of the start and end frames of each of the trajectory segments;

[0019] Regarding the target trajectory segment that is after the i - th trajectory segment of the first target and meets the preset matching conditions in the second trajectory set as the (i + 1)-th trajectory segment associatively matched with the first target; where the first target is any target within the section to be measured; i≥1 and i belongs to integers;

[0020] Wherein, the preset matching conditions include at least one of the following:

[0021] The lateral position deviation between the end frame of the i - th trajectory segment and the start frame of the target trajectory segment is less than the lateral deviation threshold;

[0022] The longitudinal position deviation between the end frame of the i - th trajectory segment and the start frame of the target trajectory segment is less than the longitudinal deviation threshold;

[0023] The distance between the end frame of the i - th trajectory segment and the start frame of the target trajectory segment is less than the distance threshold;

[0024] The heading deviation between the end frame of the i - th trajectory segment and the start frame of the target trajectory segment is less than the heading deviation threshold;

[0025] Optionally, the road type of the section to be measured includes one of the following: curved road section, ramp section, straight road section;

[0026] Among them, the matching condition thresholds corresponding to different road types are different, and the matching condition thresholds include at least one of the following: the lateral deviation threshold, the longitudinal deviation threshold, the distance threshold, and the heading deviation threshold.

[0027] Optionally, calculating the evaluation result corresponding to each target according to at least one of the trajectory segments associated with and matched to each target includes:

[0028] Determine a sub-trajectory of the first target within the area to be measured according to at least one of the trajectory segments associated with and matched to the first target; wherein, the first target is any target within the section to be measured;

[0029] Determine the evaluation result corresponding to the first target according to the sub-trajectory.

[0030] Optionally, determining the evaluation result corresponding to the first target according to the sub-trajectory includes:

[0031] Determine the number of trajectory points of the sub-trajectory;

[0032] Determine the expected number of trajectory points of the first target within the section to be measured;

[0033] Determine the quotient of the number of trajectory points of the sub-trajectory and the expected number of trajectory points as the evaluation result of the trajectory recall rate corresponding to the first target.

[0034] Optionally, determining the evaluation result corresponding to the first target according to the sub-trajectory includes:

[0035] Determine the position deviation of the j-th trajectory point in the sub-trajectory, where the position deviation is the position deviation between the j-th trajectory point and the (j - 1)-th trajectory point; j ≥ 1 and j is an integer;

[0036] Determine a first value, where the first value is the number of trajectory points with a position deviation greater than 0;

[0037] Determine the quotient of the first value and the total number of trajectory points of the sub-trajectory as the evaluation result of the positioning accuracy deviation corresponding to the first target.

[0038] Optionally, determining the evaluation result corresponding to the first target according to the sub-trajectory includes:

[0039] Determine a heading deviation of a k-th track point in the sub-track, where the heading deviation is a heading deviation between the k-th track point and a k-1 track point; k≥1 and k is an integer;

[0040] determining a second value, wherein the second value is the number of trajectory points for which the heading deviation is less than a third threshold;

[0041] The quotient of the second value and the total number of track points of the sub-track is determined as the evaluation result of the heading deviation corresponding to the first target.

[0042] Optionally, determining, according to the sub-trackline, an evaluation result corresponding to the first target includes:

[0043] Determine a speed deviation of an r-th trajectory point in the sub-trajectory, where the speed deviation is a speed deviation between the r-th trajectory point and an r-1 trajectory point; r≥1 and r is an integer;

[0044] determining a third value, the third value being the number of trajectory points at which the speed deviation is less than a fourth threshold;

[0045] The quotient of the third value and the total number of track points of the sub-track is determined as the evaluation result of the speed deviation corresponding to the first target.

[0046] Optionally, determining, according to the sub-trackline, an evaluation result corresponding to the first target includes:

[0047] Determine a first trajectory point number of a target trajectory segment; wherein the target trajectory segment is the trajectory segment with the largest number of trajectory points among at least one trajectory segment associated and matched with a first target; wherein the first target is any target within the road section to be tested;

[0048] The quotient of the first trajectory points and the total trajectory points of the sub-trajectory is determined as the evaluation result of the tracking success rate of the first target.

[0049] In a second aspect, an embodiment of the present invention provides a test system, comprising: a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for evaluating the roadside perception system as described in the first aspect are implemented.

[0050] In a third aspect, an embodiment of the present invention provides an evaluation device for a roadside perception system, comprising:

[0051] A first acquisition module is used to acquire N trajectory segments in the road section to be tested according to the perception data in the road section to be tested output by the roadside perception system; N is a positive integer;

[0052] An association matching module, configured to perform association matching between the N trajectory segments and M targets in the to-be-tested road section, where M belongs to positive integers;

[0053] A first determination module, configured to determine an evaluation result corresponding to each target according to at least one of the trajectory segments associated and matched with each target;

[0054] A second determination module, configured to determine an evaluation result of the roadside perception system according to the evaluation results corresponding to the M targets.

[0055] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the evaluation method of the roadside perception system as described in the first aspect are implemented.

[0056] The beneficial effects of the above technical solutions of the present invention are:

[0057] In the above solution, according to the perception data in the to-be-tested road section output by the roadside perception system, N trajectory segments in the to-be-tested road section are obtained; the N trajectory segments are subjected to association matching with M targets in the to-be-tested road section, where M belongs to positive integers; an evaluation result corresponding to each target is determined according to at least one of the trajectory segments associated and matched with each target; an evaluation result of the roadside perception system is determined according to the evaluation results corresponding to the M targets. In this way, the perception ability evaluation of the roadside perception system can be automatically completed by obtaining real-time perception data, saving labor costs. Description of the Drawings

[0058] Figure 1 A flowchart showing the evaluation method of the roadside perception system according to an embodiment of the present invention;

[0059] Figure 2 A structural block diagram showing the evaluation device of the roadside perception system according to an embodiment of the present invention;

[0060] Figure 3 A hardware structural block diagram showing the evaluation system of the present invention. Detailed Embodiments

[0061] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help a comprehensive understanding of the embodiments of the present invention. Therefore, those skilled in the art should clearly understand that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. In addition, descriptions of known functions and structures are omitted for clarity and conciseness.

[0062] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures, or characteristics related to the embodiment are included in at least one embodiment of the present invention. Therefore, the "in one embodiment" or "in an embodiment" that appears throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics can be combined in one or more embodiments in any suitable manner.

[0063] In various embodiments of the present invention, it should be understood that the magnitude of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0064] In addition, the terms "system" and "network" are often used interchangeably in this article.

[0065] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0066] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application.

[0067] Specifically, the embodiments of the present invention provide a method, device, and test system for evaluating a roadside perception system, which solves the problem of high labor cost in the evaluation method of the roadside perception system in the prior art.

[0068] First Embodiment

[0069] As Figure 1 shown, the embodiments of the present invention provide a method for evaluating a roadside perception system, which specifically includes the following steps:

[0070] Step 101: Obtain N trajectory segments in the to-be-tested road section according to the perception data in the to-be-tested road section output by the roadside perception system; N belongs to a positive integer.

[0071] In specific implementation, the position information of the section to be measured and the real-time perception data output by the roadside perception system can be obtained; among them, the perception data includes but is not limited to: the position coordinates of the target, the moving speed of the target, the heading of the target, the timestamp, the target ID, and the target type; based on the position coordinates of the target, it can be determined whether the target is located within the section to be measured, so as to obtain the perception data within the section to be measured; further, based on the perception data, N trajectory segments within the section to be measured are obtained.

[0072] Among them, the position information of the section to be measured includes the starting position coordinates and the ending position coordinates.

[0073] Optionally, to improve the matching accuracy, the section to be measured can be divided into intervals according to the driving direction. For example, the oncoming direction corresponds to one interval of the section to be measured, and the going direction corresponds to one interval of the section to be measured.

[0074] Step 102: Associate and match the N trajectory segments with M targets within the section to be measured, where M is a positive integer; N≥M.

[0075] It should be noted that normally, within the section to be measured, one target corresponds to one complete trajectory segment. However, when blocked by obstacles or missed detection occurs, the roadside perception system may not collect the perception data of the target in a certain area, resulting in the missing of the target's trajectory in this area. In this way, the same target will correspond to multiple trajectory segments, and the target IDs corresponding to each trajectory segment are different.

[0076] This step associates and matches at least one trajectory segment belonging to the same target, so as to obtain a complete sub-trajectory of each target within the section to be measured interval based on at least one trajectory segment associated with each target.

[0077] Step 103: Determine the evaluation result corresponding to each target according to at least one of the trajectory segments associated and matched with each target.

[0078] In this step, a complete sub-trajectory of each target is obtained according to at least one trajectory segment associated with each target; based on the complete sub-trajectory of the target, the evaluation result corresponding to the target is obtained.

[0079] Optionally, the types of evaluation results include but are not limited to: trajectory recall rate, heading deviation, positioning accuracy deviation, speed deviation, tracking success rate, number of target type changes, and perception frequency.

[0080] Step 104: Determine the evaluation result of the roadside perception system according to the evaluation results corresponding to the M targets.

[0081] In specific implementation, the evaluation result of the roadside perception system can be obtained by calculating the average value of the M target evaluation results within the road section to be measured; alternatively, the evaluation result of the roadside perception system can be obtained by performing weighted summation on the M target evaluation results.

[0082] In the above embodiments, it is possible to obtain N trajectory segments within the road section to be measured by acquiring real-time perception data, and further, through the target matching process, associate and match the N trajectory segments with M targets within the road section to be measured, so that each target is associated and matched with at least one trajectory segment; based on at least one of the trajectory segments associated and matched with each target, determine the evaluation result corresponding to each target, and finally, according to the statistical value of the M evaluation results within the road section to be measured, obtain the evaluation result of the roadside perception system, thereby automatically completing the perception ability evaluation of the roadside perception system and achieving the effect of saving labor costs. Moreover, this embodiment can be implemented without ground truth and can run in real time together with the algorithm, which is simple and efficient.

[0083] It should be noted that the embodiments of the present application can evaluate the perception abilities of various roadside perception systems, including lidar, millimeter-wave radar, pure vision algorithms, etc.

[0084] In one embodiment, in the above step 102, associating and matching the N trajectory segments with M targets within the road section to be measured includes:

[0085] Determine P trajectory segments that meet the preset screening conditions from the N trajectory segments; where each of the P trajectory segments is associated and matched with one target in a one-to-one correspondence, and the preset screening conditions are related to the start position and end position of the road section to be measured;

[0086] Regard the N - P trajectory segments that do not meet the preset screening conditions among the N trajectory segments as a second trajectory set; and,

[0087] According to the timestamps and position information of the start and end frames of each of the trajectory segments in the second trajectory set, associate and match the N - P trajectory segments with M - P targets; N ≥ M ≥ P, and P is a positive integer; where each target is associated and matched with at least one of the trajectory segments in the second trajectory set.

[0088] It should be noted that the P trajectory segments that meet the preset screening conditions are associated and matched with one target in a one-to-one correspondence, that is, the P trajectory segments are complete sub-trajectories of the P targets within the road section to be measured and are non-interrupted trajectory segments; while the N - P trajectory segments that do not meet the preset screening conditions are interrupted trajectory segments, and it is necessary to associate and match the N - P trajectory segments with M - P targets according to the timestamps and position information of the start and end frames of each trajectory segment, so that one target matches at least one trajectory segment.

[0089] Optionally, the preset screening conditions include:

[0090] The first distance is less than or equal to the first threshold;

[0091] The second distance is less than or equal to the second threshold;

[0092] Wherein, the first distance is the distance between the starting point of the trajectory segment and the starting position of the section to be measured, and the second distance is the distance between the ending point of the trajectory segment and the ending position of the section to be measured.

[0093] Exemplarily, screen for targets within the area of the section to be measured, obtain the trajectory segments of the targets within the area to be measured, and store them in the sequence {D1, D2, D3…, D n}; According to the positions of the trajectory segment D n relative to the starting position P0 and the ending position P1 of the area of the section to be measured, obtain the complete trajectory sequence O, and the M targets in each frame of data can be represented as The position of the i-th target at the t-th moment corresponding to each frame of data can be represented as The following conditions should be satisfied:

[0094]

[0095] Wherein, n1 is the first threshold; n2 is the second threshold; is the abscissa of the starting position of the trajectory segment of the i-th target, is the ordinate of the starting position of the trajectory segment of the i-th target, is the abscissa of the ending position of the trajectory segment of the i-th target, is the ordinate of the ending position of the trajectory segment of the i-th target, P0(x) is the abscissa of the starting position of the area of the section to be measured, P0(y) is the ordinate of the starting position of the area of the section to be measured, P1(x) is the abscissa of the ending position of the area of the section to be measured, and P1(y) is the ordinate of the ending position of the area of the section to be measured.

[0096] In a specific embodiment, the associating and matching of the N - P trajectory segments with the M - P targets according to the timestamps and position information of the start and end frames of each of the trajectory segments in the second trajectory set includes:

[0097] Sort the trajectory segments in the second trajectory set in chronological order according to the timestamps of the start and end frames of each of the trajectory segments in the second trajectory set;

[0098] Take the target trajectory segment that is after the $i$-th trajectory segment of the first target in the second trajectory set and meets the preset matching condition as the $(i + 1)$-th trajectory segment associated and matched with the first target; where the first target is any target within the to-be-measured road section; $i\geq1$ and $i$ is an integer.

[0099] Among them, the preset matching condition includes at least one of the following:

[0100] The lateral position deviation between the tail frame of the $i$-th trajectory segment and the head frame of the target trajectory segment is less than the lateral deviation threshold.

[0101] The longitudinal position deviation between the tail frame of the $i$-th trajectory segment and the head frame of the target trajectory segment is less than the longitudinal deviation threshold.

[0102] The distance between the tail frame of the $i$-th trajectory segment and the head frame of the target trajectory segment is less than the distance threshold.

[0103] The heading deviation between the tail frame of the $i$-th trajectory segment and the head frame of the target trajectory segment is less than the heading deviation threshold.

[0104] In specific implementation, first obtain the ID fields in the trajectory segment to be matched and the target, read the timestamps in the ID, and then match the targets in the order of the appearance and end of the targets, that is, sort the $N - P$ trajectory segments according to the timestamps of the head and tail frames of the trajectory segments in the order of time. Further, take out the $i$-th trajectory segment of the first target, obtain the set of trajectory segments after the timestamp of the tail frame (end position) of the $i$-th trajectory segment, and take the target trajectory segments in the set of trajectory segments that meet the preset matching condition as the $(i + 1)$-th trajectory segment associated and matched with the first target; add the $(i + 1)$-th trajectory segment to the trajectory sequence of the $i$-th trajectory segment, update the $i$-th trajectory segment, and finally obtain a complete sub-trajectory of the first target.

[0105] Optionally, when there are multiple target trajectory segments that meet the preset matching condition, take the trajectory segment closest to the $i$-th trajectory segment as the $(i + 1)$-th trajectory segment.

[0106] For example, the start and end frame timestamps of the first trajectory segment of target A (the trajectory segment closest to the starting position of the road section to be measured is taken as the first trajectory segment of target A) are from 10 seconds to 20 seconds. The trajectory segments after the end frame at 20 seconds include: trajectory segment a from 24 seconds to 30 seconds, trajectory segment b from 24 seconds to 35 seconds, and trajectory segment c from 23 seconds to 40 seconds. Based on a preset matching condition, a target trajectory segment can be screened out from trajectory segments a, b, and c. Specifically, the trajectory segment that meets the following preset matching condition and is the closest to the first trajectory segment is determined to be the second trajectory segment belonging to target A, and so on until all the trajectory segments of target A are found:

[0107] K(n,x)<dx; where K(n,x) is the lateral position deviation between the end position of the i-th trajectory segment and the start position of the target trajectory segment, and dx is the lateral deviation threshold;

[0108] K(n,y)<dy; where K(n,y) is the longitudinal position deviation between the end position of the i-th trajectory segment and the start position of the target trajectory segment, and dy is the longitudinal deviation threshold

[0109] D(n,dis) / △t<ds; where D(n,dis) is the distance between the end position of the i-th trajectory segment and the start position of the target trajectory segment, ds is the distance threshold, and △t represents the time difference between the end position point of the i-th trajectory segment and the start position point of the target trajectory segment;

[0110] heading<hs; where heading refers to the course deviation between the end position of the i-th trajectory segment and the start position of the target trajectory segment, and hs is the course deviation threshold.

[0111] In the above embodiments, during target matching, the start and end frame timestamps and position information of the trajectory segments are used to remove interference points, reducing the occurrence of target mis-matching problems and improving the matching accuracy.

[0112] In a specific embodiment, the road type of the road section to be measured includes one of the following: curved road section, ramp road section, straight road section;

[0113] Among them, the matching condition thresholds corresponding to different road types are different, and the matching condition thresholds include at least one of the following: the lateral deviation threshold, the longitudinal deviation threshold, the distance threshold, and the course deviation threshold.

[0114] In the above embodiments, since the target is in different road types, the corresponding lateral position change, longitudinal position change, and lateral change will be different at the same time. Therefore, different matching condition thresholds can be obtained based on the road type of the section where the target is located, which can improve the accuracy of matching. For example, the lateral deviation threshold and the heading deviation threshold in a curved road section are larger than those in a straight road section; the distance deviation in a straight road section is smaller than that in a curved road section; the longitudinal deviation of a special road (such as a ramp or a ramp) is different from that of a flat road.

[0115] In one embodiment, in the above step 103, calculating the evaluation result corresponding to each target according to at least one of the trajectory segments associated with and matched with each target includes:

[0116] Determine a sub-trajectory of the first target within the area to be measured according to at least one of the trajectory segments associated with and matched with the first target; wherein, the first target is any target within the section to be measured;

[0117] Determine the evaluation result corresponding to the first target according to the sub-trajectory.

[0118] It can be understood that the sub-trajectory may be a complete trajectory (from near the starting point to near the ending point of the section to be measured) that matches the first target within the area of the section to be measured, or it may be only a partial trajectory. For example, after the vehicle enters the area of the section to be measured, only the first half of the trajectory, or the second half of the trajectory, or a certain middle section of the trajectory is obtained until the target exits the area of the section to be measured.

[0119] This embodiment determines the evaluation result of the roadside perception system for each target based on the sub-trajectory of the target within the section to be measured.

[0120] In a specific embodiment, determining the evaluation result corresponding to the first target according to the sub-trajectory includes:

[0121] Determine the number of trajectory points of the sub-trajectory;

[0122] Determine the expected number of trajectory points of the first target within the section to be measured;

[0123] Determine the quotient of the number of trajectory points of the sub-trajectory and the expected number of trajectory points as the evaluation result of the trajectory recall rate corresponding to the first target.

[0124] When specifically implemented, the time stamp t of the first target passing through the starting position point of the area of the section to be measured can be calculated respectively according to the moving speed of the first target and the distances between the sub-trajectory and the starting position point and the ending position point of the area of the section to be measured (min) and the time stamp t of the ending position point (max) ; according to t (min) 、t (max)and the perceived frequency, determine the expected number of trajectory points of the first target within the section to be measured; expected number of trajectory points = (t (max) - t (min) ) × perceived frequency.

[0125] In a specific embodiment, the determining the evaluation result corresponding to the first target according to the sub-trajectory includes:

[0126] Determine the position deviation of the j-th trajectory point in the sub-trajectory, where the position deviation is the position deviation between the j-th trajectory point and the (j - 1)-th trajectory point; j ≥ 1 and j is an integer;

[0127] Determine the first value, where the first value is the number of trajectory points with a position deviation greater than 0;

[0128] Determine the quotient of the first value and the total number of trajectory points of the sub-trajectory as the evaluation result of the positioning accuracy deviation corresponding to the first target.

[0129] Exemplarily, the positioning accuracy deviation

[0130] where refers to the trajectory point with a position deviation greater than 0; S is the total number of trajectory points of the sub-trajectory of target n; station_error refers to the position deviation, refers to the j-th trajectory point of target n.

[0131] In specific implementation, the position deviation can be made where θ refers to the heading of the first target, which can be obtained according to the characteristics of the section to be measured where the first target is located; t + △t is the timestamp of the j-th trajectory point, and t is the timestamp of the (j - 1)-th trajectory point, refers to the lateral position deviation between the j-th trajectory point and the (j - 1)-th trajectory point, refers to the longitudinal position deviation between the j-th trajectory point and the (j - 1)-th trajectory point; is the abscissa of the j-th trajectory point of target n, is the ordinate of the j-th trajectory point of target n, is the abscissa of the (j - 1)-th trajectory point of target n, is the ordinate of the (j - 1)-th trajectory point of target n.

[0132] In a specific embodiment, the determining the evaluation result corresponding to the first target according to the sub-trajectory includes:

[0133] Determine the heading deviation of the k-th trajectory point in the sub-trajectory, where the heading deviation is the heading deviation between the k-th trajectory point and the (k - 1)-th trajectory point; k ≥ 1 and k is an integer;

[0134] Determine a second value, where the second value is the number of trajectory points with a course deviation less than a third threshold;

[0135] Determine the quotient of the second value and the total number of trajectory points of the sub-trajectory as the evaluation result of the course deviation corresponding to the first target.

[0136] Exemplarily, the course deviation where u is the third threshold, t + Δt is the timestamp of the kth trajectory point, t is the timestamp of the (k - 1)th trajectory point, and Δh refers to the course deviation between the kth trajectory point and the (k - 1)th trajectory point, refers to the course of the (k - 1)th trajectory point of target n, refers to the course of the kth trajectory point of target n, T refers to the travel time of target n, S refers to the total number of trajectory points of the sub-trajectory, refers to the second value.

[0137] In a specific embodiment, the determining the evaluation result corresponding to the first target according to the sub-trajectory includes:

[0138] Determine the speed deviation of the rth trajectory point in the sub-trajectory, where the speed deviation is the speed deviation between the rth trajectory point and the (r - 1)th trajectory point; j ≥ 1 and j is an integer;

[0139] Determine a third value, where the third value is the number of trajectory points with a speed deviation less than a fourth threshold;

[0140] Determine the quotient of the third value and the total number of trajectory points of the sub-trajectory as the evaluation result of the speed deviation corresponding to the first target.

[0141] Exemplarily, the speed deviation where s is the fourth threshold, t + Δt is the timestamp of the rth trajectory point, t is the timestamp of the (r - 1)th trajectory point, and Δz refers to the speed between the rth trajectory point and the (r - 1)th trajectory point, refers to the speed of the (r - 1)th trajectory point of target n, refers to the speed of the rth trajectory point of target n, T refers to the travel time of target n, S refers to the total number of trajectory points of the sub-trajectory, refers to the third value.

[0142] In a specific embodiment, the determining the evaluation result corresponding to the first target according to the sub-trajectory includes:

[0143] Determine the number of the first trajectory points of the target trajectory segment; wherein, the target trajectory segment is the trajectory segment with the most trajectory points among at least one of the trajectory segments associated and matched with the first target; wherein, the first target is any target within the to-be-tested road section;

[0144] Determine the quotient of the number of the first trajectory points and the total number of trajectory points of the sub-trajectory as the evaluation result of the tracking success rate of the first target.

[0145] In this embodiment, among at least one trajectory segment associated with the target, the trajectory segment with the most trajectory points is used to calculate the tracking success rate of the target.

[0146] Optionally, the method may further include: counting the number of output trajectory points of the target per second to obtain the perception frequency.

[0147] The second embodiment

[0148] As shown in FIG. 2, the second embodiment of the present invention provides an evaluation device for a roadside perception system, including:

[0149] The first acquisition module 201 is configured to acquire N trajectory segments within the to-be-tested road section according to the perception data within the to-be-tested road section output by the roadside perception system; N belongs to a positive integer;

[0150] The association and matching module 202 is configured to associate and match the N trajectory segments with M targets within the to-be-tested road section, M belongs to a positive integer;

[0151] The first determination module 203 is configured to determine the evaluation result corresponding to each target according to at least one of the trajectory segments associated and matched with each target;

[0152] The second determination module 204 is configured to determine the evaluation result of the roadside perception system according to the evaluation results corresponding to the M targets.

[0153] Optionally, the association and matching module 202 includes:

[0154] The first matching sub-module is configured to determine P trajectory segments that meet the preset screening conditions from the N trajectory segments; wherein, each of the P trajectory segments is associated and matched with a target one by one, and the preset screening conditions are related to the start position and the end position of the to-be-tested road section;

[0155] The second matching sub-module is configured to use the N-P trajectory segments that do not meet the preset screening conditions among the N trajectory segments as the second trajectory set; and,

[0156] A third matching sub-module, configured to associate and match N - P of the trajectory segments with M - P targets according to the timestamps and position information of the start and end frames of each of the trajectory segments in the second trajectory set; N≥M≥P, and P is a positive integer; wherein, each target is associated with and matches at least one of the trajectory segments in the second trajectory set.

[0157] Optionally, the preset screening conditions include:

[0158] The first distance is less than or equal to the first threshold;

[0159] The second distance is less than or equal to the second threshold;

[0160] Wherein, the first distance is the distance between the starting point of the trajectory segment and the starting position of the road section to be measured, and the second distance is the distance between the ending point of the trajectory segment and the ending position of the road section to be measured.

[0161] Optionally, the third matching sub-module includes:

[0162] A first matching unit, configured to sort each of the trajectory segments in the second trajectory set in chronological order according to the timestamps of the start and end frames of each of the trajectory segments in the second trajectory set;

[0163] A second matching unit, configured to use a target trajectory segment that is after the i-th trajectory segment of the first target in the second trajectory set and meets the preset matching conditions as the (i + 1)-th trajectory segment associated with and matched with the first target; wherein, the first target is any target within the road section to be measured; i≥1 and i belongs to integers;

[0164] Wherein, the preset matching conditions include at least one of the following:

[0165] The lateral position deviation between the end frame of the i-th trajectory segment and the start frame of the target trajectory segment is less than the lateral deviation threshold;

[0166] The longitudinal position deviation between the end frame of the i-th trajectory segment and the start frame of the target trajectory segment is less than the longitudinal deviation threshold;

[0167] The distance between the end frame of the i-th trajectory segment and the start frame of the target trajectory segment is less than the distance threshold;

[0168] The heading deviation between the end frame of the i-th trajectory segment and the start frame of the target trajectory segment is less than the heading deviation threshold;

[0169] Optionally, the road type of the road section to be measured includes one of the following: curved road section, ramp road section, straight road section;

[0170] Among them, different road types correspond to different matching condition thresholds, and the matching condition thresholds include at least one of the following: the lateral deviation threshold, the longitudinal deviation threshold, the distance threshold, and the heading deviation threshold.

[0171] Optionally, the first determining module 203 includes:

[0172] A first determination submodule is configured to determine a sub-trajectory of the first target located in the area to be tested according to at least one trajectory segment associated and matched with the first target; wherein the first target is any target in the road section to be tested;

[0173] The second determination submodule is used to determine the evaluation result corresponding to the first target according to the sub-trackline.

[0174] Optionally, the second determining submodule is specifically configured to:

[0175] Determining the number of trajectory points of the sub-trajectory;

[0176] Determining the expected number of trajectory points of the first target within the road section to be tested;

[0177] The quotient of the number of trajectory points of the sub-trajectory and the expected number of trajectory points is determined as an evaluation result of the trajectory recall rate corresponding to the first target.

[0178] Optionally, the second determining submodule is specifically configured to:

[0179] Determine a position deviation of a j-th track point in the sub-track, where the position deviation is a position deviation between the j-th track point and the j-1-th track point; j≥1 and j is an integer;

[0180] Determine a first value, the first value being the number of trajectory points having a position deviation greater than 0;

[0181] The quotient of the first value and the total number of track points of the sub-track is determined as the evaluation result of the positioning accuracy deviation corresponding to the first target.

[0182] Optionally, the second determining submodule is specifically configured to:

[0183] Determine a heading deviation of a k-th track point in the sub-track, where the heading deviation is a heading deviation between the k-th track point and a k-1 track point; k≥1 and k is an integer;

[0184] determining a second value, wherein the second value is the number of trajectory points for which the heading deviation is less than a third threshold;

[0185] The quotient of the second value and the total number of track points of the sub-track is determined as the evaluation result of the heading deviation corresponding to the first target.

[0186] Optionally, the second determination sub-module is specifically configured to:

[0187] Determine the velocity deviation of the r-th trajectory point in the sub-trajectory, where the velocity deviation is the velocity deviation between the r-th trajectory point and the r - 1 trajectory points; r ≥ 1 and r is an integer;

[0188] Determine a third value, where the third value is the number of trajectory points whose velocity deviation is less than a fourth threshold;

[0189] Determine the quotient of the third value and the total number of trajectory points of the sub-trajectory as the evaluation result of the velocity deviation corresponding to the first target.

[0190] Optionally, the second determination sub-module is specifically configured to:

[0191] Determine the number of the first trajectory points of the target trajectory segment; wherein, the target trajectory segment is the trajectory segment with the largest number of trajectory points among at least one of the trajectory segments associated and matched with the first target; wherein, the first target is any target within the to-be-tested road section;

[0192] Determine the quotient of the number of the first trajectory points and the total number of trajectory points of the sub-trajectory as the evaluation result of the tracking success rate of the first target.

[0193] The second embodiment of the present invention corresponds to the method of the above first embodiment. All the implementation means in the above first embodiment are applicable to the embodiment of the evaluation device of the roadside perception system and can achieve the same technical effects.

[0194] Third Embodiment

[0195] To better achieve the above object, as Figure 3 shown, the third embodiment of the present invention further provides a test system, including:

[0196] A processor 300; and a memory 320 connected to the processor 300 through a bus interface, where the memory 320 is used to store the programs and data used by the processor 300 when performing operations, and the processor 300 calls and executes the programs and data stored in the memory 320.

[0197] Wherein, a transceiver 310 is connected to the bus interface and is used to receive and send data under the control of the processor 300; the processor 300 is used to read the programs in the memory 320 to implement the following steps:

[0198] According to the perception data within the to-be-tested road section output by the roadside perception system, obtain N trajectory segments within the to-be-tested road section; N belongs to positive integers;

[0199] Associate the N trajectory segments with M targets within the section to be measured, where M belongs to positive integers; N ≥ M;

[0200] Determine the evaluation result corresponding to each target according to at least one of the trajectory segments associated and matched with each target;

[0201] Determine the evaluation result of the roadside perception system according to the evaluation results corresponding to the M targets.

[0202] Among them, in Figure 3 The bus architecture can include any number of interconnected buses and bridges, specifically, various circuits represented by one or more processors represented by the processor 300 and a memory represented by the memory 320 are linked together. The bus architecture can also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, so they will not be further described herein. The bus interface provides an interface. The transceiver 310 can be multiple components, that is, including a transmitter and a transceiver, and provides a unit for communicating with various other devices on the transmission medium. For different terminals, the user interface 330 can also be an interface capable of externally connecting and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, etc. The processor 300 is responsible for managing the bus architecture and general processing, and the memory 320 can store data used by the processor 300 when performing operations.

[0203] Optionally, the processor 300 is specifically configured to read a program in the memory 320 to implement the following steps:

[0204] Determine P trajectory segments that meet the preset screening conditions from the N trajectory segments; among them, each of the P trajectory segments is associated and matched with a target one by one, and the preset screening conditions are related to the starting position and the ending position of the section to be measured;

[0205] Regard the N - P trajectory segments that do not meet the preset screening conditions among the N trajectory segments as a second trajectory set; and,

[0206] According to the timestamps and position information of the start and end frames of each of the trajectory segments in the second trajectory set, associate and match the N - P trajectory segments with M - P targets; N ≥ M ≥ P, and P is a positive integer; where each target is associated and matched with at least one of the trajectory segments in the second trajectory set.

[0207] Optionally, the preset screening conditions include:

[0208] The first distance is less than or equal to the first threshold;

[0209] The second distance is less than or equal to a second threshold value;

[0210] Wherein, the first distance is the distance between the starting point of the trajectory segment and the starting position of the road section to be measured, and the second distance is the distance between the ending point of the trajectory segment and the ending position of the road section to be measured.

[0211] Optionally, the processor 300 is specifically configured to read a program in the memory 320 to implement the following steps:

[0212] Sort the trajectory segments in the second trajectory set in chronological order according to the timestamps of the first and last frames of each trajectory segment in the second trajectory set;

[0213] Use the target trajectory segment that is located after the i-th trajectory segment of the first target in the second trajectory set and meets the preset matching conditions as the (i + 1)-th trajectory segment associated and matched with the first target; wherein, the first target is any target within the road section to be measured; i ≥ 1 and i is an integer;

[0214] Wherein, the preset matching conditions include at least one of the following:

[0215] The lateral position deviation between the last frame of the i-th trajectory segment and the first frame of the target trajectory segment is less than a lateral deviation threshold;

[0216] The longitudinal position deviation between the last frame of the i-th trajectory segment and the first frame of the target trajectory segment is less than a longitudinal deviation threshold;

[0217] The distance between the last frame of the i-th trajectory segment and the first frame of the target trajectory segment is less than a distance threshold;

[0218] The heading deviation between the last frame of the i-th trajectory segment and the first frame of the target trajectory segment is less than a heading deviation threshold;

[0219] Optionally, the road type of the road section to be measured includes one of the following: a curved road section, a ramp road section, and a straight road section;

[0220] Wherein, the matching condition thresholds corresponding to different road types are different, and the matching condition thresholds include at least one of the following: the lateral deviation threshold, the longitudinal deviation threshold, the distance threshold, and the heading deviation threshold.

[0221] Optionally, the processor 300 is specifically configured to read a program in the memory 320 to implement the following steps:

[0222] Determine a sub-trajectory of the first target within the area to be measured according to at least one of the trajectory segments associated and matched with the first target; wherein, the first target is any target within the section to be measured.

[0223] Determine an evaluation result corresponding to the first target according to the sub-trajectory.

[0224] Optionally, the determining an evaluation result corresponding to the first target according to the sub-trajectory includes:

[0225] Determine the number of trajectory points of the sub-trajectory.

[0226] Determine the expected number of trajectory points of the first target within the section to be measured.

[0227] Determine the quotient of the number of trajectory points of the sub-trajectory and the expected number of trajectory points as the evaluation result of the trajectory recall rate corresponding to the first target.

[0228] Optionally, the processor 300 is specifically configured to read a program in the memory 320 to implement the following steps:

[0229] Determine the position deviation of the j-th trajectory point in the sub-trajectory, where the position deviation is the position deviation between the j-th trajectory point and the (j - 1)-th trajectory point; j ≥ 1 and j is an integer.

[0230] Determine a first value, where the first value is the number of trajectory points with a position deviation greater than 0.

[0231] Determine the quotient of the first value and the total number of trajectory points of the sub-trajectory as the evaluation result of the positioning accuracy deviation corresponding to the first target.

[0232] Optionally, the processor 300 is specifically configured to read a program in the memory 320 to implement the following steps:

[0233] Determine the heading deviation of the k-th trajectory point in the sub-trajectory, where the heading deviation is the heading deviation between the k-th trajectory point and the (k - 1)-th trajectory point; k ≥ 1 and k is an integer.

[0234] Determine a second value, where the second value is the number of trajectory points with a heading deviation less than a third threshold.

[0235] Determine the quotient of the second value and the total number of trajectory points of the sub-trajectory as the evaluation result of the heading deviation corresponding to the first target.

[0236] Optionally, the processor 300 is specifically configured to read a program in the memory 320 to implement the following steps:

[0237] Determine the velocity deviation of the r-th trajectory point in the sub-trajectory, where the velocity deviation is the velocity deviation between the r-th trajectory point and the r - 1 trajectory points; r ≥ 1 and r is an integer;

[0238] Determine a third value, where the third value is the number of trajectory points whose velocity deviation is less than a fourth threshold;

[0239] Determine the quotient of the third value and the total number of trajectory points of the sub-trajectory as the evaluation result of the velocity deviation corresponding to the first target.

[0240] Optionally, the processor 300 is specifically configured to read a program in the memory 320 to implement the following steps:

[0241] Determine the number of the first trajectory points of the target trajectory segment; wherein, the target trajectory segment is the trajectory segment with the largest number of trajectory points among at least one of the trajectory segments associated and matched with the first target; wherein, the first target is any target within the to-be-tested road section;

[0242] Determine the quotient of the number of the first trajectory points and the total number of trajectory points of the sub-trajectory as the evaluation result of the tracking success rate of the first target.

[0243] The test system provided by the present invention can automatically complete the evaluation of the perception ability of the roadside perception system by acquiring real-time perception data, saving labor costs.

[0244] Those skilled in the art can understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or can be completed by a computer program instructing relevant hardware, and the computer program includes instructions for executing part or all of the steps of the above method; and the computer program can be stored in a readable storage medium, and the storage medium can be any form of storage medium.

[0245] In addition, a specific embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steps of the method in the first embodiment above. And it can achieve the same technical effect, and for the sake of avoiding repetition, it will not be elaborated here.

[0246] In addition, it should be noted that in the devices and methods of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations shall be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above series of processes can naturally be executed chronologically in the order described, but it is not necessary to be executed chronologically. Some steps can be executed in parallel or independently of each other. For those of ordinary skill in the art, it is understandable that all or any steps or components of the methods and devices of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in the form of hardware, firmware, software, or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0247] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the object of the present invention can also be achieved only by providing a program product containing program code for implementing the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be noted that in the devices and methods of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations shall be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above series of processes can naturally be executed chronologically in the order described, but it is not necessary to be executed chronologically. Some steps can be executed in parallel or independently of each other.

[0248] The above are the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An evaluation method for a roadside perception system, characterized in that, Including: Obtain N trajectory segments within the to-be-measured road section according to the perception data within the to-be-measured road section output by the roadside perception system; N belongs to positive integers; Associate and match the N trajectory segments with M targets within the to-be-measured road section, where M belongs to positive integers; N≥M; Determine the evaluation result corresponding to each target according to at least one of the trajectory segments associated and matched with each target; Determine the evaluation result of the roadside perception system according to the evaluation results corresponding to the M targets; Wherein, the associating and matching the N trajectory segments with M targets within the to-be-measured road section includes: Determine P trajectory segments that meet the preset screening conditions from the N trajectory segments; wherein, each of the P trajectory segments is associated and matched with one target in a one-to-one correspondence, and the preset screening conditions are related to the starting position and the ending position of the to-be-measured road section; Take the N-P trajectory segments that do not meet the preset screening conditions among the N trajectory segments as the second trajectory set; and According to the timestamps and position information of the start and end frames of each trajectory segment in the second trajectory set, associate and match the N-P trajectory segments with M-P targets; N≥M≥P, and P is a positive integer; wherein, each target is associated and matched with at least one of the trajectory segments in the second trajectory set.

2. The evaluation method for a roadside perception system according to claim 1, characterized in that, The preset screening conditions include: The first distance is less than or equal to the first threshold; The second distance is less than or equal to the second threshold; Wherein, the first distance is the distance between the starting point of the trajectory segment and the starting position of the to-be-measured road section, and the second distance is the distance between the ending point of the trajectory segment and the ending position of the to-be-measured road section.

3. The evaluation method for a roadside perception system according to claim 1, characterized in that, The associating and matching the N-P trajectory segments with M-P targets according to the timestamps and position information of the start and end frames of each trajectory segment in the second trajectory set includes: Sort the trajectory segments in the second trajectory set in chronological order according to the timestamps of the start and end frames of each trajectory segment in the second trajectory set; Take the target trajectory segment that is after the i-th trajectory segment of the first target and meets the preset matching conditions in the second trajectory set as the (i + 1)-th trajectory segment associated and matched with the first target; wherein, the first target is any target within the to-be-measured road section; i≥1 and i belongs to integers; Wherein, the preset matching conditions include at least one of the following: The lateral position deviation between the end frame of the i-th trajectory segment and the start frame of the target trajectory segment is less than the lateral deviation threshold; The longitudinal position deviation between the end frame of the i-th trajectory segment and the start frame of the target trajectory segment is less than the longitudinal deviation threshold; The distance between the end frame of the i-th trajectory segment and the start frame of the target trajectory segment is less than the distance threshold; The heading deviation between the end frame of the i-th trajectory segment and the start frame of the target trajectory segment is less than the heading deviation threshold.

4. The evaluation method for a roadside perception system according to claim 3, characterized in that, The road type of the to-be-measured road section includes one of the following: curved road section, ramp road section, straight road section; Among them, the matching condition thresholds corresponding to different road types are different, and the matching condition thresholds include at least one of the following: the lateral deviation threshold, the longitudinal deviation threshold, the distance threshold, and the heading deviation threshold.

5. The evaluation method for a roadside perception system according to claim 1, characterized in that, Calculating the evaluation result corresponding to each target according to at least one of the trajectory segments associated and matched with each target includes: Determining a sub-trajectory of the first target within the to-be-tested section according to at least one of the trajectory segments associated and matched with the first target; wherein, the first target is any target within the to-be-tested section; Determining the evaluation result corresponding to the first target according to the sub-trajectory.

6. The evaluation method for a roadside perception system according to claim 5, characterized in that, The determining the evaluation result corresponding to the first target according to the sub-trajectory includes: Determining the number of trajectory points of the sub-trajectory; Determining the expected number of trajectory points of the first target within the to-be-tested section; Determining the quotient of the number of trajectory points of the sub-trajectory and the expected number of trajectory points as the evaluation result of the trajectory recall rate corresponding to the first target.

7. The evaluation method of the roadside perception system according to claim 5, wherein, The determining the evaluation result corresponding to the first target according to the sub-trajectory includes: Determining the position deviation of the j-th trajectory point in the sub-trajectory, where the position deviation is the position deviation between the j-th trajectory point and the (j - 1)-th trajectory point; j≥1 and j is an integer; Determining a first value, where the first value is the number of trajectory points with the position deviation greater than 0; Determining the quotient of the first value and the total number of trajectory points of the sub-trajectory as the evaluation result of the positioning accuracy deviation corresponding to the first target.

8. The evaluation method of the roadside perception system according to claim 5, wherein, The determining the evaluation result corresponding to the first target according to the sub-trajectory includes: Determining the heading deviation of the k-th trajectory point in the sub-trajectory, where the heading deviation is the heading deviation between the k-th trajectory point and the (k - 1)-th trajectory point; k≥1 and k is an integer; Determining a second value, where the second value is the number of trajectory points with the heading deviation less than a third threshold; Determining the quotient of the second value and the total number of trajectory points of the sub-trajectory as the evaluation result of the heading deviation corresponding to the first target.

9. The evaluation method of the roadside perception system according to claim 5, wherein, The determining the evaluation result corresponding to the first target according to the sub-trajectory includes: Determining the speed deviation of the r-th trajectory point in the sub-trajectory, where the speed deviation is the speed deviation between the r-th trajectory point and the (r - 1)-th trajectory point; r≥1 and r is an integer; Determining a third value, where the third value is the number of trajectory points with the speed deviation less than a fourth threshold; Determining the quotient of the third value and the total number of trajectory points of the sub-trajectory as the evaluation result of the speed deviation corresponding to the first target.

10. The evaluation method of the roadside perception system according to claim 5, wherein, The determining the evaluation result corresponding to the first target according to the sub-trajectory includes: Determining the number of the first trajectory points of the target trajectory segment; wherein, the target trajectory segment is the trajectory segment with the most trajectory points among at least one of the trajectory segments associated and matched with the first target; wherein, the first target is any target within the to-be-tested section; Determining the quotient of the number of the first trajectory points and the total number of trajectory points of the sub-trajectory as the evaluation result of the tracking success rate of the first target.

11. A test system, comprising: A transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the evaluation method of the roadside perception system according to any one of claims 1 to 10 are implemented.

12. An evaluation device for a roadside perception system, wherein, Including: A first acquisition module, configured to acquire N trajectory segments in the to-be-tested road section according to the perception data in the to-be-tested road section output by the roadside perception system; N belongs to positive integers; An association matching module, configured to perform association matching between the N trajectory segments and M targets in the to-be-tested road section, where M belongs to positive integers; A first determination module, configured to determine an evaluation result corresponding to each target according to at least one of the trajectory segments associated and matched with each target; A second determination module, configured to determine the evaluation result of the roadside perception system according to the evaluation results corresponding to the M targets; Wherein, the association matching module includes: A first matching sub-module, configured to determine P trajectory segments that meet a preset screening condition from the N trajectory segments; wherein, each of the P trajectory segments is associated and matched with one target in a one-to-one correspondence, and the preset screening condition is related to the start position and end position of the to-be-tested road section; A second matching sub-module, configured to use the N-P trajectory segments that do not meet the preset screening condition among the N trajectory segments as a second trajectory set; and A third matching sub-module, configured to perform association matching between the N-P trajectory segments and M-P targets according to the timestamps and position information of the start and end frames of each trajectory segment in the second trajectory set; N≥M≥P, and P is a positive integer; wherein each target is associated and matched with at least one of the trajectory segments in the second trajectory set.

13. A computer-readable storage medium, on which a computer program is stored, wherein, When the computer program is executed by the processor, the steps of the evaluation method of the roadside perception system according to any one of claims 1 to 10 are implemented.

Images