CN117198057A - Experimental method and system for road side perception track data quality inspection - Google Patents
Experimental method and system for road side perception track data quality inspection Download PDFInfo
- Publication number
- CN117198057A CN117198057A CN202311335369.3A CN202311335369A CN117198057A CN 117198057 A CN117198057 A CN 117198057A CN 202311335369 A CN202311335369 A CN 202311335369A CN 117198057 A CN117198057 A CN 117198057A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- truth
- road side
- evaluation
- 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 83
- 238000007689 inspection Methods 0.000 title claims abstract description 35
- 238000002474 experimental method Methods 0.000 title claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims abstract description 73
- 238000013441 quality evaluation Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 238000001303 quality assessment method Methods 0.000 claims description 4
- 238000012854 evaluation process Methods 0.000 claims description 3
- 238000012805 post-processing Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 230000006855 networking Effects 0.000 abstract description 4
- 230000009897 systematic effect Effects 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000010426 asphalt Substances 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G08G1/0125—Traffic data processing
-
- 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
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
-
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an experimental method and system for road side perception track data quality inspection, comprising the following steps: s1, checking the composition of equipment at a road side to be checked and judging the quality of track data, and determining the checking and judging requirement of the quality check and judging of the track data and an evaluating system of the quality check and judging of the track data; s2, selecting and placing a vehicle-mounted truth unit and a video truth unit, and simultaneously collecting track perception data of the vehicle-mounted truth unit and collecting perception data of the video truth unit; s3, comparing the perceived track data of the road side equipment to be inspected with the data true value, and calculating accuracy evaluation and continuity evaluation indexes of the track data; and S4, evaluating and grading the perceived track data quality of the road side to be evaluated according to grading standards, generating a data quality report and giving application suggestions. According to the invention, the systematic, normalized and comprehensive road side perception track data quality evaluation requirements under the intelligent networking environment can be met, and the road side perception data system level application and road side perception facility performance monitoring are guided.
Description
Technical Field
The invention relates to the technical field of traffic data quality assessment, in particular to an experimental method and system for road side perception track data quality assessment.
Background
Along with the rapid development of intelligent expressways, a large number of edge computing devices can be deployed on the road side of the expressways, and intelligent sensors such as high-definition cameras, millimeter wave radars and laser radars can acquire all-time-space road traffic perception track data through multi-source data fusion and target recognition tracking, so that the possibility is provided for micro driving behavior perception, accurate recognition of traffic states, online parallel simulation deduction and the like. However, the quality of the road traffic perception trajectory data directly determines the effects of analysis, evaluation and management and control measures of the traffic system, and how to evaluate the quality of the road traffic perception trajectory data becomes a difficult problem to be broken under the rapid development of intelligent highway and vehicle road coordination.
The past study mainly considers that the quality evaluation of the road side perceived track data is to compare and evaluate the truth value data and the road side perceived track data under the same time and space by using high-precision perception equipment, and provides a series of related track data quality evaluation indexes. However, when the perceived trajectory data is put into practical use, accuracy and continuity of the trajectory data in spatial coordinates need to be considered. Most of the researches are limited by limited evaluation equipment, imperfect evaluation system and the like, the track data quality evaluation process lacks an evaluation system comprising accuracy and continuity, and reliable quality evaluation indexes and results are difficult to obtain. The quality inspection and evaluation of the current road side perceived track data is difficult to meet the systematic, normalized and comprehensive road side perceived track data quality inspection and evaluation requirements in the intelligent networking environment.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide an experimental method and an experimental system for detecting and evaluating the quality of road side perception track data, which can meet the systematic, normalized and comprehensive road side perception track data quality detection requirements in an intelligent networking environment and guide the road side perception data system level application and road side perception facility performance monitoring. To achieve the above objects and other advantages and in accordance with the purpose of the invention, there is provided an experimental system for road side perception trajectory data quality inspection, comprising:
the system comprises a to-be-inspected road side sensing unit, a to-be-inspected road side sensing system and a track data acquisition system;
the vehicle truth value information is collected through a sensor for selecting and arranging a vehicle-mounted truth value unit, and the information comprises vehicle truth value track information;
collecting road side video data and vehicle information by selecting and arranging a video truth value unit;
the method comprises the steps of collecting data collected by a road side sensing unit to be inspected, a vehicle-mounted truth unit and a video truth unit through a data recording module;
and calculating a perceived track data quality evaluation index of the road side to be evaluated through a quality evaluation module, grading the data quality, generating a track data quality report and giving an application suggestion.
Preferably, the vehicle-mounted truth unit comprises a truth vehicle, an inertial integrated navigation subunit, a vehicle-mounted perception subunit and a data acquisition subunit, wherein the inertial integrated navigation subunit is arranged on the truth vehicle;
the inertial integrated navigation subunit comprises an inertial navigation element and a GNSS positioning element, and the size, the position, the speed and the course angle true value information of the vehicle are obtained through the inertial navigation element and the GNSS positioning element;
the vehicle-mounted sensing subunit comprises a vehicle-mounted laser radar and a millimeter wave radar;
the data acquisition subunit is used for acquiring data from the inertial integrated navigation subunit and the vehicle-mounted sensing subunit, acquiring positioning coordinates of the truth vehicle, relative positioning coordinates of surrounding vehicles, speed and course angle as reference truth data, and evaluating the quality of the road side sensing data.
Preferably, the video truth unit comprises video sensing equipment and an offline processing server, the video sensing equipment collects video data and transmits the video data to the offline processing server for post-processing through a collection host, and the corresponding relation between each vehicle in the range of the road side equipment to be checked and evaluated and the road side sensing track is determined in a manual checking mode and used as reference truth data to evaluate the quality of the road side sensing data;
in the evaluation process, the road side sensing unit to be evaluated and the vehicle-mounted truth unit or the video truth unit synchronously acquire data and transmit the data to the data recording module.
An experimental method for road side perception track data quality inspection comprises the following steps:
s1, checking the composition of equipment at a road side to be checked and judging the quality of track data, and determining the checking and judging requirement of the quality check and judging of the track data and an evaluating system of the quality check and judging of the track data;
s2, selecting and placing a vehicle-mounted truth unit and a video truth unit, and simultaneously collecting track perception data of the vehicle-mounted truth unit and collecting perception data of the video truth unit;
s3, comparing the perceived track data of the road side equipment to be inspected with the data true value, and calculating accuracy evaluation and continuity evaluation indexes of the track data;
and S4, evaluating and grading the perceived track data quality of the road side to be evaluated according to grading standards, generating a data quality report and giving application suggestions.
Preferably, in step S1, the hardware configuration including the device, the detection accuracy, the frequency and the placement requirements are checked;
determining the evaluation requirement of the track data quality evaluation, wherein the evaluation requirement comprises an evaluation road requirement and an evaluation environment requirement;
the evaluation dimension in the evaluation system comprises track data accuracy evaluation and track data continuity evaluation, and the specific evaluation index is determined according to actual scene requirements.
Preferably, the step S2 specifically includes the following steps:
s21, selecting a proper truth vehicle according to the main vehicle type of the road to be inspected and evaluated, installing an inertial integrated navigation subunit and a vehicle-mounted sensing subunit on the body of the truth vehicle, calibrating the inertial integrated navigation subunit and the vehicle-mounted sensing subunit, and carrying out unified time service with sensing facilities on the road to be inspected and evaluated;
s22, sequentially controlling the speed of the vehicle to be 20km/h, 40km/h, 60km/h and 80km/h in the perception range of the to-be-inspected evaluation sensor, and respectively driving the vehicle under the scenes of low road traffic saturation (less than or equal to 0.3), medium road traffic saturation (0.3-0.7) and high road traffic saturation (more than or equal to 0.7), wherein the vehicle-mounted truth unit and the to-be-inspected evaluation sensor synchronously and repeatedly acquire inspection data, so that the truth vehicle completes at least 1 lane change behavior in the facility perception range and covers data of driving of different lanes in a road;
s23, after the detection and evaluation data acquisition is completed, determining road side rail data corresponding to the truth vehicle under each time of data acquisition from the road side perception track data to be detected, carrying out space-time alignment on the vehicle-mounted truth unit and the road side sensor to be detected, extracting the truth data of the vehicle size and the position coordinates of each time of the truth vehicle based on the road side rail data time stamp to be detected, and inputting the data into the data recording module.
Preferably, the step S3 specifically includes the following steps:
s31, selecting and placing a video truth unit according to the track data quality inspection requirements, so that the video truth unit obtains video data of roads in the range of the road side facility to be inspected, and adjusting the data acquisition frequency and accuracy according to the track data quality inspection requirements, wherein the video truth unit and the road side rail sensing equipment to be inspected synchronously acquire track sensing data;
s32, synchronously acquiring evaluation data under the scenes of low road traffic saturation (less than or equal to 0.3), medium road traffic saturation (0.3-0.7) and high road traffic saturation (more than or equal to 0.7) by the road side equipment to be evaluated and the video truth unit, wherein the data acquisition time lasts for 15 minutes under each traffic scene;
s33, after the acquisition of the inspection and evaluation data is completed, the video data acquired through the video truth unit is used for manually counting the corresponding relation between the real vehicles in the range of the equipment at the road side to be inspected and the ID marks of the vehicles with the perceived track data at the road side under each scene, counting the track number of tracking continuous, incremental inspection and missed inspection in the perceived track data at the road side to be inspected, calculating the track length of the tracking correct track, and inputting the data into the data recording module.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the vehicle-mounted truth system is selected and placed, and track perception data of the vehicle-mounted truth system are collected to participate in accuracy evaluation of the road side perception track data to be inspected; the video truth system is selected and placed, the perceived data of the video truth system is collected to participate in the continuity evaluation of the perceived track data of the road side to be evaluated, and the perceived track data of the road side is comprehensively evaluated by combining two important aspects of accuracy and continuity. The invention can meet the systematic, normalized and comprehensive road side perception track data quality inspection requirements under the intelligent networking environment, and guide road side perception data system level application and road side perception facility performance monitoring.
Drawings
FIG. 1 is a schematic flow chart of an experimental method and system for evaluating the quality of road-side-oriented perceived trajectory data according to the present invention;
FIG. 2 is a schematic diagram of a system architecture of an experimental method and system for road side perception trajectory data quality assessment according to the present invention;
fig. 3 is a schematic diagram of evaluation of accuracy of track data of the experimental method and system for evaluating quality of perceived track data of road side according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-3, an experimental method for road side perception trajectory data quality inspection comprises the following steps:
s1, checking the composition of equipment at a road side to be checked and judging the quality of track data, and determining the checking and judging requirement of the quality check and judging of the track data and an evaluating system of the quality check and judging of the track data; checking hardware constitution, detection precision, frequency and placement requirements of equipment; determining the evaluation requirement of the track data quality evaluation, wherein the evaluation requirement comprises an evaluation road requirement and an evaluation environment requirement; the evaluation dimension in the evaluation system comprises track data accuracy evaluation and track data continuity evaluation, and the specific evaluation index is determined according to actual scene requirements. Wherein the evaluation road should satisfy the following conditions:
(1) The road is straight and smooth, the road surface condition is good, and the bidirectional lanes are at least two lanes;
(2) The pavement is made of asphalt or concrete, is flat and free of obvious jolts, pits, bulges and cracks, and meets the related requirements of JTG/T F20;
(3) The arrangement of the lane lines should meet the related requirements of GB 5768.3, the color should be white or yellow, the line type should be solid line or broken line, the lane lines should be clear and complete, and no damage or shielding exists.
The evaluation environment should satisfy the following conditions:
(1) The temperature of the inspection environment is-20 ℃ to 60 ℃ and the relative humidity is 25 percent to 75 percent;
(2) The severe weather conditions of snow fall, hail and dust emission are avoided in the evaluation environment, and the horizontal visibility is more than 500m; the inspection environment is clear and no barrier is blocked, so that the high-precision positioning requirement of the vehicle is met;
(3) The evaluation environment ensures the coverage of wireless signals, has no signals with strong interference to communication, and meets the normal requirements of wireless communication and data transmission.
S2, selecting and placing a vehicle-mounted truth unit and a video truth unit, and simultaneously collecting track perception data of the vehicle-mounted truth unit and collecting perception data of the video truth unit;
when the vehicle truth value list is selected and placed: selecting a proper truth vehicle according to the main vehicle type of the road to be inspected, installing an inertial integrated navigation subunit and a vehicle-mounted sensing subunit on the body of the truth vehicle, calibrating the inertial integrated navigation subunit and the vehicle-mounted sensing subunit, and carrying out unified time service with sensing facilities on the road to be inspected;
the vehicle-mounted truth unit and the road side sensor to be checked synchronously and repeatedly acquire checking and evaluating data, and the data acquisition process is repeated for at least 3 times under each vehicle speed scene, so that the truth vehicle completes at least 1 lane changing behavior in the facility perception range and covers data of running of different lanes in a road;
after the evaluation data are acquired, the road side rail data corresponding to the true value vehicle under each data acquisition are determined from the road side perception track data to be evaluated. Furthermore, the sensing track data of the vehicle-mounted truth value unit and the sensing track data of the evaluation road side to be tested are subjected to space-time alignment. Aiming at space alignment, a sensor coordinate system of a vehicle-mounted truth unit and an estimated road side track sensing coordinate system are obtained, the sensor coordinate system of the vehicle-mounted truth unit is changed into a world coordinate system according to vehicle parameters, and then the sensor coordinate system of the vehicle-mounted truth unit is aligned with the estimated road side track sensing coordinate system by utilizing absolute position information of a sensor; aiming at time alignment, the sensing system time of the vehicle-mounted truth unit is aligned with the road side data system time through manual calibration parameters, and the data sampling time is synchronized, so that the time comparability of the vehicle-mounted road data is ensured. And after the data time-space alignment is completed, extracting the truth data of the vehicle size, the position coordinates, the relative position coordinates, the speed and the course angle at each moment of the truth vehicle based on the side rail data time stamp of the road to be inspected, and inputting the truth data into the data recording module.
Select and place video truth unit: synchronously acquiring perception data of a video truth system according to a data truth value requirement, synchronously carrying out data processing, and enabling extracted vehicle data and a video data input data recording module to participate in continuity evaluation of perception track data of a road side to be inspected, wherein the method specifically comprises the following steps: selecting a proper video truth system to be arranged near the road side facility to be inspected according to scene conditions, ensuring that the video truth system can acquire video data of roads in the range of the road side facility to be inspected, adjusting data acquisition frequency and precision according to track data quality inspection requirements, and synchronously acquiring track perception data with track side rail perception equipment to be inspected;
the road side equipment to be inspected and the video truth system synchronously acquire inspection data in scenes of low road traffic saturation (less than or equal to 0.3), medium road traffic saturation (0.3-0.7) and high road traffic saturation (more than or equal to 0.7), wherein the data acquisition time lasts for 15 minutes in each traffic scene;
after the acquisition of the inspection and evaluation data is completed, the video data acquired by the video truth system is utilized to manually count the corresponding relation between the real vehicles in the range of the equipment at the road side to be inspected and the ID marks of the vehicles of the road side perception track data in each scene, count the track number of tracking continuous, incremental inspection and omission inspection in the road side perception track data to be inspected, calculate and track length correctly, and input the data into the data recording module.
S3, comparing the perceived track data of the road side equipment to be inspected with the data true value, and calculating accuracy evaluation and continuity evaluation indexes of the track data; and calculating an accuracy index of the road side sensing track data to be inspected by using the sensing data of the vehicle-mounted truth value unit, calculating a continuity index of the road side sensing track data to be inspected by using the sensing data of the video truth value unit, and taking an average value of index evaluation results obtained by collecting and calculating each time under different inspection scenes.
And S4, after calculating the index, evaluating and grading the perceived track data quality of the road side to be evaluated according to the grading standard according to the perceived track data quality evaluation index condition, generating a data quality report and giving an application suggestion.
The specific track data quality evaluation index in step S4 specifically includes the following track data accuracy and track data continuity parts:
in the quality inspection and evaluation of road side perception track data, the accuracy refers to the accuracy degree of road side perception facilities for the perception of the size, the pose and the speed information of a vehicle target, and the accuracy degree comprises five evaluation indexes including a vehicle size error, a vehicle absolute positioning error, a vehicle relative positioning error, a vehicle speed error and a vehicle course angle error:
(1) The vehicle size error refers to the average absolute deviation between the real size of the vehicle and the road side perceived vehicle size at the corresponding moment, and the calculation formula is as follows:
in E s Is a vehicle size error index (m); (l) v (s),w v (s),h v (s)) is the true value (m) of the length, width and height of the vehicle in the time of data acquisition of the s times; (l) r (s,i),w r (s,i),h r (s, i)) is the length, width and height (m) of the road side perception vehicle at the i time when the s-th data are acquired.
(2) The absolute positioning error of the vehicle refers to the average absolute deviation between the true value of the position coordinate of the central point of the vehicle and the position coordinate of the road side perception vehicle at the corresponding moment, and the calculation formula is as follows:
in E pa An absolute positioning error index (m) for the vehicle; (x) v (s,i),y v (s, i)) is true position coordinates of a center point of the vehicle at the moment i during the acquisition of the time data of the s th time; (x) r (s,i),y r (s, i)) is vehicle position coordinates perceived by the road side at the i time point when the s-th data is acquired.
(3) The vehicle relative positioning error refers to the average absolute deviation between the true value of the relative position coordinates of the vehicle and all surrounding vehicles and the relative position coordinates of the road side sensing vehicle at the corresponding moment, and the calculation formula is as follows:
in E pr A relative positioning error index (m) of the vehicle;the true value of the relative position coordinates of the surrounding vehicles j and the center true value vehicle at the ith moment in the s-th data acquisition; />Sensing the relative position coordinates of the vehicle j and the central vehicle at the ith moment in the process of collecting the ith data; r is (r) s The number of vehicles around the center truth vehicle at the time of data acquisition of the s-th data.
(4) The vehicle speed error refers to the average absolute deviation between the actual vehicle speed and the road side perceived vehicle speed at the corresponding moment, and the calculation formula is as follows:
wherein is E v Is a vehicle speed error index (m/s); v v (s, i) is a true value (m/s) of the speed of the vehicle at the i time when the s-th data is acquired; v r (s, i) is the vehicle speed (m/s) perceived by the road side at the i-th moment in the s-th data acquisition.
(5) The vehicle course angle error refers to the average absolute deviation between the actual course angle of the vehicle and the road side perceived vehicle course angle at the corresponding moment, and the calculation formula is as follows:
in E θ Is a vehicle heading angle error index (°);the true value (°) of the heading angle of the vehicle at the i time when the data are acquired at the s time; θ r (s, i) is the road side perceived vehicle course angle (°) at the i-th moment in the s-th data acquisition.
In the quality inspection and evaluation of road side perception track data, the track data continuity refers to the degree of continuity of tracks in the process of tracking vehicle targets by a road side perception facility, and comprises two evaluation indexes of multi-target tracking continuity and track space-time continuity:
(1) The multi-target tracking continuity refers to the average value of the ratio of the number of continuous vehicle tracks to the total quantity of perceived data of the road sides of the vehicle tracks in the time and space range corresponding to the evaluation experiment, and the calculation formula is as follows:
c in the formula mt Tracking a continuity index (%) for multiple targets; TP(s) is the number of continuous vehicle tracks tracked in road side perception data during the s-th data acquisition; FN(s) is the number of missed vehicle tracks in road side perception data during the s-th data acquisition; FP(s) is the number of vehicle tracks detected in road side perception data during the s-th data acquisition.
(2) Track space-time continuity refers to the average value of the ratio of the track length of a continuously tracked road side sensing vehicle to the length of the maximum tracking range of a road side sensing facility in the time and space range corresponding to the evaluation experiment, and the calculation formula is as follows:
c in the formula st Is a track space-time continuity index (%); l (L) r (s, i) is the length of the road side perception vehicle track i continuously tracked during the s-th data acquisition; l (L) v The length of the range is tracked for the maximum of the roadside awareness facilities.
In step S4, the track data quality evaluation grading criteria include grading and index requirements:
in order to make the roadside perception system better serve different application scenarios, the roadside perception data quality requirements can be divided into three perception levels (perception levels). The different sensing levels are divided on the basis of:
(1) Perception level 1 (SL 1): the perceived data quality grade facing the platform data class application, the perceived data information of the vehicle track road side conforming to the grade is complete, the target tracking is basically accurate and continuous, and the corresponding traffic data statistics, traffic event management and related traffic control class application can be supported;
(2) Perception level 2 (SL 2): the perceived data quality grade facing the application of the auxiliary driving class, the perceived data of the road side of the vehicle track conforming to the grade should keep higher accuracy and integrity, and the perceived data can support and provide real-time road traffic information, risk early warning information and the like to assist the driver to apply the field decision class;
(3) Perception level 3 (SL 3): the perceived data quality grade of the vehicle track road side application facing the vehicle-road cooperative automatic driving class is used for providing real-time, accurate and complete vehicle motion information for an automatic driving system, realizing the beyond-the-vehicle visual range perception function and supporting the vehicle automatic driving system to apply decision classes.
The requirements of different sensing grades for various data quality evaluation indexes are shown in table 2. The corresponding perception level can be calculated according to each index, and corresponding perception data application suggestions are given according to the perception level and the actual requirements of the intelligent road scene and the table 3.
Table 2: quality evaluation index classification requirement
Table 3: perceptual data classification and application function comparison reference
In order to realize the above-mentioned evaluation method, a quality evaluation system for road side perception track data is provided, comprising: the road side sensing unit to be checked and evaluated;
the vehicle truth value information is collected through a sensor for selecting and arranging a vehicle-mounted truth value unit, and the information comprises vehicle truth value track information;
collecting road side video data and vehicle information by selecting and arranging a video truth value unit;
the method comprises the steps of collecting data collected by a road side sensing unit to be inspected, a vehicle-mounted truth unit and a video truth unit through a data recording module;
and calculating a perceived track data quality evaluation index of the road side to be evaluated through a quality evaluation module, grading the data quality, generating a track data quality report and giving an application suggestion.
Further, the vehicle-mounted truth unit comprises a truth vehicle, an inertial integrated navigation subunit, a vehicle-mounted perception subunit and a data acquisition subunit, wherein the inertial integrated navigation subunit is arranged on the truth vehicle;
the inertial integrated navigation subunit comprises an inertial navigation element and a GNSS positioning element, and the size, the position, the speed and the course angle true value information of the vehicle are obtained through the inertial navigation element and the GNSS positioning element;
the vehicle-mounted sensing subunit comprises a vehicle-mounted laser radar and a millimeter wave radar; the number of high-precision sensing sensors mounted on the true value vehicle is not less than two, the relative position coordinates of the vehicle targets in the 360-degree range around the vehicle can be sensed, and the sensing distance is more than or equal to 50m.
The data acquisition subunit is used for acquiring data from the inertial integrated navigation subunit and the vehicle-mounted sensing subunit, acquiring positioning coordinates of the truth vehicle, relative positioning coordinates of surrounding vehicles, speed and course angle as reference truth data, and evaluating the quality of the road side sensing data.
The data format and corresponding data accuracy requirements derived by the vehicle-mounted truth-value sensing system are shown in table 4.
Table 4: data output format and accuracy requirement of vehicle-mounted truth system
Further, the video truth unit comprises video sensing equipment and an offline processing server, the video sensing equipment collects video data and transmits the video data to the offline processing server for post-processing through a collection host, and the corresponding relation between each vehicle in the range of the road side equipment to be checked and evaluated and the road side sensing track is determined in a manual checking mode and used as reference truth data to evaluate the quality of the road side sensing data;
and in the evaluation process, the road side sensing unit to be evaluated and the vehicle-mounted truth unit or the video truth unit synchronously acquire data and transmit the data to the data recording module, and an evaluation person checks the acquired data truth value and calculates each quality evaluation index in the quality evaluation module, and generates a data quality evaluation report.
The number of devices and the scale of processing described herein are intended to simplify the description of the invention, and applications, modifications and variations of the invention will be apparent to those skilled in the art.
Although embodiments of the present invention have been disclosed above, it is not limited to the details and embodiments shown and described, it is well suited to various fields of use for which the invention would be readily apparent to those skilled in the art, and accordingly, the invention is not limited to the specific details and illustrations shown and described herein, without departing from the general concepts defined in the claims and their equivalents.
Claims (7)
1. The utility model provides an experimental system for road side perception orbit data quality inspection, its characterized in that includes:
the road side sensing unit to be checked and evaluated;
the vehicle truth value information is collected through a sensor for selecting and arranging a vehicle-mounted truth value unit, and the information comprises vehicle truth value track information;
collecting road side video data and vehicle information by selecting and arranging a video truth value unit;
the method comprises the steps of collecting data collected by a road side sensing unit to be inspected, a vehicle-mounted truth unit and a video truth unit through a data recording module;
and calculating a perceived track data quality evaluation index of the road side to be evaluated through a quality evaluation module, grading the data quality, generating a track data quality report and giving an application suggestion.
2. The experimental system for road side perception trajectory data quality inspection and evaluation according to claim 1, wherein the vehicle-mounted truth unit comprises a truth vehicle, an inertial integrated navigation subunit arranged on the truth vehicle, a vehicle-mounted perception subunit and a data acquisition subunit;
the inertial integrated navigation subunit comprises an inertial navigation element and a GNSS positioning element, and the size, the position, the speed and the course angle true value information of the vehicle are obtained through the inertial navigation element and the GNSS positioning element;
the vehicle-mounted sensing subunit comprises a vehicle-mounted laser radar and a millimeter wave radar;
the data acquisition subunit is used for acquiring data from the inertial integrated navigation subunit and the vehicle-mounted sensing subunit, acquiring positioning coordinates of the truth vehicle, relative positioning coordinates of surrounding vehicles, speed and course angle as reference truth data, and evaluating the quality of the road side sensing data.
3. The experimental system for road side perception trajectory data quality inspection and evaluation as claimed in claim 2, wherein the video truth unit comprises video perception equipment and an offline processing server, the video perception equipment collects video data and transmits the video data to the offline server for post-processing through a collection host, each vehicle in the range of the road side equipment to be inspected and the corresponding relation between the vehicle and the road side perception trajectory are determined through a manual checking mode, and the video perception equipment evaluates the road side perception data quality as reference truth data;
in the evaluation process, the road side sensing unit to be evaluated and the vehicle-mounted truth unit or the video truth unit synchronously acquire data and transmit the data to the data recording module.
4. An experimental method for road side perception trajectory data quality assessment according to any one of claims 1-3, comprising the steps of:
s1, checking the composition of equipment at a road side to be checked and judging the quality of track data, and determining the checking and judging requirement of the quality check and judging of the track data and an evaluating system of the quality check and judging of the track data;
s2, selecting and placing a vehicle-mounted truth unit and a video truth unit, and simultaneously collecting track perception data of the vehicle-mounted truth unit and collecting perception data of the video truth unit;
s3, comparing the perceived track data of the road side equipment to be inspected with the data true value, and calculating accuracy evaluation and continuity evaluation indexes of the track data;
and S4, evaluating and grading the perceived track data quality of the road side to be evaluated according to grading standards, generating a data quality report and giving application suggestions.
5. The experimental method for road side perception trajectory data quality inspection and assessment according to claim 4, wherein in step S1, the hardware composition, detection accuracy, frequency and placement requirements of the device are inspected;
determining the evaluation requirement of the track data quality evaluation, wherein the evaluation requirement comprises an evaluation road requirement and an evaluation environment requirement;
the evaluation dimension in the evaluation system comprises track data accuracy evaluation and track data continuity evaluation, and the specific evaluation index is determined according to actual scene requirements.
6. The method for evaluating the quality of road-side-oriented perceived trajectory data according to claim 4, wherein the step S2 comprises the steps of:
s21, selecting a proper truth vehicle according to the main vehicle type of the road to be inspected and evaluated, installing an inertial integrated navigation subunit and a vehicle-mounted sensing subunit on the body of the truth vehicle, calibrating the inertial integrated navigation subunit and the vehicle-mounted sensing subunit, and carrying out unified time service with sensing facilities on the road to be inspected and evaluated;
s22, sequentially controlling the speed of the vehicle to be 20km/h, 40km/h, 60km/h and 80km/h in the perception range of the to-be-inspected evaluation sensor, and respectively driving the vehicle under the scenes of low road traffic saturation (less than or equal to 0.3), medium road traffic saturation (0.3-0.7) and high road traffic saturation (more than or equal to 0.7), wherein the vehicle-mounted truth unit and the to-be-inspected evaluation sensor synchronously and repeatedly acquire inspection data, so that the truth vehicle completes at least 1 lane change behavior in the facility perception range and covers data of driving of different lanes in a road;
s23, after the detection and evaluation data acquisition is completed, determining road side rail data corresponding to the truth vehicle under each time of data acquisition from the road side perception track data to be detected, carrying out space-time alignment on the vehicle-mounted truth unit and the road side sensor to be detected, extracting the truth data of the vehicle size and the position coordinates of each time of the truth vehicle based on the road side rail data time stamp to be detected, and inputting the data into the data recording module.
7. The method for evaluating the quality of road-side-oriented perceived trajectory data according to claim 4, wherein the step S3 comprises the steps of:
s31, selecting and placing a video truth unit according to the track data quality inspection requirements, so that the video truth unit obtains video data of roads in the range of the road side facility to be inspected, and adjusting the data acquisition frequency and accuracy according to the track data quality inspection requirements, wherein the video truth unit and the road side rail sensing equipment to be inspected synchronously acquire track sensing data;
s32, synchronously acquiring evaluation data under the scenes of low road traffic saturation (less than or equal to 0.3), medium road traffic saturation (0.3-0.7) and high road traffic saturation (more than or equal to 0.7) by the road side equipment to be evaluated and the video truth unit, wherein the data acquisition time lasts for 15 minutes under each traffic scene;
s33, after the acquisition of the inspection and evaluation data is completed, the video data acquired through the video truth unit is used for manually counting the corresponding relation between the real vehicles in the range of the equipment at the road side to be inspected and the ID marks of the vehicles with the perceived track data at the road side under each scene, counting the track number of tracking continuous, incremental inspection and missed inspection in the perceived track data at the road side to be inspected, calculating the track length of the tracking correct track, and inputting the data into the data recording module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311335369.3A CN117198057A (en) | 2023-10-16 | 2023-10-16 | Experimental method and system for road side perception track data quality inspection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311335369.3A CN117198057A (en) | 2023-10-16 | 2023-10-16 | Experimental method and system for road side perception track data quality inspection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117198057A true CN117198057A (en) | 2023-12-08 |
Family
ID=88983504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311335369.3A Pending CN117198057A (en) | 2023-10-16 | 2023-10-16 | Experimental method and system for road side perception track data quality inspection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117198057A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113505687A (en) * | 2021-07-08 | 2021-10-15 | 北京星云互联科技有限公司 | Equipment test method, device, electronic equipment, system and storage medium |
-
2023
- 2023-10-16 CN CN202311335369.3A patent/CN117198057A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113505687A (en) * | 2021-07-08 | 2021-10-15 | 北京星云互联科技有限公司 | Equipment test method, device, electronic equipment, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110853393B (en) | Intelligent network vehicle test field data acquisition and fusion method and system | |
| WO2022206978A1 (en) | Roadside millimeter-wave radar calibration method based on vehicle-mounted positioning apparatus | |
| Sochor et al. | Comprehensive data set for automatic single camera visual speed measurement | |
| CN112700470B (en) | Target detection and track extraction method based on traffic video stream | |
| CN110033479A (en) | Traffic flow parameter real-time detection method based on Traffic Surveillance Video | |
| CN113419244A (en) | Vehicle track splicing method based on millimeter wave radar data | |
| CN105608431A (en) | Vehicle number and traffic flow speed based highway congestion detection method | |
| JP2019196680A (en) | Pavement information gathering inspection system, pavement information gathering inspection method, and program | |
| CN103499337A (en) | Vehicle-mounted monocular camera distance and height measuring device based on vertical target | |
| CN117198057A (en) | Experimental method and system for road side perception track data quality inspection | |
| CN114357019A (en) | Method for monitoring data quality of road side sensing unit in intelligent networking environment | |
| Sochor et al. | Brnocompspeed: Review of traffic camera calibration and comprehensive dataset for monocular speed measurement | |
| CN115527364B (en) | Traffic accident tracing method and system based on radar data fusion | |
| CN114648231A (en) | Quality evaluation method for road-side data of vehicle-road cooperation | |
| CN114926984B (en) | Real-time traffic conflict collection and road safety evaluation method | |
| CN113255469A (en) | Method and device for measuring road occupancy of traffic monitoring scene | |
| CN114858214A (en) | Urban road performance monitoring system | |
| CN110363988A (en) | A kind of computing system and method for intersection vehicles traffic efficiency | |
| CN116631187B (en) | Intelligent acquisition and analysis system for case on-site investigation information | |
| CN116818397B (en) | Quick load test method and system for small and medium span bridges based on machine vision | |
| CN113642845A (en) | Quality evaluation method of road traffic perception track data | |
| Grone | An evaluation of non-intrusive traffic detectors at the NTC/NDOR detector test bed | |
| CN116229708A (en) | Perception test method of road side perception system on traffic target based on V2I | |
| CN105303837A (en) | Method and system for detecting following behavior characteristic parameter of driver | |
| CN116635739A (en) | Road side millimeter wave radar calibration method based on vehicle-mounted positioning device |
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 |