Roadside sensing equipment monitoring method and device, electronic equipment and storage medium

By using high-quality lidar and RTK test vehicles within the perception range of road-side perception equipment, the automatic comparison of perception data is solved, and the defects of manual monitoring in the prior art are realized, and efficient and all-weather road-side perception equipment monitoring is achieved.

CN119091631APending Publication Date: 2024-12-06ZHIDAO NETWORK TECH (BEIJING) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411290544.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-14
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing roadside perception system relies on manual viewing of video frames, resulting in human error, high cost, time-consuming and inability to monitor around the clock, and cannot meet the real-time monitoring needs.

Method used

Using test vehicles carrying high-quality lidar and RTK to move back and forth within the perception range of road-side sensing equipment. By comparing the lidar sensing data uploaded by the test vehicles and the perception data of road-side sensing equipment, the quasi-calling rate and false alarm rate are calculated in real time. , realize automated monitoring.

Benefits of technology

It improves the monitoring accuracy and efficiency of road-side perception equipment, reduces labor costs, realizes real-time monitoring capabilities around the clock, and reduces abnormal data deviations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091631A_ABST
    Figure CN119091631A_ABST
Patent Text Reader

Abstract

The invention discloses a roadside sensing equipment monitoring method and device, electronic equipment and a storage medium, and the method comprises the steps: to-be-tested roadside sensing equipment and a test vehicle are determined, the test vehicle at least comprises an RTK and a laser radar, and the test vehicle moves back and forth in the sensing range of the to-be-tested roadside sensing equipment; obtaining first sensing data uploaded by the test vehicle, wherein the first sensing data comprises laser radar sensing data and a vehicle track obtained through RTK; according to first sensing data uploaded by the test vehicle, second sensing data uploaded by the to-be-tested roadside sensing equipment is acquired, and the second sensing data comprises multiple pieces of sensing track data; and comparing the first sensing data with the second sensing data to obtain a final monitoring result of the roadside sensing equipment. On one hand, efficient monitoring of the roadside sensing device is achieved, and on the other hand, labor cost is reduced, and all-weather monitoring is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of roadside sensing technology, and in particular to a roadside sensing equipment monitoring method, device, electronic device, and storage medium. Background Art

[0002] The intelligent traffic roadside monitoring system is becoming more and more mature, and the traffic participants it monitors mainly include various motor vehicles, two-wheeled vehicles, pedestrians, etc.

[0003] At present, the roadside evaluation of the accuracy and false alarm rate of traffic participants is mainly carried out by extracting frames from a video of the sensing area, and after reaching a certain number of frames, manually checking the number of traffic participants as the true value, and then comparing it with the system output for calculation. However, this method has problems such as human error, high labor costs, time-consuming, and inability to evaluate all day long. Summary of the invention

[0004] The embodiments of the present application provide a roadside sensing device monitoring method, device, electronic device, and storage medium to achieve efficient monitoring.

[0005] The present application embodiment adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a roadside perception device monitoring method, wherein the method includes:

[0007] Determine a roadside perception device to be tested and a test vehicle, wherein the test vehicle includes at least an RTK and a laser radar, and the test vehicle moves back and forth within a perception range of the roadside perception device to be tested;

[0008] Acquire first perception data uploaded by the test vehicle, where the first perception data includes laser radar perception trajectory data and vehicle trajectory information obtained by RTK;

[0009] Acquire, according to the first perception data uploaded by the test vehicle, second perception data uploaded by the roadside perception device to be tested, where the second perception data includes a plurality of perception trajectory data;

[0010] By comparing the first perception data with the second perception data, the final roadside perception equipment monitoring result is obtained.

[0011] In some embodiments, obtaining the first perception data uploaded by the test vehicle includes:

[0012] Acquire the latitude and longitude information and self-vehicle perception data uploaded by the test vehicle, wherein the self-vehicle perception data at least includes the position information of the road participant, the heading angle information of the road participant, the speed information of the road participant, and the size information of the road participant;

[0013] Obtaining vehicle trajectory information according to the latitude and longitude information of the vehicle and the corresponding time;

[0014] The acquiring, according to the first perception data uploaded by the test vehicle, the second perception data uploaded by the roadside perception device to be tested, comprises:

[0015] According to the vehicle trajectory information, the perception data of the road participant corresponding to the test vehicle trajectory perceived by the roadside perception device to be tested is obtained, and the vehicle trajectory information includes the position of the vehicle and the time corresponding to the position of the vehicle.

[0016] In some embodiments, obtaining a final roadside sensing device monitoring result by comparing the first sensing data with the second sensing data includes:

[0017] By time matching the first perception data and the second perception data, matched lidar perception data uploaded by the test vehicle in each frame, vehicle trajectory information, and perception data within the corresponding range identified by the roadside perception device in the corresponding frame are obtained.

[0018] In some embodiments, obtaining a final roadside sensing device monitoring result by comparing the first sensing data with the second sensing data further includes:

[0019] Calculate a preset reference value of each perceived object in the lidar perception data uploaded by the test vehicle in the current frame and a corresponding perceived object in the perception data within the corresponding range identified by the roadside perception device in the corresponding frame;

[0020] If it is determined that the preset reference value meets the set threshold, the target is determined to be recalled.

[0021] In some embodiments, the method further comprises:

[0022] Calculate a preset reference value of each perceived object in each frame of the laser radar perception data uploaded by the test vehicle and a corresponding perceived object in the perception data within a corresponding range identified by the roadside perception device in the corresponding frame;

[0023] Under the condition that the preset reference value meets the preset threshold, any one or more results of accuracy, recall rate, and false alarm rate in the final monitoring results of the roadside perception equipment are obtained.

[0024] In some embodiments, the comparing the first perception data with the second perception data includes:

[0025] Acquire a timestamp of the first perception data and a timestamp of the second perception data;

[0026] The two timestamps with the closest time interval are used for matching to obtain the lidar perception data uploaded by the test vehicle in each frame and the perception data within the corresponding range recognized by the roadside perception device in the corresponding frame.

[0027] In some embodiments, the comparing the first perception data with the second perception data includes:

[0028] Determining roadside perception data of a corresponding time range according to the vehicle trajectory;

[0029] Map each frame of roadside perception data to the time axis of the ego vehicle perception data to obtain a frame of virtual ego vehicle perception data, wherein the ego vehicle perception data is used to calculate the heading angle, speed, longitude and latitude information of all traffic participants at the above mapping time point;

[0030] The virtual self-vehicle perception data virtual frame is matched with the roadside perception data frame at the corresponding time point to obtain the lidar perception data uploaded by each frame of the test vehicle and the perception data within the corresponding range recognized by the roadside perception device in the corresponding frame.

[0031] In a second aspect, an embodiment of the present application further provides a roadside sensing device monitoring device, wherein the device comprises:

[0032] A determination module, used to determine a roadside perception device to be tested and a test vehicle, wherein the test vehicle includes at least an RTK and a laser radar, and the test vehicle moves back and forth within a perception range of the roadside perception device to be tested;

[0033] A first acquisition module is used to acquire first perception data uploaded by the test vehicle, where the first perception data includes laser radar perception trajectory data and a self-vehicle trajectory obtained by RTK;

[0034] A second acquisition module is used to acquire second perception data uploaded by the roadside perception device to be tested according to the first perception data uploaded by the test vehicle, wherein the second perception data includes a plurality of perception trajectory data;

[0035] A comparison module is used to obtain a final roadside perception device monitoring result by comparing the first perception data with the second perception data.

[0036] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the above method.

[0037] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the above method.

[0038] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: determine the roadside perception device to be tested and the test vehicle. The test vehicle includes at least RTK and laser radar, and the test vehicle moves back and forth within the perception range of the roadside perception device to be tested. The test vehicle can collect the longitude and latitude information of the vehicle and the surrounding obstacle information perceived by the vehicle. By moving the test vehicle back and forth within the perception range of the roadside perception device to be tested, multiple motion trajectories can be obtained. The first perception data uploaded by the test vehicle is obtained, and the first perception data includes laser radar trajectory data. Then, based on the first perception data uploaded by the test vehicle, the second perception data uploaded by the roadside perception device to be tested is obtained, and the second perception data includes multiple perception trajectory data. By comparing the first perception data with the second perception data, the final roadside perception device monitoring result is obtained. Based on the test vehicle equipped with high-quality laser radar and RTK, the accurate recall rate and false alarm rate of the test vehicle within a certain range are used to calculate the accurate recall rate and false alarm rate of the roadside perception result in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0040] Figure 1 A schematic diagram of a usage scenario of a roadside sensing device monitoring method in an embodiment of the present application;

[0041] Figure 2 A schematic diagram of a process flow of a roadside sensing device monitoring method in an embodiment of the present application;

[0042] Figure 3 This is a schematic diagram of the structure of the roadside sensing equipment monitoring device in an embodiment of the present application;

[0043] Figure 4 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0045] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0046] The present application embodiment provides a roadside sensing device monitoring method, such as Figure 2 As shown, a schematic flow chart of a method for monitoring a roadside sensing device in an embodiment of the present application is provided, and the method at least includes the following steps S210 to S240:

[0047] Step S210, determining a roadside perception device to be tested and a test vehicle, wherein the test vehicle at least includes an RTK and a laser radar, and the test vehicle moves back and forth within a perception range of the roadside perception device to be tested.

[0048] The roadside sensing device to be tested is the roadside sensing device that needs to be tested, which usually includes multiple devices. The roadside sensing device can sense the information of traffic participants and also includes test vehicles. The test vehicle includes RTK (Real-time kinematic) and Laser Radar. RTK can provide accurate differential positioning information, and Laser Radar can sense and generate laser point cloud data.

[0049] like Figure 1 As shown, the test vehicle will move back and forth within the perception range of the roadside perception device to be tested, and the roadside perception device to be tested will be monitored based on the perception results obtained. The test vehicle can preferably be an autonomous driving vehicle carrying high-quality, high-precision lidar and RTK identified by the roadside perception device to be tested, and the range is the area where the autonomous driving vehicle can perceive accurately.

[0050] It can be understood that when the test vehicle is preferably an autonomous driving vehicle and is within the set roadside perception range, all-weather testing can be ensured, thereby generating a large amount of test data, thereby improving the test coverage and reducing the numerical deviation caused by abnormal data.

[0051] Step S220, obtaining first perception data uploaded by the test vehicle, where the first perception data includes lidar perception trajectory data and the vehicle trajectory obtained by RTK.

[0052] Usually, the RTK data in the first perception data uploaded by the test vehicle to the roadside backend server is obtained within one or more cycles, including the latitude and longitude information of the vehicle. And the perception data of the test vehicle can be filtered within the n-meter accurate perception range according to the test vehicle's accurate recall rate and false alarm rate to obtain its perception data within n meters. The first perception data includes the laser radar perception trajectory data and the vehicle trajectory obtained by RTK. It can be convenient to match with multiple perception trajectory data of the second perception data later.

[0053] It can be understood that the accuracy of the recall rate and false alarm rate is obtained after the test vehicle is calibrated, and is used as an indicator parameter to determine whether the calibration result is accurate. The recall rate usually refers to the two evaluation indicators of accuracy and recall, which are often used to evaluate the performance of classification models, especially in binary classification problems.

[0054] False Alarm Rate refers to the probability that under certain conditions, reconnaissance equipment mistakenly judges noise or other interference signals as target signals. In radar systems, the false alarm rate may be set at a lower level to ensure system reliability and accurate target detection.

[0055] Step S230: acquiring second perception data uploaded by the roadside perception device to be tested according to the first perception data uploaded by the test vehicle, wherein the second perception data includes a plurality of perception trajectory data.

[0056] According to the latitude and longitude information of the test vehicle uploaded to the roadside backend server at each time, the roadside perception data of the roadside perception device to be tested in the corresponding time period is obtained. In addition, the laser radar vehicle identified in the roadside perception data is calculated according to the trajectory of the test vehicle. The perception data within n meters of the test vehicle obtained in the above steps is also filtered to obtain the perception data within n meters of the test vehicle identified by the roadside perception device to be tested.

[0057] Step S240, obtaining a final roadside sensing device monitoring result by comparing the first sensing data with the second sensing data.

[0058] By comparing the matching results of each frame in the first perception data and the second perception data and the parameters of each frame, the final roadside perception equipment monitoring result is obtained.

[0059] Through the above method, the accurate recall rate and false alarm rate of each roadside perception can be calculated in real time. Whenever a test vehicle passes the roadside perception device to be tested, the perception data of the test vehicle can be used as the true value to determine whether the perception data of the roadside perception device to be tested is recalled.

[0060] Through the above method, the roadside perception equipment to be tested can be monitored in real time within the range passed by the test vehicle, and each frame can be matched according to the trajectory matching result, and the reference value corresponding to each frame can be calculated to determine whether the target is recalled.

[0061] Different from the related technology which mainly extracts frames from a video of a perception area, manually checks the number of each traffic participant as the true value after reaching a certain number of frames, and then compares it with the system output to calculate the resulting monitoring result which cannot meet the requirements of real-time monitoring, the above method is based on an autonomous driving vehicle carrying high-quality, high-precision lidar and RTK, and realizes real-time perception of the roadside to be monitored within its accurate perception area.

[0062] In one embodiment of the present application, the acquiring of the first perception data uploaded by the test vehicle includes: acquiring the latitude and longitude information and the self-vehicle perception data uploaded by the test vehicle, the self-vehicle perception data including at least the position information of the road participants, the heading angle information of the road participants, the speed information of the road participants and the size information of the road participants; obtaining the self-vehicle trajectory information according to the latitude and longitude information and the corresponding time of the self-vehicle; the acquiring of the second perception data uploaded by the roadside perception device to be tested according to the first perception data uploaded by the test vehicle includes: acquiring the perception data of the road participants corresponding to the trajectory of the test vehicle perceived by the roadside perception device to be tested according to the self-vehicle trajectory information, the self-vehicle trajectory information including the position of the self-vehicle and the time corresponding to the position of the self-vehicle.

[0063] The test vehicle uploads information including but not limited to the latitude and longitude information of the vehicle and the perception data of the vehicle. The latitude and longitude information of the vehicle serves as the location information of the vehicle. The perception data of the vehicle also includes the location information of road participants, the heading angle information of road participants, the speed information of road participants and the size information of road participants. Further, through the trajectory information of the vehicle, the perception data of the road participants corresponding to the test vehicle perceived by the roadside perception device to be tested is obtained. Since the trajectory information of the vehicle includes the location of the vehicle and the time corresponding to the location of the vehicle, the roadside perception device to be tested can obtain the perception data of the road participants at the corresponding location and time.

[0064] In one embodiment of the present application, the final roadside perception device monitoring result is obtained by comparing the first perception data with the second perception data, including: matching the first perception data with the second perception data according to time, and obtaining matched lidar perception data uploaded by each frame of the test vehicle, the vehicle trajectory information signal and the perception data within the corresponding range identified by the roadside perception device in the corresponding frame.

[0065] When comparing the first perception data with the second perception data, it is found that the perception data of both are data of a certain moment (frame), so the two are matched according to time to obtain the perception data uploaded by the lidar vehicle in each frame and the perception data within the corresponding range identified by the roadside in the corresponding frame.

[0066] In one embodiment of the present application, the final roadside perception device monitoring result is obtained by comparing the first perception data with the second perception data, and it also includes: calculating the preset reference value of each perception object in the lidar perception data uploaded by the test vehicle of the current frame and the corresponding perception object in the perception data within the corresponding range identified by the roadside perception device of the corresponding frame, and the preset reference value at least includes IOU (Intersection over Union, as a standard for measuring the accuracy of detecting corresponding objects in a specific data set); if it is judged that the preset reference value meets the set threshold, the target is determined to be recalled.

[0067] In order to obtain more accurate recognition results, the preset reference value of each perceived object corresponding to the two data sources above is calculated (with the perception data of the test vehicle as the true value). If the preset reference value meets a certain threshold (depending on the actual situation, and set at 80% in the test standard), the target is determined to be recalled, and then its type is determined.

[0068] In one embodiment of the present application, the method also includes: calculating a preset reference value of each perceived object in the lidar perception data uploaded by the test vehicle in each frame and the corresponding perceived object in the perception data within the corresponding range identified by the roadside perception device in the corresponding frame; under the condition that the preset reference value meets a preset threshold, obtaining any one or more results of accuracy, recall rate, and false alarm rate in the final monitoring result of the roadside perception device.

[0069] Calculate the preset reference value of each perceived object in the lidar perception data uploaded by the test vehicle in each frame and the corresponding perceived object in the perception data within the corresponding range identified by the roadside perception device in the corresponding frame. Under the condition that the preset reference value meets the preset threshold, the final monitoring result of the roadside perception device includes but is not limited to any one or more results of accuracy, recall rate, and false alarm rate.

[0070] Precision: measures the proportion of samples predicted by the model to be positive that are actually positive. The calculation formula is:

[0071] Accuracy = Number of samples that are actually positive Number of samples predicted to be positive / Number of samples predicted to be positive Number of samples that are actually positive

[0072] The accuracy reflects the proportion of positive classes predicted by the model that are actually positive.

[0073] Recall: It measures the proportion of positive samples correctly identified by the model to all actual positive samples. The calculation formula is:

[0074] Recall rate = the number of positive samples predicted correctly by the model / the number of samples that are actually positive / Recall rate = the number of samples that are actually positive / the number of samples that are correctly predicted by the model.

[0075] The recall rate reflects the proportion of samples that the model can identify among all samples that are actually positive.

[0076] These two metrics are often used together because they evaluate the performance of the model from different perspectives. A high precision means that the model predicts a high proportion of positive classes that are actually positive, while a high recall means that the model is able to identify most of the samples that are actually positive.

[0077] In one embodiment of the present application, the comparison of the first perception data and the second perception data includes: obtaining the timestamp of the first perception data and the timestamp of the second perception data; matching the two timestamps with the closest time intervals to obtain each frame of lidar perception data uploaded by the test vehicle and the perception data within the corresponding range identified by the roadside perception device in the corresponding frame.

[0078] According to the trajectory of the vehicle (including the time range), the roadside perception data of the corresponding time range is obtained. If the time of each frame of the roadside perception data is closest to the time of a frame of the vehicle perception data, then the frame of the roadside perception data matches the corresponding frame of the vehicle perception data. That is, the first frame of the vehicle perception data matches the first frame of the roadside perception data. Since the frequency of the RTK data is 100hz and the frequency of the roadside perception device to be tested is 10hz, there may be a 5ms time error.

[0079] In one embodiment of the present application, the comparison of the first perception data and the second perception data includes: determining the roadside perception data of the corresponding time range based on the trajectory information of the self-vehicle; mapping each frame time of the roadside perception data to the time axis of the self-vehicle perception data to obtain a frame of virtual self-vehicle perception data, and the self-vehicle perception data is used to calculate the heading angle, speed, longitude and latitude information of all traffic participants at the above-mentioned mapping time point; matching the virtual self-vehicle perception data virtual frame with the roadside perception data frame at the corresponding time point to obtain each frame of lidar perception data uploaded by the test vehicle and the perception data within the corresponding range identified by the roadside perception device of the corresponding frame.

[0080] According to the trajectory information of the ego vehicle including the time range, the roadside perception data of the corresponding time range is obtained. Since each frame of the roadside perception data is mapped to the time axis of the ego vehicle perception data, the ego vehicle perception data calculates the heading angle, speed, longitude and latitude information of all traffic participants at the above mapping time point, thereby obtaining a frame of virtual ego vehicle perception data, which matches the roadside perception data frame at the corresponding time point. Since the frequency of RTK data is 100hz, this method can minimize the existing 5ms error.

[0081] For example, when the roadside perception data at time 1 is mapped to the time axis of the ego vehicle perception data, assuming that all traffic participants perceived by the ego vehicle are traveling at a constant speed from time 1 to time 2 of the ego vehicle, for a certain traffic participant perceived by the ego vehicle, its position, speed, and heading angle at time 1 are calculated as follows:

[0082] Longitude: lon(pin 1) = lon(1) + (lon(2) - lon(1)) * (t(pin 1) - t(1))l / (t(2) - t(1));

[0083] Latitude: lat(pin 1) = lat(1) + (lat(2) - lat(1)) * (t(pin 1) - t(1))l / (t(2) - t(1));

[0084] Speed: speed(pin 1) = speed(1) + (speed(2) - speed(1)) * (t(pin 1) - t(1))l / (t(2) - t(1));

[0085] Heading angle: headingd(pin 1)=headingd(1)+(headingd(2)-headingd(1))*(t(pin 1)-t(1))l / (t(2)-t(1)).

[0086] The present application also provides a roadside sensing device monitoring device 300, such as Figure 3 As shown, a schematic diagram of the structure of a roadside sensing device monitoring device in an embodiment of the present application is provided, wherein the roadside sensing device monitoring device 300 at least includes: a determination module 310, a first acquisition module 320, a second acquisition module 330 and a comparison module 340, wherein:

[0087] In one embodiment of the present application, the determination module 310 is specifically used to: determine a roadside perception device to be tested and a test vehicle, the test vehicle at least includes RTK and a lidar, and the test vehicle moves back and forth within the perception range of the roadside perception device to be tested.

[0088] The roadside sensing device to be tested is the roadside sensing device that needs to be tested, which usually includes multiple devices. The roadside sensing device can sense the information of traffic participants and also includes a test vehicle. The test vehicle includes RTK and LiDAR. RTK can provide accurate differential positioning information, and LiDAR can sense and generate laser point cloud data.

[0089] The test vehicle will move back and forth within the perception range of the roadside perception device to be tested, and the test vehicle will monitor the roadside perception device to be tested within the perception range. The test vehicle can preferably be an autonomous driving vehicle with high-quality, high-precision LiDAR and RTK identified by the roadside perception device to be tested, and the range is the area where the autonomous driving vehicle can perceive accurately.

[0090] It can be understood that when the test vehicle is preferably an autonomous driving vehicle and is within the set roadside perception range, all-weather testing can be ensured, thereby generating a large amount of test data, thereby improving the test coverage and reducing the numerical deviation caused by abnormal data.

[0091] In one embodiment of the present application, the first acquisition module 220 is specifically used to: acquire first perception data uploaded by the test vehicle, where the first perception data includes lidar perception trajectory data and the vehicle trajectory obtained by RTK.

[0092] Usually, the longitude and latitude information of the self-vehicle uploaded by the first perception data uploaded by the test vehicle is obtained in one or more timing cycles. And the self-vehicle perception data of the test vehicle can be filtered within the perception range n meters according to the accurate recall rate and false alarm rate of the test vehicle to obtain the perception data within n meters.

[0093] It can be understood that the accuracy of the recall rate and false alarm rate is obtained after the test vehicle is calibrated, and is used as an indicator parameter to determine whether the calibration result is accurate. The recall rate usually refers to the two evaluation indicators of accuracy and recall, which are often used to evaluate the performance of classification models, especially in binary classification problems.

[0094] False Alarm Rate refers to the probability that under certain conditions, reconnaissance equipment mistakenly judges noise or other interference signals as target signals. In radar systems, the false alarm rate may be set at a lower level to ensure system reliability and accurate target detection.

[0095] In one embodiment of the present application, the second acquisition module 230 is specifically used to: acquire second perception data uploaded by the roadside perception device to be tested according to the first perception data uploaded by the test vehicle, and the second perception data includes multiple perception trajectory data.

[0096] According to the latitude and longitude information of the test vehicle uploaded at each time, the roadside perception data of the roadside perception device to be tested in the corresponding time period is obtained. In addition, the laser radar vehicle identified in the roadside perception data is calculated according to the trajectory of the test vehicle. The perception data within n meters of the test vehicle obtained in the above steps is also filtered to obtain the perception data within n meters of the test vehicle identified by the roadside perception device to be tested.

[0097] In one embodiment of the present application, the comparison module 340 is specifically used to obtain a final roadside perception device monitoring result by comparing the first perception data with the second perception data.

[0098] By comparing the matching results of each frame in the first perception data and the second perception data and the parameters of each frame, the final roadside perception equipment monitoring result is obtained.

[0099] In one embodiment of the present application, the first acquisition module 310 is further used to

[0100] Acquire the latitude and longitude information and self-vehicle perception data uploaded by the test vehicle, wherein the self-vehicle perception data includes the position information, the heading angle information, the speed information and the size information of the road participant;

[0101] The acquiring, according to the first perception data uploaded by the test vehicle, the second perception data uploaded by the roadside perception device to be tested, comprises:

[0102] According to the trajectory information of the vehicle, the perception data of the road participant corresponding to the test vehicle perceived by the roadside perception device to be tested is obtained, and the trajectory information of the vehicle includes the position of the vehicle and the time corresponding to the position of the vehicle.

[0103] In one embodiment of the present application, the comparison module 340 is also used to

[0104] By time matching the first perception data and the second perception data, the lidar perception data uploaded by each frame of the test vehicle and the perception data within the corresponding range identified by the roadside perception device in the corresponding frame are obtained.

[0105] In one embodiment of the present application, it further includes: a matching module for

[0106] Calculate a preset reference value of each perceived object in the lidar perception data uploaded by the test vehicle in the current frame and a corresponding perceived object in the perception data within the corresponding range identified by the roadside perception device in the corresponding frame, wherein the preset reference value includes at least an IOU;

[0107] If it is determined that the preset reference value meets the set threshold, the target is determined to be recalled.

[0108] In one embodiment of the present application, it further includes: a computing module for

[0109] Calculate a preset reference value of each perceived object in each frame of the laser radar perception data uploaded by the test vehicle and a corresponding perceived object in the perception data within a corresponding range identified by the roadside perception device in the corresponding frame;

[0110] Under the condition that the preset reference value meets the preset threshold, any one or more results of accuracy, recall rate, and false alarm rate in the final monitoring results of the roadside perception equipment are obtained.

[0111] In one embodiment of the present application, the comparison module 340 is also used to

[0112] Acquire a timestamp of the first perception data and a timestamp of the second perception data;

[0113] The two timestamps with the closest time interval are used for matching to obtain the lidar perception data uploaded by the test vehicle in each frame and the perception data within the corresponding range recognized by the roadside perception device in the corresponding frame.

[0114] In one embodiment of the present application, the comparison module 340 is also used to

[0115] According to the trajectory of the vehicle, determine the roadside perception data of the corresponding time range;

[0116] Map each frame of roadside perception data to the time axis of the ego vehicle perception data to obtain a frame of virtual ego vehicle perception data, wherein the ego vehicle perception data is used to calculate the heading angle, speed, longitude and latitude information of all traffic participants at the above mapping time point;

[0117] The simulated self-vehicle perception data virtual frame is matched with the roadside perception data frame at the corresponding time point to obtain the lidar perception data uploaded by the test vehicle in each frame and the perception data within the corresponding range recognized by the roadside perception device in the corresponding frame.

[0118] It can be understood that the above-mentioned roadside perception equipment monitoring device can implement the various steps of the roadside perception equipment monitoring method provided in the aforementioned embodiment, and the relevant explanations about the roadside perception equipment monitoring method are applicable to the roadside perception equipment monitoring device, which will not be repeated here.

[0119] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0120] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0121] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0122] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a roadside sensing equipment monitoring device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0123] Determine a roadside perception device to be tested and a test vehicle, wherein the test vehicle includes at least an RTK and a laser radar, and the test vehicle moves back and forth within a perception range of the roadside perception device to be tested;

[0124] Acquire first perception data uploaded by the test vehicle, where the first perception data includes laser radar perception trajectory data and a self-vehicle trajectory obtained by RTK;

[0125] Acquire, according to the first perception data uploaded by the test vehicle, second perception data uploaded by the roadside perception device to be tested, where the second perception data includes a plurality of perception trajectory data;

[0126] By comparing the first perception data with the second perception data, the final roadside perception equipment monitoring result is obtained.

[0127] The above application Figure 2 The method performed by the roadside sensing equipment monitoring device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or instructions in software form. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0128] The electronic device may also perform Figure 2 The method is executed by the roadside sensing device monitoring device, and the roadside sensing device monitoring device is realized in Figure 2 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0129] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 2 The method performed by the roadside sensing device monitoring device in the illustrated embodiment is specifically used to perform:

[0130] Determine a roadside perception device to be tested and a test vehicle, wherein the test vehicle includes at least an RTK and a laser radar, and the test vehicle moves back and forth within a perception range of the roadside perception device to be tested;

[0131] Acquire first perception data uploaded by the test vehicle, where the first perception data includes laser radar perception trajectory data and a self-vehicle trajectory obtained by RTK;

[0132] Acquire, according to the first perception data uploaded by the test vehicle, second perception data uploaded by the roadside perception device to be tested, where the second perception data includes a plurality of perception trajectory data;

[0133] By comparing the first perception data with the second perception data, the final roadside perception equipment monitoring result is obtained.

[0134] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0136] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0138] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0139] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0140] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0141] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0142] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0143] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A roadside sensing device monitoring method, wherein: The method comprises: Determine a roadside perception device to be tested and a test vehicle, wherein the test vehicle includes at least an RTK and a laser radar, and the test vehicle moves back and forth within a perception range of the roadside perception device to be tested; Acquire first perception data uploaded by the test vehicle, where the first perception data includes laser radar perception trajectory data and vehicle trajectory information obtained by RTK; Acquire, according to the first perception data uploaded by the test vehicle, second perception data uploaded by the roadside perception device to be tested, where the second perception data includes a plurality of perception trajectory data; By comparing the first perception data with the second perception data, the final roadside perception equipment monitoring result is obtained.

2. The method of claim 1, wherein: The obtaining of the first perception data uploaded by the test vehicle includes: Acquire the latitude and longitude information and self-vehicle perception data uploaded by the test vehicle, wherein the self-vehicle perception data at least includes the position information of the road participant, the heading angle information of the road participant, the speed information of the road participant, and the size information of the road participant; Obtaining vehicle trajectory information according to the latitude and longitude information of the vehicle and the corresponding time; The acquiring, according to the first perception data uploaded by the test vehicle, the second perception data uploaded by the roadside perception device to be tested, comprises: According to the vehicle trajectory information, the perception data of the road participant corresponding to the test vehicle trajectory perceived by the roadside perception device to be tested is obtained, and the vehicle trajectory information includes the position of the vehicle and the time corresponding to the position of the vehicle.

3. The method of claim 1, wherein: The obtaining of a final roadside sensing device monitoring result by comparing the first sensing data with the second sensing data includes: By time matching the first perception data and the second perception data, matched lidar perception data uploaded by the test vehicle in each frame, vehicle trajectory information, and perception data within the corresponding range identified by the roadside perception device in the corresponding frame are obtained.

4. The method of claim 3, wherein: By comparing the first perception data with the second perception data, a final roadside perception device monitoring result is obtained, further comprising: Calculate a preset reference value of each perceived object in the lidar perception data uploaded by the test vehicle in the current frame and a corresponding perceived object in the perception data within the corresponding range identified by the roadside perception device in the corresponding frame; If it is determined that the preset reference value meets the set threshold, the target is determined to be recalled.

5. The method of claim 4, wherein: The method further comprises: Calculate a preset reference value of each perceived object in each frame of the laser radar perception data uploaded by the test vehicle and a corresponding perceived object in the perception data within a corresponding range identified by the roadside perception device in the corresponding frame; Under the condition that the preset reference value meets the preset threshold, any one or more results of accuracy, recall rate, and false alarm rate in the final monitoring results of the roadside perception equipment are obtained.

6. The method of claim 1, wherein: Comparing the first sensed data with the second sensed data includes: Acquire a timestamp of the first perception data and a timestamp of the second perception data; The two timestamps with the closest time interval are used for matching to obtain the lidar perception data uploaded by the test vehicle in each frame and the perception data within the corresponding range recognized by the roadside perception device in the corresponding frame.

7. The method of claim 1, wherein: The comparing the first perception data with the second perception data includes: Determining roadside perception data within a corresponding time range according to the vehicle trajectory information; Map each frame of roadside perception data to the time axis of the vehicle perception data to obtain a frame of virtual vehicle perception data, which is used to calculate the heading angle, speed, longitude and latitude information of all traffic participants at the above mapping time point; The virtual self-vehicle perception data virtual frame is matched with the roadside perception data frame at the corresponding time point to obtain the lidar perception data uploaded by each frame of the test vehicle and the perception data within the corresponding range recognized by the roadside perception device of the corresponding frame.

8. A roadside sensing device monitoring device, wherein: The device comprises: A determination module, used to determine a roadside perception device to be tested and a test vehicle, wherein the test vehicle includes at least an RTK and a laser radar, and the test vehicle moves back and forth within a perception range of the roadside perception device to be tested; A first acquisition module is used to acquire first perception data uploaded by the test vehicle, where the first perception data includes laser radar perception trajectory data and a self-vehicle trajectory obtained by RTK; A second acquisition module, configured to acquire second perception data uploaded by the roadside perception device to be tested according to the first perception data uploaded by the test vehicle, wherein the second perception data includes a plurality of perception trajectory data; A comparison module is used to obtain a final roadside perception device monitoring result by comparing the first perception data with the second perception data.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute any one of the methods of claims 1 to 7.