CN113920729A - Method for evaluating perception capability of traffic participants based on roadside perception system - Google Patents
Method for evaluating perception capability of traffic participants based on roadside perception system Download PDFInfo
- Publication number
- CN113920729A CN113920729A CN202111183372.9A CN202111183372A CN113920729A CN 113920729 A CN113920729 A CN 113920729A CN 202111183372 A CN202111183372 A CN 202111183372A CN 113920729 A CN113920729 A CN 113920729A
- Authority
- CN
- China
- Prior art keywords
- roadside
- perception
- traffic
- traffic participants
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000008447 perception Effects 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000011156 evaluation Methods 0.000 claims abstract description 59
- 238000012360 testing method Methods 0.000 claims abstract description 51
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 17
- 238000012544 monitoring process Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method for evaluating the perception capability of a traffic participant based on a roadside sensing system, which comprises the steps of installing a roadside truth value system and a roadside sensing system to be tested at the same roadside position, and is characterized by comprising the following steps of: the method comprises the following steps that a road side sensing system to be tested is used for collecting road side sensing data of traffic participants and truth-value vehicles; acquiring test data of a truth-value vehicle and test data of a road side truth-value system on traffic participants; and inputting the roadside sensing data and the test data into a traffic participant sensing ability evaluation algorithm based on timestamp matching of the roadside sensing data and the test data to obtain a traffic participant sensing ability evaluation result. The invention can systematically and effectively evaluate the perception capability of the traffic participants of the road side perception system to be tested, and meets the requirements of the road side perception system on high-accuracy test and verification of the perception capability of the traffic participants.
Description
Technical Field
The invention relates to the technical field of vehicle-road cooperative systems, in particular to a method for evaluating the perception capability of a traffic participant based on a vehicle-road cooperative roadside perception system.
Background
The intelligent driving technology is to really realize efficient and safe transportation and travel, the single-vehicle intelligence is far from enough, and the vehicle-road cooperation is the future direction. Particularly, with a series of technical breakthroughs of 5G, V2X, artificial intelligence, cloud computing and big data, the vehicle, road and cloud depths are integrated to construct a collaborative intelligent traffic system, so that the limitation of the current single-vehicle intelligence and traditional traffic management can be effectively solved.
The vehicle-road cooperation is a safe, efficient and environment-friendly road traffic system which adopts the advanced wireless communication, new generation internet and other technologies, implements vehicle-road dynamic real-time information interaction in all directions, develops vehicle active safety control and road cooperative management on the basis of full-time dynamic traffic information acquisition and fusion, fully realizes effective cooperation of human and vehicle roads, ensures traffic safety and improves traffic efficiency.
In the cooperative application of the vehicle and the road, the roadside sensing system realizes the real-time vectorization and tracking of the global target, and the accurate sensing capability of the roadside sensing system is the key of the roadside sensing system.
At present, the test and the evaluation of the perception abilities of the traffic participants of the vehicle-road cooperative roadside sensing system are less explored, an evaluation index system of the perception abilities of the traffic participants of the roadside sensing system is not established, and the perception abilities of the traffic participants of the roadside sensing system cannot be systematically verified.
Therefore, how to provide an effective evaluation method for the sensing ability of the traffic participants of the to-be-tested vehicle-road cooperative drive test sensing system in a systematized manner is a problem that needs to be solved by the technical staff in the field.
Disclosure of Invention
In view of the above, the invention provides an evaluation index system, a test method and an evaluation method for the perception capability of the traffic participants of the road-side cooperative perception system, which are constructed, and can meet the requirements of high-accuracy test and verification on the perception capability of the traffic participants of the road-side cooperative perception system in the road-side cooperative system.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for evaluating the perception capability of a traffic participant based on a roadside sensing system is characterized in that a roadside truth value system and a roadside sensing system to be tested are installed at the same roadside position, and comprises the following steps:
the method comprises the following steps that a road side sensing system to be tested is used for collecting road side sensing data of traffic participants and truth-value vehicles;
acquiring test data of a truth-value vehicle and test data of a road side truth-value system on traffic participants;
and inputting the roadside perception data and the test data into a perception capability evaluation algorithm of the traffic participants based on timestamp matching of the roadside perception data and the test data to obtain a perception capability evaluation result of the traffic participants.
Preferably, the acquisition of roadside sensing data by using a real-valued vehicle of the roadside sensing system to be tested comprises:
a real-value vehicle passes through a sensing area within a given speed range;
the roadside sensing system that awaits measuring exports vehicle roadside perception data with time stamp, includes: location, speed, heading angle, and/or size of the vehicle.
Preferably, the acquisition of roadside sensing data of the traffic participant by using the roadside sensing system to be tested comprises:
the road side sensing system to be tested identifies the target number of the traffic participants passing through the sensing area and the classification number of the traffic participants passing through the sensing area in a given time interval.
Preferably, the acquisition of roadside sensing data of the traffic participant by using the roadside sensing system to be tested comprises:
a road side truth value system carries out statistics to obtain a track truth value;
counting the total target track number A of the video frames in a given number before and after by taking the video frames of the maximum track true value detection target number of the road side true value system as the center;
and acquiring the number B of unchanged target tracks corresponding to the same video frame of the roadside sensing system to be detected according to the timestamp.
Preferably, the categories of the traffic participants include: automotive, pedestrian, and non-automotive.
Preferably, the acquiring of the test data of the truth vehicle includes:
a truth vehicle outputs time-stamped test data as it passes through a sensing region within a given speed range, comprising: true vehicle positioning, speed, heading angle, and/or size.
Preferably, the acquiring the test data of the road side truth value system on the traffic participants comprises:
the roadside truth system identifies the target number of traffic participants passing through the sensing region and the classification number of the traffic participants passing through the sensing region within the given time interval.
Preferably, the method for evaluating the perception capability of the traffic participant comprises the steps of inputting roadside perception data and test data into a perception capability evaluation algorithm of the traffic participant based on timestamp matching of the roadside perception data and the test data, and obtaining a perception capability evaluation result of the traffic participant, wherein the steps comprise:
determining the perception capability evaluation factors of the traffic participants, wherein the perception capability evaluation factors comprise the size precision, the positioning precision, the speed precision and/or the course angle precision of the motor vehicle;
and comparing and calculating roadside perception data corresponding to the evaluation factors with the test data according to the time stamp, wherein the positioning precision converts longitude and latitude into Euclidean distance to carry out result statistics.
Preferably, the method for evaluating the perception capability of the traffic participant comprises the steps of inputting roadside perception data and test data into a perception capability evaluation algorithm of the traffic participant based on timestamp matching of the roadside perception data and the test data, and obtaining a perception capability evaluation result of the traffic participant, wherein the steps comprise:
determining the perception capability evaluation factors of the traffic participants, including the classification accuracy, the omission factor and/or the false detection rate of motor vehicles, pedestrians and non-motor vehicles;
and respectively extracting road side sensing data corresponding to the evaluation factors of a plurality of time periods and the test data according to the time stamps for comparison and calculation.
Preferably, the method for evaluating the perception capability of the traffic participant comprises the steps of inputting roadside perception data and test data into a perception capability evaluation algorithm of the traffic participant based on timestamp matching of the roadside perception data and the test data, and obtaining a perception capability evaluation result of the traffic participant, wherein the steps comprise:
determining the perception capability evaluation factors of the traffic participants, including the target tracking success rate of the traffic participants;
and calculating the tracking success rate according to the target track quantity A corresponding to the track true value and the target track quantity B acquired by the road side sensing system to be detected.
Through the technical scheme, compared with the prior art, the invention has the beneficial effects that:
according to the method, from the requirement of a service object of the vehicle-road cooperative roadside sensing system, an evaluation index system, a test method and an evaluation method for the perception capability of the traffic participants of the vehicle-road cooperative roadside sensing system are constructed according to the data interaction requirement of the vehicle-road cooperative roadside sensing system in the standard of application layer and application data interaction of the communication system for the vehicle of the T/CSAE53-2020 cooperative intelligent transportation system, the perception capability of the traffic participants of the vehicle-road cooperative roadside sensing system can be verified in the vehicle-road cooperative system, the perception capability rating of the traffic participants of the vehicle-road cooperative roadside sensing system is determined according to the evaluation model, the evaluation system has higher accuracy and comprehensiveness for the road-side sensing system to be tested, and the method has important significance for standardizing the application and popularization of the vehicle-road cooperative system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts;
fig. 1 is a schematic diagram of an evaluation method for perception abilities of traffic participants based on a roadside perception system according to an embodiment of the present invention;
fig. 2 is an evaluation hierarchy structure diagram of an evaluation method for a traffic participant perception capability based on a roadside perception system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The roadside sensing is realized by utilizing sensors such as a camera, a millimeter wave radar and a laser radar and combining roadside edge calculation, and the final purpose is to realize instantaneous intelligent sensing of traffic participants, road conditions and the like of the road section. The intelligent monitoring system has the advantages that the integrated operation monitoring of human-vehicle-road-cloud is realized, the road traffic abnormity is found at the first time, the intelligent applications such as vehicle-road cooperation, vehicle-cloud cooperation and regional road-cloud cooperation are realized, the intelligent travel demands of automatically driven vehicles and social vehicles are met, and meanwhile, the intelligent monitoring system can enable a monitoring mechanism to become more efficient and flexible, so that a monitoring environment with higher response speed and more flexibility is established.
In the method for evaluating the perception capability of a traffic participant based on a roadside sensing system disclosed by the embodiment, a roadside truth value system and a roadside sensing system to be tested are installed at the same roadside position. Referring to fig. 1, the method needs to construct an evaluation index system, test data of a road side real value system and a real value vehicle based on evaluation factors in the system, and acquire road side sensing data of a road side sensing system to be tested.
It should be noted that the data evaluated by the roadside truth value system and the roadside sensing system to be tested are both in the same timestamp range, so as to ensure the accuracy of data comparison and calculation.
The specific implementation process is as follows:
s1: and (5) constructing an evaluation index system. The evaluation factors in the evaluation index system comprise:
the size precision, the positioning precision, the speed precision and the course angle precision of the motor vehicle.
The classification accuracy, the omission factor and the false detection rate of the traffic participants.
And the target tracking success rate of the traffic participants.
S2: and (5) testing the perception ability of the traffic participants.
S21 testing the dimensional accuracy, positioning accuracy, speed accuracy and course angle accuracy of the motor vehicle
And (3) testing conditions are as follows: truth-value vehicle
The real-value vehicle passes through the sensing area within the allowable speed range;
outputting the position, the speed and the course angle of the vehicle by the truth-value vehicle, comparing the position, the speed and the course angle according to the timestamp and the system output, and comparing the vehicle size with the actual vehicle size;
the 4 lanes are respectively tested for at least 1 time;
and S22, testing the classification accuracy, the omission factor and the false detection rate of the traffic participants.
And (3) testing conditions are as follows: roadside truth system + manual review
Each set of roadside system to be tested is installed and operated for 24 hours, the total number of samples is not less than 30000 (motor vehicles are preferably not less than 25000, non-motor vehicles and pedestrians are not less than 5000, if the number of field samples is not less than the number within the set time, the field samples are revised), and a roadside truth value system is installed on the roadside;
taking the target number, classification number and the like of the traffic participants output by the road side truth value system and subjected to manual rechecking as true values;
and respectively extracting data of 8: 30-9: 30, 13: 00-14: 00 and 17: 00-18: 00, comparing the system sensing result with the true value data, and respectively counting the classification accuracy, the undetected rate and the false detection rate of the motor vehicles, pedestrians and non-motor vehicles.
And S23, the target tracking success rate (motor vehicle) of the traffic participants.
And (3) testing conditions are as follows: road side truth value system
A road side truth value system carries out statistics to obtain a track truth value;
counting the total number A of target tracks of the front and rear 100 frames by taking the frame with the maximum detection target number as a center, wherein A is not less than 100 tracks;
the ID number B of the target which is not changed and is given by the system to be tested;
the tracking success rate is B/A.
S3: traffic participant perception test data evaluation
The method for evaluating the size precision, the positioning precision, the speed precision and the course angle precision of the motor vehicle.
And the positioning precision converts the longitude and latitude into the Euclidean distance to carry out result statistics.
The average value and standard deviation of the difference value meet the requirement.
A traffic participant classification accuracy, omission factor and false detection rate evaluation method.
The classification accuracy is as follows: the ratio of the sample number of the traffic participant category to the total sample number is correctly given by the system to be tested;
the omission factor is: in a given test sample, the ratio of the number of samples of traffic participants not detected by the system to be tested to the total number of samples comprises the missing rate of the traffic participants of different classes;
the false detection rate is as follows: in a given test sample, the ratio of the number of samples of the traffic participants which are actually not detected by the system to be tested to the total number of samples comprises the false detection rate of the traffic participants of different classes.
Provided is a traffic participant target tracking success rate evaluation method.
The tracking success rate meets the requirements.
According to the traffic participant perception data and road side truth value system data output by the vehicle and road cooperative road side perception system and the comparison process, the traffic participant perception capability rating can be determined according to a model established by an evaluation algorithm.
The evaluation process of the technical scheme of the invention in a specific embodiment is given as follows:
table 1 below shows the test data and the evaluation factors for the perception abilities of the traffic participants. The relative error is absolute error/true value.
TABLE 1 test data and traffic participant perceptibility assessment factor
And (3) carrying out weight distribution on the obtained evaluation factor related test data by using an analytic hierarchy process:
the method comprises the following steps: and establishing an evaluation index level according to the evaluation factor, namely the influence factor of the perception capability evaluation of traffic participation. As shown in fig. 2.
Step two: constructing a judgment matrix and assigning
And constructing a judgment matrix according to the hierarchical structure of the evaluation index. The method for constructing the judgment matrix comprises the following steps: each element with the downward membership is used as the first element of the judgment matrix, each element which is subordinate to the element is arranged on the first row and the first column behind the element at one time, then the judgment matrix is filled, the importance degree of the two elements which are compared in pairs is determined according to the expert learning method and the criterion of the judgment matrix, and the importance degree is assigned according to 1-9. Higher valuation indicates that the former is more important than the latter.
After the hierarchical model is constructed, for a certain layer, when the importance of the ith element and the jth element relative to a certain factor of the previous layer is compared, the importance is expressed by using the relative importance aij of the number quantization, and if n elements are totally involved in the comparison, the matrix
Referred to as a decision matrix.
Wherein 2,4,6,8 are respectively between the corresponding importance levels of 1,3,5,7, 9. Obviously, the elements in a satisfy:
1)aij＞0
2)aji＝1/aij
3)aii＝1
the decision matrix is shown in table 2 below.
TABLE 2 decision matrix
| A | B1 | B2 | B3 | B4 | B5 | B6 | B7 | B8 |
| B1 | 1 | 3/7 | 1/3 | 3/5 | 3/5 | 5/7 | 7/9 | 3/5 |
| B2 | 7/3 | 1 | 5/3 | 1/3 | 3/1 | 2/1 | 3/2 | 4/3 |
| B3 | 3/1 | 3/5 | 1 | 8/9 | 3/2 | 7/4 | 5/2 | 4/3 |
| B4 | 5/3 | 3/1 | 9/8 | 1 | 5/3 | 5/4 | 7/6 | 3/4 |
| B5 | 5/3 | 1/3 | 2/3 | 3/5 | 1 | 5/3 | 7/3 | 3/2 |
| B6 | 7/5 | 1/2 | 4/7 | 4/5 | 3/5 | 1 | 4/3 | 6/5 |
| B7 | 9/7 | 2/3 | 2/5 | 6/7 | 3/7 | 3/4 | 1 | 5/6 |
| B8 | 5/3 | 3/4 | 3/4 | 4/3 | 2/3 | 5/6 | 6/5 | 1 |
Step three: weight vectors are computed and a consistency check is performed.
Firstly, the consistency of the judgment matrix A is checked.
The essential condition for the N-order positive and reciprocal matrix A to be the consistency matrix is as follows: maximum eigenvalue λ of Amax＝n。
The consistency check steps are as follows:
1) calculating the maximum eigenvalue lambda of the judgment matrix Amax；
2) And (3) obtaining a consistency index:
CI-0 means complete agreement, with larger CI being more inconsistent;
3) calculating corresponding average random consistency index RI by using a random simulation averaging method, or directly simulating for multiple times to obtain an RI table;
4) calculate the consistency ratio:
5) judging that the judgment matrix A has satisfactory consistency when CR is less than 0.1; if CR is greater than or equal to 0.1, the modified judgment matrix A should be considered.
Second, a weight vector is calculated.
The weight vector is determined using the feature root method. For the consistency judgment matrix a, its normalized eigenvector corresponding to the largest eigen root is used as the weight vector W, and then AW is λ W, and W is { W ═ W {1，w2...wnAre multiplied by
The weights for each evaluation item were calculated by the Matlab program as follows table 3:
table 3 weight distribution table for each evaluation item
| Evaluation item | Weight assignment |
| Dimensional accuracy | 10％ |
| Positioning accuracy | 15％ |
| Accuracy of speed | 15％ |
| Course angle accuracy | 10％ |
| Accuracy of classification | 15％ |
| Rate of missed examination | 15％ |
| False detection rate | 10％ |
| Target tracking success rate | 10％ |
Final weighted score evaluation criteria
The ratings are given in table 4 below:
table 4 rating scale
Final weighted score calculation formula:
S＝B1*10％+B2*15％+B3*15％+B4*10％+B5*15％+B6*15％+B7*10％+B8*10％。
the method for evaluating the perception capability of the traffic participants based on the roadside perception system provided by the invention is described in detail, a specific example is applied in the method to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for evaluating the perception capability of a traffic participant based on a roadside sensing system is characterized in that a roadside truth value system and a roadside sensing system to be tested are installed at the same roadside position, and the method comprises the following steps:
the method comprises the following steps that a road side sensing system to be tested is used for collecting road side sensing data of traffic participants and truth-value vehicles;
acquiring test data of a truth-value vehicle and test data of a road side truth-value system on traffic participants;
and inputting the roadside perception data and the test data into a perception capability evaluation algorithm of the traffic participants based on timestamp matching of the roadside perception data and the test data to obtain a perception capability evaluation result of the traffic participants.
2. The method for evaluating the perception capability of the traffic participants based on the roadside sensing system of claim 1, wherein the collecting of roadside sensing data by using a true value vehicle of the roadside sensing system to be tested comprises:
a real-value vehicle passes through a sensing area within a given speed range;
the roadside sensing system that awaits measuring exports vehicle roadside perception data with time stamp, includes: location, speed, heading angle, and/or size of the vehicle.
3. The method for evaluating the perception capability of the traffic participant based on the roadside sensing system according to claim 1, wherein the collecting of roadside sensing data of the traffic participant by the roadside sensing system to be tested comprises:
the road side sensing system to be tested identifies the target number of the traffic participants passing through the sensing area and the classification number of the traffic participants passing through the sensing area in a given time interval.
4. The method for evaluating the perception capability of the traffic participant based on the roadside sensing system according to claim 1, wherein the collecting of roadside sensing data of the traffic participant by the roadside sensing system to be tested comprises:
a road side truth value system carries out statistics to obtain a track truth value;
counting the total target track number A of the video frames in a given number before and after by taking the video frames of the maximum track true value detection target number of the road side true value system as the center;
and acquiring the number B of unchanged target tracks corresponding to the same video frame of the roadside sensing system to be detected according to the timestamp.
5. The method for evaluating the perception capability of the traffic participants based on the roadside perception system according to claim 3, wherein the categories of the traffic participants comprise: automotive, pedestrian, and non-automotive.
6. The method for evaluating the perception capability of a traffic participant based on the roadside perception system according to claim 1, wherein the obtaining of the test data of the truth car comprises:
a truth vehicle outputs time-stamped test data as it passes through a sensing region within a given speed range, comprising: true vehicle positioning, speed, heading angle, and/or size.
7. The method for evaluating the perception capability of the traffic participants based on the roadside perception system as claimed in claim 3, wherein the obtaining of the test data of the roadside truth-value system on the traffic participants comprises:
the roadside truth system identifies the target number of traffic participants passing through the sensing region and the classification number of the traffic participants passing through the sensing region within the given time interval.
8. The method for evaluating the perception abilities of the traffic participants based on the roadside sensing system as claimed in claim 1, wherein the roadside sensing data and the test data are input to a traffic participant perception ability evaluation algorithm based on timestamp matching of the roadside sensing data and the test data to obtain a traffic participant perception ability evaluation result, and the method comprises the following steps:
determining the perception capability evaluation factors of the traffic participants, wherein the perception capability evaluation factors comprise the size precision, the positioning precision, the speed precision and/or the course angle precision of the motor vehicle;
and comparing and calculating roadside perception data corresponding to the evaluation factors with the test data according to the time stamp, wherein the positioning precision converts longitude and latitude into Euclidean distance to carry out result statistics.
9. The method for evaluating the perception abilities of the traffic participants based on the roadside sensing system as claimed in claim 1, wherein the roadside sensing data and the test data are input to a traffic participant perception ability evaluation algorithm based on timestamp matching of the roadside sensing data and the test data to obtain a traffic participant perception ability evaluation result, and the method comprises the following steps:
determining the perception capability evaluation factors of the traffic participants, including the classification accuracy, the omission factor and/or the false detection rate of motor vehicles, pedestrians and non-motor vehicles;
and respectively extracting road side sensing data corresponding to the evaluation factors of a plurality of time periods and the test data according to the time stamps for comparison and calculation.
10. The method for evaluating the perception abilities of the traffic participants based on the roadside sensing system as claimed in claim 4, wherein the roadside sensing data and the test data are input into a traffic participant perception ability evaluation algorithm based on timestamp matching of the roadside sensing data and the test data to obtain a traffic participant perception ability evaluation result, and the method comprises the following steps:
determining the perception capability evaluation factors of the traffic participants, including the target tracking success rate of the traffic participants;
and calculating the tracking success rate according to the target track quantity A corresponding to the track true value and the target track quantity B acquired by the road side sensing system to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111183372.9A CN113920729A (en) | 2021-10-11 | 2021-10-11 | Method for evaluating perception capability of traffic participants based on roadside perception system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111183372.9A CN113920729A (en) | 2021-10-11 | 2021-10-11 | Method for evaluating perception capability of traffic participants based on roadside perception system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113920729A true CN113920729A (en) | 2022-01-11 |
Family
ID=79239346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111183372.9A Pending CN113920729A (en) | 2021-10-11 | 2021-10-11 | Method for evaluating perception capability of traffic participants based on roadside perception system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113920729A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114550450A (en) * | 2022-02-15 | 2022-05-27 | 云控智行科技有限公司 | Method and device for verifying perception accuracy of roadside sensing equipment and electronic equipment |
| CN114596706A (en) * | 2022-03-15 | 2022-06-07 | 阿波罗智联(北京)科技有限公司 | Detection method and device of roadside sensing system, electronic equipment and roadside equipment |
| CN114792469A (en) * | 2022-04-06 | 2022-07-26 | 大唐高鸿智联科技(重庆)有限公司 | Test method, device and test equipment for sensing system |
| CN115134775A (en) * | 2022-05-25 | 2022-09-30 | 合众新能源汽车有限公司 | Data reliability testing system, method, apparatus and electronic equipment |
| CN116170347A (en) * | 2022-12-29 | 2023-05-26 | 信通院车联网创新中心(成都)有限公司 | A time-frequency performance testing method for roadside perception system of Internet of Vehicles |
| CN116229708A (en) * | 2022-12-15 | 2023-06-06 | 信通院车联网创新中心(成都)有限公司 | Perception test method of road side perception system on traffic target based on V2I |
| CN116403395A (en) * | 2022-12-15 | 2023-07-07 | 信通院车联网创新中心(成都)有限公司 | Perception test method of road side perception system on traffic event based on V2I |
| CN117198057A (en) * | 2023-10-16 | 2023-12-08 | 同济大学 | Experimental method and system for road side perception track data quality inspection |
| CN118612688A (en) * | 2024-05-31 | 2024-09-06 | 中国汽车工程研究院股份有限公司 | Automated vehicle-road collaborative deployment method and system for roadside equipment |
| CN118918707A (en) * | 2024-07-24 | 2024-11-08 | 浙江省交通运输科学研究院 | Comprehensive quality determination method for radar fusion system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627206A (en) * | 2020-05-12 | 2020-09-04 | 重庆车辆检测研究院有限公司 | Scale test evaluation method applied to vehicle-road cooperative roadside system |
| CN111797012A (en) * | 2020-06-28 | 2020-10-20 | 公安部交通管理科学研究所 | Method, device and system for testing functional application of roadside unit |
| CN112382079A (en) * | 2020-09-21 | 2021-02-19 | 广州中国科学院软件应用技术研究所 | Road side perception analog simulation method and system for vehicle-road cooperation |
| US20210099831A1 (en) * | 2019-09-30 | 2021-04-01 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method for measuring sensing range of vehicle, device and medium |
| CN112816954A (en) * | 2021-02-09 | 2021-05-18 | 中国信息通信研究院 | Road side perception system evaluation method and system based on truth value |
| CN112907955A (en) * | 2021-01-28 | 2021-06-04 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Evaluation method of vehicle-road cooperative system based on information fusion |
-
2021
- 2021-10-11 CN CN202111183372.9A patent/CN113920729A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210099831A1 (en) * | 2019-09-30 | 2021-04-01 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method for measuring sensing range of vehicle, device and medium |
| CN111627206A (en) * | 2020-05-12 | 2020-09-04 | 重庆车辆检测研究院有限公司 | Scale test evaluation method applied to vehicle-road cooperative roadside system |
| CN111797012A (en) * | 2020-06-28 | 2020-10-20 | 公安部交通管理科学研究所 | Method, device and system for testing functional application of roadside unit |
| CN112382079A (en) * | 2020-09-21 | 2021-02-19 | 广州中国科学院软件应用技术研究所 | Road side perception analog simulation method and system for vehicle-road cooperation |
| CN112907955A (en) * | 2021-01-28 | 2021-06-04 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Evaluation method of vehicle-road cooperative system based on information fusion |
| CN112816954A (en) * | 2021-02-09 | 2021-05-18 | 中国信息通信研究院 | Road side perception system evaluation method and system based on truth value |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114550450A (en) * | 2022-02-15 | 2022-05-27 | 云控智行科技有限公司 | Method and device for verifying perception accuracy of roadside sensing equipment and electronic equipment |
| CN114596706A (en) * | 2022-03-15 | 2022-06-07 | 阿波罗智联(北京)科技有限公司 | Detection method and device of roadside sensing system, electronic equipment and roadside equipment |
| CN114596706B (en) * | 2022-03-15 | 2024-05-03 | 阿波罗智联(北京)科技有限公司 | Detection method and device of road side perception system, electronic equipment and road side equipment |
| CN114792469B (en) * | 2022-04-06 | 2023-06-02 | 中信科智联科技有限公司 | Testing method and device for sensing system and testing equipment |
| CN114792469A (en) * | 2022-04-06 | 2022-07-26 | 大唐高鸿智联科技(重庆)有限公司 | Test method, device and test equipment for sensing system |
| CN115134775A (en) * | 2022-05-25 | 2022-09-30 | 合众新能源汽车有限公司 | Data reliability testing system, method, apparatus and electronic equipment |
| CN116229708A (en) * | 2022-12-15 | 2023-06-06 | 信通院车联网创新中心(成都)有限公司 | Perception test method of road side perception system on traffic target based on V2I |
| CN116403395A (en) * | 2022-12-15 | 2023-07-07 | 信通院车联网创新中心(成都)有限公司 | Perception test method of road side perception system on traffic event based on V2I |
| CN116170347A (en) * | 2022-12-29 | 2023-05-26 | 信通院车联网创新中心(成都)有限公司 | A time-frequency performance testing method for roadside perception system of Internet of Vehicles |
| CN116170347B (en) * | 2022-12-29 | 2025-02-14 | 信通院车联网创新中心(成都)有限公司 | A method for testing time-frequency performance of roadside perception system in connected vehicle network |
| CN117198057A (en) * | 2023-10-16 | 2023-12-08 | 同济大学 | Experimental method and system for road side perception track data quality inspection |
| CN118612688A (en) * | 2024-05-31 | 2024-09-06 | 中国汽车工程研究院股份有限公司 | Automated vehicle-road collaborative deployment method and system for roadside equipment |
| CN118918707A (en) * | 2024-07-24 | 2024-11-08 | 浙江省交通运输科学研究院 | Comprehensive quality determination method for radar fusion system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113920729A (en) | Method for evaluating perception capability of traffic participants based on roadside perception system | |
| Shepelev et al. | A Study of the Travel Time of Intersections by Vehicles using Computer Vision. | |
| CN113155173B (en) | Perception performance evaluation method and device, electronic device and storage medium | |
| Wang et al. | Traffic sensory data classification by quantifying scenario complexity | |
| CN108877213B (en) | Traffic accident identification method and system | |
| Asmara et al. | Prediction of traffic density using yolo object detection and implemented in raspberry pi 3b+ and intel ncs 2 | |
| CN107610464A (en) | A kind of trajectory predictions method based on Gaussian Mixture time series models | |
| CN104134349A (en) | Bus road condition processing system and method based on traffic multi-source data fusion | |
| Daraghmi et al. | Crowdsourcing-based road surface evaluation and indexing | |
| CN118072523B (en) | A big data weighing accuracy audit method based on EM algorithm | |
| Wang et al. | Vehicle reidentification with self-adaptive time windows for real-time travel time estimation | |
| Vitianingsih et al. | Spatial analysis model for traffic accident-prone roads classification: A proposed framework | |
| CN114023061B (en) | Traffic flow acquisition capacity evaluation method based on vehicle-road cooperative roadside sensing system | |
| Kussl et al. | Advancing vehicle classification: A novel framework for type, model, and fuel identification using nonvisual sensor systems for seamless data sharing | |
| CN114066288B (en) | Intelligent data center-based emergency detection method and system for operation road | |
| CN115809768A (en) | Smart city information resource display system and method | |
| CN110704789B (en) | Population dynamic measurement and calculation method and system based on 'urban superconcephalon' computing platform | |
| CN117456482B (en) | Abnormal event identification method and system for traffic monitoring scene | |
| CN118918707A (en) | Comprehensive quality determination method for radar fusion system | |
| CN116881778B (en) | Intelligent auxiliary teaching system safety warning and protection function testing system and method | |
| CN117671971A (en) | Vehicle speed control method, system and device based on V2X and feedforward neural network | |
| Stipancic et al. | Massive GNSS data for road safety analysis: Comparing crash models for several Canadian cities and data sources | |
| Zhang et al. | Autonomous vehicles as a sensor: Simulating data collection process | |
| CN117132958A (en) | Road element identification method and related device | |
| Shrinivas et al. | Integrating Machine Learning in Pedestrian Forensics: A Comprehensive Tool for Analysing Pedestrian Collisions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220111 |
|
| RJ01 | Rejection of invention patent application after publication |