Data resource collecting and labeling method based on big data mining

Abstract

The invention provides a data resource collecting and labeling method based on big data mining, and relates to the technical field of data collecting and labeling. The method comprises the specific implementation steps of collecting multi-view traffic images, traffic flow data and vehicle speed data of a target road section in real time, preprocessing the multi-view traffic images, and dividing the multi-view traffic images into traffic image groups according to a time sequence; secondly, calculating a traffic concentration index in the first view angle traffic image, identifying a blocking region, mapping the blocking region to another view angle traffic image, and performing congestion labeling; then, through projection of an overlapped detection frame and traffic element point cloud calculation, a traffic accident is marked in combination with a vehicle sag detection model; and finally, environment consistency verification and annotation conflict verification are carried out on a congestion annotation result to ensure the accuracy and integrity of the data. According to the method, the processing accuracy of the traffic data is improved, effective support is provided for traffic management and decision making, and the operation efficiency of an intelligent traffic system is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of data collection and annotation, and in particular to a data resource collection and annotation method based on big data mining. Background Art

[0002] With the acceleration of urbanization and the increase in population mobility, problems such as traffic congestion and traffic accidents have become increasingly prominent, bringing huge challenges to urban traffic management. As an important part of modern traffic management, the intelligent transportation system can achieve real-time monitoring and intelligent management of traffic flow, road conditions and traffic facilities through advanced technologies such as big data, the Internet of Things and artificial intelligence. In the intelligent transportation system, the collection and annotation of data resources play a vital role. Through sensors, cameras and other equipment, multi-dimensional data such as traffic flow, vehicle speed and road conditions are collected in real time and accurately annotated, which can not only realize real-time monitoring of traffic flow, but also be applied to traffic prediction, accident analysis and emergency response.

[0003] At present, existing technologies only focus on traffic element annotation (such as vehicles, pedestrians, traffic signs and traffic lights) based on traffic image data, ignoring the impact of traffic flow and traffic accidents on traffic conditions. This single data annotation method limits the comprehensive understanding of complex traffic scenes, resulting in many traffic congestion events and traffic accidents not being marked, making the intelligent transportation system ineffective in traffic management and accident prevention.

[0004] Therefore, a data resource collection and annotation method based on big data mining is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a data resource collection and annotation method based on big data mining, which is used to collect and annotate traffic data. In order to solve the problems existing in the prior art, the present invention collects multi-perspective traffic images, traffic flow data and speed data of the target road section in real time, and pre-processes the multi-perspective traffic images, and divides them into traffic image groups in chronological order; secondly, calculates the traffic concentration index in the first-perspective traffic image and identifies the blocked area, maps the blocked area to the traffic image of another perspective, and performs congestion annotation; then, through the projection of overlapping detection boxes and traffic element point cloud computing, combined with the vehicle sag detection model, the traffic accidents are annotated; finally, the congestion annotation results are subjected to environmental consistency verification and annotation conflict verification to ensure the accuracy and integrity of the data. This method improves the processing accuracy of traffic data, provides effective support for traffic management and decision-making, and optimizes the operating efficiency of the intelligent transportation system.

[0006] A data resource collection and annotation method based on big data mining, comprising:

[0007] Collect multi-view traffic images, traffic flow data and vehicle speed data of the target road section in real time; pre-process the multi-view traffic images and divide them into traffic image groups in chronological order; obtain vehicle detection frames and pedestrian detection frames in traffic images of different viewpoints of the traffic image group through a target detection algorithm;

[0008] The position density index is obtained by the position coordinates and confidences of different vehicle detection frames in the first-view traffic image of the traffic image group, and it is judged whether the corresponding vehicles are dense; all the detection frames of dense vehicles are merged to obtain a synthetic detection frame; the traffic concentration index in the synthetic detection frame is calculated to determine whether it is a blocked area; the blocked area is mapped to another traffic image with different view angles to obtain a vehicle distribution area, and it is judged whether it is a blocked area; and congestion marking is performed by combining the judgment results of the traffic images of all view angles;

[0009] Calculate the contact risk index of two different detection frames in the first-view traffic image, and determine whether they overlap; map the overlapping detection frames to another different-view traffic image to obtain a mapped detection frame; project the overlapping detection frame and the mapped detection frame to a world coordinate system to form a traffic element point cloud; and determine whether to perform accident marking in combination with the corresponding point cloud overlap ratio and the vehicle dent detection model;

[0010] An environmental consistency check is performed on the congestion marking result according to the vehicle flow data and the vehicle speed data; and a marking conflict check is performed in combination with the congestion marking result and the accident marking result.

[0011] Preferably, preprocessing the multi-view traffic image includes denoising, image enhancement and standardization; the multi-view traffic image includes M view traffic images at different times; and the process of dividing the preprocessed multi-view traffic image into the traffic image groups according to the time sequence includes:

[0012] The preprocessed multi-perspective traffic images are sorted in chronological order to obtain M groups of time-series traffic images; the time of the first-perspective traffic image in the first group of time-series traffic images is obtained, and in combination with a predetermined time window, the image with the smallest time difference is matched in another M-1 groups of time-series traffic images; the first-perspective traffic image and the corresponding M-1 matching images are divided into a group to obtain the traffic image group of different times; the traffic image group contains M perspective traffic images of the same time.

[0013] Preferably, the implementation process of determining whether to perform congestion marking in combination with traffic images from different viewing angles includes:

[0014] The first-perspective traffic image and another M-1-perspective traffic images of the traffic image group are obtained; different vehicle detection frames in the first-perspective traffic image are obtained, and different vehicles are judged to be densely distributed to obtain the synthetic detection frame; based on the position coordinates and the number of vehicles of the synthetic detection frame, whether the synthetic detection frame is a blocked area is determined; if the synthetic detection frame is a blocked area, the vehicle distribution area corresponding to the synthetic detection frame in another M-1 different-perspective traffic images is obtained through a key point matching algorithm, and it is determined whether congestion marking is performed.

[0015] Preferably, the synthetic detection frame in the first-view traffic image is obtained, and it is determined whether it is a blocked area:

[0016] Obtain different vehicle detection frames in the first-perspective traffic image, and determine whether different vehicles are densely packed; calculate the position density index of the corresponding vehicle according to the confidence and position coordinates of two different detection frames; if the position density index is greater than a predetermined dense threshold, calculate the minimum outer frame of the two different detection frames to obtain the composite detection frame; repeat the dense determination operation on the composite detection frame and the vehicle detection frame until both the vehicle detection frame and the composite detection frame do not meet the dense condition; obtain the position coordinates and the number of vehicles inside the composite detection frame, and calculate the traffic concentration index; if the traffic concentration index is greater than the predetermined density threshold, it indicates that the composite detection frame is a blocked area.

[0017] Preferably, the process of obtaining the vehicle distribution area corresponding to the synthetic detection frame in another M-1 traffic images with different viewing angles and determining whether to perform congestion marking includes:

[0018] Perform key point matching on the first-perspective traffic image and the traffic image of another perspective to obtain the coordinates of the vehicle distribution area of ​​the blocked area in the traffic image of the other perspective; obtain the number of vehicles corresponding to the vehicle distribution area through the target detection algorithm; calculate the traffic concentration index based on the coordinates of the vehicle distribution area and the number of vehicles; determine whether it is a blocked area according to a predetermined density threshold; repeat the operation of determining the blocked area for another M-2 traffic images with different perspectives, and if the vehicle distribution areas corresponding to all the traffic images with different perspectives are blocked areas, mark the vehicle distribution area and the synthetic detection frame as congested; otherwise, do not mark them.

[0019] Preferably, the specific process of determining whether to perform accident marking includes:

[0020] The vehicle detection frame and the pedestrian detection frame in the traffic image of the first perspective are obtained, and the same vehicle detection frame and / or pedestrian detection frame in different perspectives are matched by a key point matching algorithm, and are projected into the world coordinate system to obtain a traffic element point cloud; the point cloud overlap ratio is calculated, and if the point cloud overlap ratio is greater than a predetermined overlap threshold, an accident is marked; if the point cloud overlap ratio is less than or equal to the predetermined overlap threshold, a dent detection is performed on the vehicle detection frame by a vehicle dent detection model; if the detection result is a dented vehicle, the vehicle detection frame is marked as an accident.

[0021] Preferably, the specific process of calculating the point cloud overlap ratio and marking the accident includes:

[0022] Obtain the vehicle detection frame and the pedestrian detection frame in the first-perspective traffic image, and determine whether two different detection frames overlap; calculate a contact risk index based on the position coordinates of the two detection frames; if the contact risk index is greater than a predetermined risk threshold, obtain the mapping detection frames of the two detection frames in another M-1-perspective traffic images through a key point matching algorithm; project the pixel coordinates of the corresponding detection frame or the mapping detection frame into the world coordinate system according to the built-in parameters of different cameras, and obtain the traffic element point cloud of the pedestrian or vehicle corresponding to the detection frame; calculate the point cloud overlap ratio, and if the point cloud overlap ratio is greater than the predetermined overlap threshold, merge the corresponding detection frames and mark them as accidents.

[0023] Preferably, the specific process of performing sag detection on the vehicle detection frame by using the vehicle sag detection model includes:

[0024] The vehicle dent detection model is constructed and trained on a public data set of automobile damage; the vehicle dent detection model includes a feature extraction module, a multi-view feature fusion module and a classifier; if the point cloud overlap ratio is less than or equal to the predetermined overlap threshold, a multi-view vehicle image corresponding to the vehicle detection frame is obtained; the multi-view vehicle image is input into the feature extraction module, and the edge, texture and shape features of the vehicle image are obtained through a multi-layer convolutional neural network to obtain a multi-view feature map; the multi-view feature map is input into the multi-view feature fusion module, and the feature maps of different views are spatially aligned through a key point matching algorithm, and the multi-view feature maps are spatially fused in combination with an attention mechanism and feature weighting to obtain a multi-view fusion map; the multi-view fusion map is nonlinearly mapped with the classifier to obtain the vehicle category of the multi-view vehicle image; if the vehicle category is a dented vehicle, the corresponding vehicle detection frame is marked as an accident.

[0025] Preferably, the specific implementation process of performing the environmental consistency check on the congestion annotation result according to the vehicle flow data and the vehicle speed data is as follows:

[0026] According to the congestion marking results from different perspectives, the congested road section, congestion time and driving direction are determined; the traffic flow data and the vehicle speed data are combined to obtain the congested traffic flow and the average congested vehicle speed of the congested road section in the driving direction within a predetermined time before and after the congestion time; the monthly average traffic flow and the monthly average vehicle speed of the congested road section in the driving direction are calculated; if the congested traffic flow is less than or equal to the monthly average traffic flow, or the average congested vehicle speed is greater than the monthly average vehicle speed, it indicates that the congestion marking result is wrong, and the corresponding image is fed back to the management personnel.

[0027] Preferably, the specific implementation process of the annotation conflict check is performed in combination with the congestion annotation result and the accident annotation result:

[0028] If the congestion annotation result and the accident annotation result exist in the same group of traffic images, the corresponding congestion annotation box and accident annotation box in the traffic image of the same perspective are obtained, and it is determined whether they overlap; if the congestion annotation box and the accident annotation box overlap, the annotation overlap rate is calculated; if the annotation overlap rates in the traffic images of different perspectives are all greater than the predetermined annotation overlap threshold, it indicates that there is a conflict between the congestion annotation result and the accident annotation result, and the corresponding image is fed back to the management personnel.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] 1. The present invention combines the vehicle detection frames in traffic images from different perspectives for comprehensive judgment, and realizes accurate marking of traffic congestion areas. By calculating the position density index and traffic concentration index between vehicles, the congestion area in the first-perspective traffic image can be accurately identified; the vehicle distribution area corresponding to the first-perspective congestion area in the traffic images from other perspectives is obtained, and further congestion judgment is made in combination with the traffic concentration index, avoiding the misjudgment that may be caused by a single perspective, and ensuring the accuracy and reliability of congestion marking.

[0031] 2. The present invention can effectively identify the occurrence of traffic accidents and improve the accuracy and efficiency of accident annotation through accurate matching of vehicle and pedestrian detection frames and calculation of the ratio of point cloud overlap. Through the key point matching algorithm, the detection frames under different viewing angles are spatially projected to obtain more comprehensive point cloud data and improve the ability to reconstruct the accident scene; combined with the vehicle dent detection model, the edge, texture and shape features of the vehicle are extracted to achieve intelligent identification of vehicle damage, so that accident annotation is not limited to simple overlap detection, and the ability to distinguish complex traffic accidents is further improved.

[0032] 3. The present invention can effectively improve the accuracy of the labeling results through environmental consistency verification and labeling conflict verification. After determining the congested road section, time and driving direction, the calculation is combined with the traffic flow and speed data to timely discover labeling errors and feedback to management personnel, thereby improving the response efficiency of traffic management; combining the congestion and accident labeling results for conflict verification helps to identify and resolve possible labeling contradictions, ensure the integrity and consistency of traffic data, and improve the accuracy of labeling results, thereby effectively reducing traffic congestion and accidents and improving road use efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flowchart of a data resource collection and annotation method based on big data mining provided in an embodiment of the present invention;

[0034] Figure 2 A flow chart of congestion marking provided for an embodiment of the present invention;

[0035] Figure 3 A schematic diagram of a synthetic detection frame acquisition process provided in an embodiment of the present invention;

[0036] Figure 4 A flowchart of accident marking provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] With the acceleration of urbanization, traffic congestion and frequent traffic accidents have become major challenges facing the world. Intelligent transportation systems have emerged to improve the efficiency and safety of traffic management through advanced information technology and communication technology. These systems rely on massive amounts of traffic data to monitor traffic flow in real time, predict traffic conditions, and optimize resource allocation. In this context, the collection and annotation of traffic data is particularly important. Accurate traffic data not only provides basic support for intelligent algorithms, but also high-quality annotated data can improve the accuracy of machine learning models, thereby achieving effective analysis and prediction of traffic conditions. Therefore, building an efficient and accurate traffic data collection and annotation system has become a key link in achieving the goal of intelligent transportation.

[0039] The invention proposes a data resource collection and annotation method based on big data mining, which collects and annotates traffic data to improve the effect of intelligent transportation system in traffic management and accident prevention. In order to illustrate the effectiveness of the method of the invention, the invention will be described in detail in combination with the accompanying drawings of the embodiment and the following specific implementation details.

[0040] Embodiment 1

[0041] The embodiment of the present application discloses a data resource collection and annotation method based on big data mining to realize the collection and annotation of traffic data at intersection A. Figure 1 The specific steps of the method proposed in the present invention include: S1. Real-time collection of multi-view traffic images, vehicle flow data and vehicle speed data of the target road section; S2. Preprocessing the multi-view traffic images and dividing them into traffic image groups in chronological order; S3. Merging the detection frames of dense vehicles according to the position coordinates and confidence of the vehicle detection frames, and calculating the traffic concentration index to determine whether to perform congestion marking; S4. Projecting the overlapping detection frames in the traffic images of different viewpoints into the world coordinate system to obtain the traffic element point cloud, and combining the point cloud overlap number ratio and the vehicle dent detection model to determine whether to perform accident marking; S5. According to the vehicle flow data and the vehicle speed data, performing environmental consistency check and marking conflict check on the congestion marking results and the accident marking results.

[0042] Furthermore, multi-perspective traffic images, traffic flow data and vehicle speed data at the A intersection are collected in real time; the multi-perspective traffic images are preprocessed and divided into traffic image groups in chronological order; vehicle detection frames and pedestrian detection frames in traffic images of different perspectives in the traffic image group are obtained through a target detection algorithm, corresponding to the above steps S1 and S2; wherein the preprocessing of the multi-perspective traffic images includes denoising, image enhancement and standardization; the multi-perspective traffic images include M perspective traffic images at different times; the process of dividing the preprocessed multi-perspective traffic images into the traffic image groups according to chronological order includes:

[0043] The preprocessed multi-perspective traffic images are sorted in chronological order to obtain M groups of time-series traffic images; the time of the first-perspective traffic image in the first group of time-series traffic images is obtained, and in combination with a predetermined time window, the image with the smallest time difference is matched in another M-1 groups of time-series traffic images; the first-perspective traffic image and the corresponding M-1 matching images are divided into a group to obtain the traffic image group of different times; the traffic image group contains M perspective traffic images of the same time.

[0044] The embodiments of the present application improve the image quality and reduce interference factors through denoising, image enhancement and standardization, thereby ensuring the accuracy of subsequent analysis; sort the multi-perspective traffic images in chronological order so that the traffic conditions under different perspectives can be effectively compared and analyzed, and the time difference between perspectives can be minimized, thereby improving the similarity and consistency of the traffic image group; by dividing each first-perspective traffic image and the corresponding matching image into a group, a rich multi-perspective data set can be formed, which provides data support for subsequent traffic status analysis and promotes the effective implementation of the intelligent transportation system.

[0045] Further, through the position coordinates and confidences of different vehicle detection frames in the first-view traffic image of the traffic image group, it is determined whether the corresponding vehicles are dense; the detection frames of dense vehicles are merged to obtain a synthetic detection frame, and the traffic concentration index is calculated to determine whether it is a blocked area; the area is mapped to traffic images of different viewpoints to obtain a vehicle distribution area, and it is determined whether it is a blocked area; combined with the judgment result, the traffic image group is congested, corresponding to the above-mentioned step S3; refer to Figure 2 The specific implementation process includes:

[0046] The first-perspective traffic image and another M-1-perspective traffic images of the traffic image group are obtained; different vehicle detection frames in the first-perspective traffic image are obtained, and different vehicles are judged to be densely distributed to obtain the synthetic detection frame; based on the position coordinates and the number of vehicles of the synthetic detection frame, whether the synthetic detection frame is a blocked area is determined; if the synthetic detection frame is a blocked area, the corresponding vehicle distribution areas in the other M-1 different-perspective traffic images of the synthetic detection frame are obtained through a key point matching algorithm, and it is determined whether congestion marking is performed.

[0047] The embodiment of the present application analyzes the vehicle detection frames of traffic images of different perspectives in the traffic image group and combines the position coordinates and confidence information to effectively determine the density of vehicles and identify potential congestion areas, thereby monitoring and improving traffic flow in real time and improving traffic efficiency.

[0048] Further, the synthetic detection frame in the first-view traffic image is obtained, and it is determined whether it is a blocked area:

[0049] Obtain different vehicle detection frames in the first perspective traffic image, and determine whether different vehicles are densely spaced; calculate the position density index of the corresponding vehicle according to the confidence and position coordinates of two different detection frames, and the calculation formula is expressed as:

[0050]

[0051] α c =1-pc ,α d =p d ;

[0052] Among them, DI c,d Represents the position density index of the detection box c and the detection box d; exp() represents the power function with a natural constant as the base; x c ,y c Respectively represent the horizontal and vertical coordinates of the upper left corner of the detection box c; c ,h c Respectively represent the width and height of the detection box c; x d ,y d Respectively represent the horizontal and vertical coordinates of the upper left corner of the detection box d; d ,h d Respectively represent the width and height of the detection box d; α c ,α d represents the adjustment parameter; p c ,p d Represent the confidence of detection frames c and d respectively. If detection frames c and / or d are synthetic detection frames, their corresponding confidence is the average confidence of all vehicle detection frames in the synthetic detection frame;

[0053] If the position density index is greater than a predetermined density threshold, the minimum outer bounding box of two different detection frames is calculated to obtain the composite detection frame; the density judgment operation is repeated for the composite detection frame and the vehicle detection frame until both the vehicle detection frame and the composite detection frame do not meet the density condition; the position coordinates and the number of vehicles inside the composite detection frame are obtained, and the traffic density index is calculated. The specific calculation formula is expressed as follows:

[0054]

[0055] Among them, VD i N represents the traffic concentration index of the i-th synthetic detection frame; i represents the number of vehicles inside the i-th synthetic detection frame; h i ,w i represents the height and width of the i-th synthetic detection frame;

[0056] If the traffic concentration index is greater than a predetermined density threshold, it indicates that the synthetic detection frame is a blocked area.

[0057] Specifically, see Figure 3, repeating the dense judgment operation on the synthetic detection frame, indicating that the synthetic detection frame is regarded as the vehicle detection frame, and by calculating the position density index of the synthetic detection frame and the remaining vehicle detection frames or synthetic detection frames, it is determined whether to merge again to obtain a new synthetic detection frame. When both the vehicle detection frame and the synthetic detection frame do not meet the dense condition, it means that the position density index between the remaining detection frames in the first-view traffic image cannot meet a predetermined dense threshold, thereby obtaining the final synthetic detection frame.

[0058] In order to further illustrate the role of the traffic concentration index proposed in the present invention in determining whether the synthetic detection frame in the first-perspective traffic image is congested, the traffic concentration indexes of different synthetic detection frames in the first-perspective traffic image at the A intersection are given as an example for comparison. Refer to Table 1 for a list of traffic concentration indexes of different synthetic detection frames in the first-perspective traffic image at the A intersection.

[0059] Table 1. Traffic concentration index of different synthetic detection frames in the first-person traffic image at intersection A

[0060]

[0061] According to the data in Table 1, it can be seen that the size of the synthetic detection frame and the number of vehicles inside are related to the judgment of whether there is congestion. For example, in the case of synthetic detection frames 1 and 3, when their detection frame sizes are similar, the larger the number of vehicles inside, the greater the possibility that the area is a congested area, that is, within a similar spatial range, a smaller number of vehicles indicates that the traffic conditions in the area are relatively smooth.

[0062] The embodiment of the present application can effectively identify the blocked area in the traffic image through the above method, thereby improving the efficiency of traffic management. By using the density judgment between different vehicle detection frames, the changes in traffic flow can be accurately captured; by calculating the vehicle position density index, potential blocked areas can be identified; the generation of synthetic detection frames and further density judgment ensure the accurate identification of blocked areas. This method not only improves the monitoring accuracy of traffic status, but also provides important data support for the optimization of intelligent transportation systems, thereby improving overall traffic efficiency and safety.

[0063] Furthermore, the process of obtaining the vehicle distribution area corresponding to the synthetic detection frame in another M-1 traffic images with different viewing angles and determining whether to perform congestion marking includes:

[0064] Perform key point matching on the first-perspective traffic image and the traffic image of another perspective to obtain the coordinates of the vehicle distribution area of ​​the blocked area in the traffic image of the other perspective; obtain the number of vehicles corresponding to the vehicle distribution area through the target detection algorithm; calculate the traffic concentration index based on the coordinates of the vehicle distribution area and the number of vehicles; determine whether it is a blocked area according to a predetermined density threshold; repeat the operation of determining the blocked area for another M-2 traffic images with different perspectives, and if the vehicle distribution areas corresponding to all the traffic images with different perspectives are blocked areas, mark the vehicle distribution area and the synthetic detection frame as congested; otherwise, do not mark them.

[0065] In the traffic data annotation of intersection A, traffic mobility and traffic concentration index may show significant differences in images from different perspectives. Different perspectives provide a multi-dimensional observation of traffic conditions and can more comprehensively capture the true situation of traffic congestion. For example, some vehicle detection frames may appear overlapping in a traffic image from one perspective, but may not overlap in another perspective. Therefore, by analyzing images from multiple perspectives to ensure the accuracy and reliability of the judgment of the blocked area, it can not only reduce the judgment errors caused by a single perspective, but also improve the overall understanding of the traffic conditions and ensure the quality of annotation.

[0066] The embodiment of the present application can accurately obtain the coordinates of the vehicle distribution area and the corresponding number of vehicles by performing key point matching and target detection on traffic images from multiple perspectives, thereby effectively calculating the traffic concentration index. This method not only improves the recognition accuracy of the blocked area, but also comprehensively considers the image information from different perspectives to ensure the consistency and reliability of the judgment. When the vehicle distribution area under all perspectives is confirmed to be spatially congested, the area is marked as congested, thereby providing accurate data support for traffic management and intelligent navigation, greatly improving the efficiency of traffic flow monitoring and management, and helping to alleviate traffic congestion problems.

[0067] Further, it is determined whether two different detection frames in the first perspective traffic image overlap, and overlapping detection frames in traffic images of different perspectives are obtained; the overlapping detection frames are projected into the world coordinate system to obtain a traffic element point cloud; by calculating the overlapping number ratio of the point clouds corresponding to the two different detection frames, combined with the vehicle dent detection model, it is determined whether to perform accident marking, corresponding to Figure 1 S4 step of Figure 4 The specific process includes:

[0068] The vehicle detection frame and the pedestrian detection frame in the traffic image of the first perspective are obtained, and the same vehicle detection frame and / or pedestrian detection frame in different perspectives are matched by a key point matching algorithm, and are projected into the world coordinate system to obtain a traffic element point cloud; the point cloud overlap ratio is calculated, and if the point cloud overlap ratio is greater than a predetermined overlap threshold, an accident is marked; if the point cloud overlap ratio is less than or equal to the predetermined overlap threshold, a dent detection is performed on the vehicle detection frame by a vehicle dent detection model; if the detection result is a dented vehicle, the vehicle detection frame is marked as an accident.

[0069] The embodiment of the present application can effectively improve the accuracy and efficiency of accident annotation by analyzing the overlap of different detection frames in the first-person perspective traffic image and projecting the overlapping frames to the world coordinate system to obtain the traffic element point cloud. The method uses a key point matching algorithm to associate the vehicle or pedestrian detection frames in different perspectives to ensure the consistency and integrity of the data; calculates the point cloud overlap ratio to enable timely accident annotation and ensure timely handling of the accident; and when the overlap ratio is insufficient, the vehicle is further analyzed through the vehicle dent detection model to ensure that every vehicle that may be damaged can be accurately labeled. This method not only enhances the accuracy of accident identification, but also improves the overall efficiency of traffic safety management.

[0070] Furthermore, the specific process of calculating the point cloud overlap ratio and marking the accident includes:

[0071] The vehicle detection frame and the pedestrian detection frame in the first-view traffic image are obtained to determine whether the two different detection frames overlap; the contact risk index is calculated according to the position coordinates of the two detection frames; the specific calculation formula is:

[0072]

[0073] Among them, CP c,d represents the contact risk index of detection box c and detection box d; x c ,y c Respectively represent the horizontal and vertical coordinates of the upper left corner of the detection box c; c ,h c Respectively represent the width and height of the detection box c; x d ,y d Respectively represent the horizontal and vertical coordinates of the upper left corner of the detection box d; d ,h d They represent the width and height of the detection box d respectively; max() represents the maximum value function;

[0074] If the contact risk index is greater than the predetermined risk threshold, the mapping detection frames of the two detection frames in the other M-1 perspective traffic images are obtained through the key point matching algorithm; the pixel coordinates of the corresponding detection frame or the mapping detection frame are projected into the world coordinate system according to the built-in parameters of different cameras, and the traffic element point cloud of the pedestrian or vehicle corresponding to the detection frame is obtained. The specific formula is expressed as follows:

[0075] [X,Y,Z] T =R×[X cam ,Y cam ,Z cam ] T +t c ;

[0076]

[0077] Wherein, [X, Y, Z] represents the traffic element point cloud; [] T Represents the matrix transposition operation; R represents the rotation matrix of the camera; t c Represents the coordinates of the camera in the world coordinate system; [X cam ,Y cam ,Z cam ] represents the coordinates in the camera coordinate system; D represents the camera depth, that is, the distance between the camera and the vehicle; Represents the camera's built-in parameter matrix, f x ,f y is the focal length of the camera on the horizontal and vertical axes, c x ,c y is the center coordinate of the image; u, v represents the horizontal and vertical coordinates of the key point in the image; [] -1 Represents the matrix inversion operation;

[0078] The point cloud overlap ratio is calculated. If the point cloud overlap ratio is greater than the predetermined overlap threshold, the corresponding detection frames are merged and marked as an accident.

[0079] Specifically, according to the traffic element point clouds of the targets corresponding to the two detection frames, the number of overlapping point clouds is calculated; the edge traffic element point cloud of one of the targets is obtained, and the traffic element point cloud of the other target is compared with the edge traffic element point cloud to screen out the number of point clouds in the edge traffic element point cloud area; combined with the total number of point clouds of the corresponding targets, the point cloud overlapping number ratio is obtained.

[0080] The method of the embodiment of the present application can effectively identify key elements in traffic accidents by calculating the point cloud overlap ratio and contact risk index, thereby improving the accuracy of accident detection. By acquiring traffic images and their detection frames from different perspectives and mapping them using a key point matching algorithm, the integration of multi-perspective information is achieved, allowing a more comprehensive assessment of potential collisions between vehicles and pedestrians; projecting the pixel coordinates of the detection frame to the world coordinate system can accurately obtain the traffic element point cloud of pedestrians and / or vehicles, further analyzing the spatial relationship between different targets, and improving the efficiency of accident identification.

[0081] Furthermore, the specific process of performing sag detection on the vehicle detection frame by using the vehicle sag detection model includes:

[0082] The vehicle dent detection model is constructed and trained on a public data set of automobile damage; the vehicle dent detection model includes a feature extraction module, a multi-view feature fusion module and a classifier; if the point cloud overlap ratio is less than or equal to the predetermined overlap threshold, a multi-view vehicle image corresponding to the vehicle detection frame is obtained; the multi-view vehicle image is input into the feature extraction module, and the edge, texture and shape features of the vehicle image are obtained through a multi-layer convolutional neural network to obtain a multi-view feature map; the multi-view feature map is input into the multi-view feature fusion module, and the feature maps of different views are spatially aligned through a key point matching algorithm, and the multi-view feature maps are spatially fused in combination with an attention mechanism and feature weighting to obtain a multi-view fusion map. The specific formula is:

[0083]

[0084] Among them, F multi represents the multi-view fusion graph; F j W represents the multi-view feature map of the j-th view; j represents the weight coefficient of the multi-view feature map of the j-th view; Softmax() represents the softmax activation function; Flatten() represents the sequence expansion operation; () T Indicates transpose operation; d f Represents the matrix Flatten(F j ) dimension;

[0085] The multi-view fusion image is subjected to nonlinear feature mapping by the classifier to obtain the vehicle category of the multi-view vehicle image; if the vehicle category is a dented vehicle, the corresponding vehicle detection frame is marked as an accident.

[0086] The embodiment of the present application improves the detection accuracy and efficiency of vehicle dents through a vehicle dent detection model. The model is trained on a public data set of automobile damage to ensure its good adaptability to various damage situations, thereby improving the reliability of recognition; the multi-layer convolutional neural network of the feature extraction module can accurately capture the edge, texture and shape features in the vehicle image, providing rich information for subsequent feature fusion; the multi-view feature fusion module combines the key point matching algorithm and the attention mechanism to effectively align and weight the feature maps of different perspectives, ensuring the comprehensiveness and consistency of multi-view information; through the nonlinear feature mapping of the classifier, the model can not only accurately identify dented vehicles, but also quickly mark the relevant detection boxes.

[0087] Further, the congestion annotation result is subjected to the environmental consistency check according to the vehicle flow data and the vehicle speed data; Figure 1 The specific implementation process of step S5 is as follows:

[0088] According to the congestion marking results from different perspectives, the congested road section, congestion time and driving direction are determined; the traffic flow data and the vehicle speed data are combined to obtain the congested traffic flow and the average congested vehicle speed of the congested road section in the driving direction within a predetermined time before and after the congestion time; the monthly average traffic flow and the monthly average vehicle speed of the congested road section in the driving direction are calculated; if the congested traffic flow is less than or equal to the monthly average traffic flow, or the average congested vehicle speed is greater than the monthly average vehicle speed, it indicates that the congestion marking result is wrong, and the corresponding image is fed back to the management personnel.

[0089] The embodiment of the present application can effectively improve the accuracy of congestion annotation results by checking the environmental consistency of traffic flow data and speed data. This process can not only accurately identify congested sections, congestion time and driving direction, but also conduct dynamic analysis in combination with actual traffic conditions to ensure that the annotation results are consistent with the actual situation; by calculating the monthly average traffic flow and monthly average speed of congested sections, annotation errors can be discovered and corrected in a timely manner, thereby providing accurate information for traffic management personnel, improving road traffic efficiency and alleviating traffic congestion.

[0090] Further, combining the congestion marking result and the accident marking result, the marking conflict check is performed; corresponding Figure 1 The specific implementation process of step S5 is as follows:

[0091] If the congestion annotation result and the accident annotation result exist in the same group of traffic images, obtain the corresponding congestion annotation frame and accident annotation frame in the traffic image of the same viewing angle, and determine whether they overlap; if the congestion annotation frame and the accident annotation frame overlap, calculate the annotation overlap rate, and the specific formula is:

[0092]

[0093] Wherein, OR represents the annotation overlap rate; A over A represents the overlapping area of ​​the congestion labeling box and the accident labeling box. If the two labeling boxes do not overlap, then A over =0; A ca A represents the area of ​​the congestion annotation box; ia represents the area of ​​the accident marking box; min() represents the minimum function;

[0094] If the annotation overlap rates in the traffic images from different viewing angles are all greater than a predetermined annotation overlap threshold, it indicates that there is a conflict between the congestion annotation result and the accident annotation result, and the corresponding image is fed back to the management personnel.

[0095] The embodiment of the present application can effectively improve the accuracy and reliability of the traffic management system by combining the congestion annotation results and the accident annotation results to perform annotation conflict verification. When there are congestion and accident annotations in the same set of traffic images, the overlap between these annotations can be automatically identified and analyzed, and the annotation overlap rate can be calculated; if the annotation overlap rate in traffic images from different perspectives exceeds a predetermined threshold, potential annotation conflicts are identified. This process can optimize traffic flow management, reduce false alarms, and improve accident response efficiency, thereby improving overall traffic safety and traffic efficiency.

[0096] The embodiment of the present application realizes accurate labeling of traffic congestion areas by making comprehensive judgments based on vehicle detection frames in traffic images with different perspectives. The specific implementation process mainly includes the following steps: (1) Identifying the congestion area in multi-perspective traffic images; (2) Identifying the accident area in multi-perspective traffic images; (3) Promptly discovering labeling errors and feeding back to management personnel through environmental consistency verification and labeling conflict verification. The present invention proposes a congestion labeling method, an accident labeling method, and a labeling result verification for the above three processes respectively; the congestion labeling method realizes a comprehensive detection of traffic flow conditions and improves the accuracy of congestion labeling results; the accident labeling method further improves the ability to identify complex traffic accidents; the labeling result verification realizes the consistency of traffic labeling data, thereby improving the accuracy of labeling results.

[0097] Embodiment 2

[0098] In Example 1, the method of the present invention realizes the collection and labeling of traffic data at the intersection A. In the embodiment of the present application, the method proposed by the present invention will be described again to realize the collection and labeling of traffic data at the roundabout intersection B. The specific implementation process is as follows:

[0099] Collect multi-view traffic images, traffic flow data and vehicle speed data of the target road section in real time; pre-process the multi-view traffic images and divide them into traffic image groups in chronological order; and obtain vehicle detection frames and pedestrian detection frames in traffic images of different viewpoints of the traffic image group through a target detection algorithm.

[0100] Furthermore, the position density index is obtained through the position coordinates and confidence levels of different vehicle detection frames in the first-perspective traffic image of the traffic image group, and it is determined whether the corresponding vehicles are dense; the detection frames of all dense vehicles are merged to obtain a synthetic detection frame; the traffic concentration index in the synthetic detection frame is calculated to determine whether it is a blocked area; the blocked area is mapped to another traffic image of a different perspective to obtain a vehicle distribution area, and it is determined whether it is a blocked area; and congestion marking is performed based on the judgment results of traffic images of all perspectives.

[0101] Further, the contact risk index of two different detection frames in the first perspective traffic image is calculated, and whether they overlap is determined; the overlapping detection frames are mapped to another different perspective traffic image to obtain a mapped detection frame; the overlapping detection frames and the mapped detection frames are projected into the world coordinate system to form a traffic element point cloud; and whether to perform accident marking is determined in combination with the corresponding point cloud overlap quantity ratio and the vehicle dent detection model; the specific implementation process includes:

[0102] The vehicle detection frame and the pedestrian detection frame in the first-perspective traffic image are obtained to determine whether the two different detection frames overlap; a contact risk index is calculated according to the position coordinates of the two detection frames; if the contact risk index is greater than a predetermined risk threshold, the mapping detection frames of the two detection frames in the other M-1 perspective traffic images are obtained through a key point matching algorithm; the pixel coordinates of the corresponding detection frame or the mapping detection frame are projected into the world coordinate system according to the built-in parameters of different cameras to obtain the traffic element point cloud of the pedestrian or vehicle corresponding to the detection frame; the corresponding point cloud overlap ratio is calculated, and if the point cloud overlap ratio is greater than the predetermined overlap threshold, the corresponding detection frames are merged and marked as accidents; if the point cloud overlap ratio is less than or equal to the predetermined overlap threshold, the multi-perspective vehicle images are detected through a vehicle dent detection model to obtain the vehicle type; if the vehicle category is a dented vehicle, the corresponding vehicle detection frame is marked as an accident.

[0103] When annotating traffic data for roundabout B, the point cloud overlap ratio can effectively evaluate the degree of interaction between two detection frames. When different detection frames overlap, the calculation of the point cloud overlap ratio can reveal the potential collision risk between traffic participants, which is crucial for timely identification of possible accidents, especially in complex traffic environments such as roundabouts, where there is frequent interaction between vehicles and pedestrians or other vehicles. The point cloud overlap ratio can help determine whether there is an actual collision risk. In the case of a high contact risk index, by combining the information captured by different cameras, the construction of three-dimensional point cloud data can be used to judge traffic accidents from multiple perspectives to improve the accuracy of accident annotation. At the same time, dent detection can analyze the damage to the vehicle. When a dented vehicle is detected, it means that the vehicle may have been involved in a traffic accident. Therefore, the corresponding detection frame is supplemented with annotations to improve the integrity of the accident annotation.

[0104] Furthermore, according to the vehicle flow data and the vehicle speed data, the congestion annotation result is checked for environmental consistency; the congestion annotation result and the accident annotation result are combined to perform an annotation conflict check; the specific implementation process of the annotation conflict check is as follows:

[0105] If the congestion annotation result and the accident annotation result exist in the same group of traffic images, obtain the corresponding congestion annotation frame and accident annotation frame in the traffic image of the same viewing angle, and determine whether they overlap; if the congestion annotation frame and the accident annotation frame overlap, calculate the annotation overlap rate, and the specific formula is:

[0106]

[0107] Wherein, OR represents the annotation overlap rate; A over A represents the overlapping area of ​​the congestion labeling box and the accident labeling box. If the two labeling boxes do not overlap, then A over =0; A ca A represents the area of ​​the congestion annotation box; ia represents the area of ​​the accident marking box; min() represents the minimum function;

[0108] If the annotation overlap rates in the traffic images from different viewing angles are all greater than a predetermined annotation overlap threshold, it indicates that there is a conflict between the congestion annotation result and the accident annotation result, and the corresponding image is fed back to the management personnel.

[0109] In order to further illustrate the role of the annotation overlap rate proposed in the present invention in determining the accuracy of the annotation result, the annotation overlap rates of traffic images of different viewing angles at the B roundabout are given as an example for comparison. The annotation overlap rates of traffic images of different viewing angles at the B roundabout are listed in Table 2; wherein the unit of area is (pixel 2 ).

[0110] According to the data analysis in Table 2, it can be seen that there is a certain relationship between the annotation overlap rate of traffic images from different perspectives of the B roundabout and the area of ​​the congestion annotation box and the accident annotation box. For example, in the TX01 image, the area of ​​the congestion annotation box is 15444, the area of ​​the accident annotation box is 1440, the overlapping area is 782, and the annotation overlap rate reaches 0.54, which is much higher than the predetermined threshold of 0.3, showing that the two annotation boxes have obvious overlap, indicating that there may be annotation errors and further processing is required; in TX03, the overlapping area is 0, resulting in a 0 annotation overlap rate, which indicates that there is no overlap between the annotation boxes, that is, there is no conflict between the two annotations.

[0111] Table 2. Annotation overlap rate of traffic images from different perspectives of roundabout B

[0112]

[0113] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A data resource collection and annotation method based on big data mining, characterized in that: include: Collect multi-view traffic images, traffic flow data and vehicle speed data of the target road section in real time; pre-process the multi-view traffic images and divide them into traffic image groups in chronological order; Obtaining vehicle detection frames and pedestrian detection frames in traffic images of different viewing angles in the traffic image group through a target detection algorithm; The position density index is obtained by the position coordinates and confidences of different vehicle detection frames in the first-view traffic image of the traffic image group, and it is judged whether the corresponding vehicles are dense; all the detection frames of dense vehicles are merged to obtain a synthetic detection frame; the traffic concentration index in the synthetic detection frame is calculated to determine whether it is a blocked area; the blocked area is mapped to another traffic image with different view angles to obtain a vehicle distribution area, and it is judged whether it is a blocked area; and congestion marking is performed by combining the judgment results of the traffic images of all view angles; Calculate the contact risk index of two different detection frames in the first-view traffic image, and determine whether they overlap; map the overlapping detection frames to another different-view traffic image to obtain a mapped detection frame; project the overlapping detection frame and the mapped detection frame to a world coordinate system to form a traffic element point cloud; and determine whether to perform accident marking in combination with the corresponding point cloud overlap ratio and the vehicle dent detection model; An environmental consistency check is performed on the congestion marking result according to the vehicle flow data and the vehicle speed data; and a marking conflict check is performed in combination with the congestion marking result and the accident marking result.

2. The data resource collection and annotation method based on big data mining according to claim 1 is characterized in that: Preprocessing the multi-view traffic image includes denoising, image enhancement and standardization; the multi-view traffic image includes M view traffic images at different times; The process of dividing the pre-processed multi-view traffic image into the traffic image groups according to the time sequence includes: Sorting the preprocessed multi-view traffic images in chronological order to obtain M groups of time-series traffic images; The time of the first-perspective traffic image in the first group of time-series traffic images is obtained, and combined with a predetermined time window, the image with the smallest time difference is matched in another M-1 groups of time-series traffic images; the first-perspective traffic image and the corresponding M-1 matching images are divided into a group to obtain the traffic image group at different times; the traffic image group includes M-perspective traffic images at the same time.

3. The data resource collection and annotation method based on big data mining according to claim 1 is characterized in that: The implementation process of combining traffic images from different perspectives to determine whether to mark congestion includes: The first-perspective traffic image and another M-1-perspective traffic images of the traffic image group are obtained; different vehicle detection frames in the first-perspective traffic image are obtained, and different vehicles are judged to be densely distributed to obtain the synthetic detection frame; based on the position coordinates and the number of vehicles of the synthetic detection frame, whether the synthetic detection frame is a blocked area is determined; if the synthetic detection frame is a blocked area, the vehicle distribution area corresponding to the synthetic detection frame in another M-1 different-perspective traffic images is obtained through a key point matching algorithm, and it is determined whether congestion marking is performed.

4. The data resource collection and annotation method based on big data mining according to claim 3 is characterized in that: Obtain the synthetic detection frame in the first-view traffic image, and determine whether it is a blocked area: Obtain different vehicle detection frames in the first-perspective traffic image, and determine whether different vehicles are densely packed; calculate the position density index of the corresponding vehicle according to the confidence and position coordinates of two different detection frames; if the position density index is greater than a predetermined density threshold, calculate the minimum outer frame of the two different detection frames to obtain the composite detection frame; repeat the density determination operation on the composite detection frame and the vehicle detection frame until both the vehicle detection frame and the composite detection frame do not meet the density condition; obtain the position coordinates and the number of vehicles inside the composite detection frame, and calculate the traffic concentration index; if the traffic concentration index is greater than the predetermined density threshold, it indicates that the composite detection frame is a blocked area.

5. The data resource collection and annotation method based on big data mining according to claim 3 is characterized in that: The process of obtaining the vehicle distribution area corresponding to the synthetic detection frame in another M-1 traffic images with different viewing angles and determining whether to perform congestion marking includes: Perform key point matching on the first-perspective traffic image and the traffic image of another perspective to obtain the coordinates of the vehicle distribution area of ​​the blocked area in the traffic image of the other perspective; obtain the number of vehicles corresponding to the vehicle distribution area through the target detection algorithm; calculate the traffic concentration index based on the coordinates of the vehicle distribution area and the number of vehicles; determine whether it is a blocked area according to a predetermined density threshold; repeat the operation of determining the blocked area for another M-2 traffic images with different perspectives, and if the vehicle distribution areas corresponding to all the traffic images with different perspectives are blocked areas, mark the vehicle distribution area and the synthetic detection frame as congested; otherwise, do not mark them.

6. The data resource collection and annotation method based on big data mining according to claim 1 is characterized in that: The specific process of determining whether to mark an accident includes: The vehicle detection frame and the pedestrian detection frame in the traffic image of the first perspective are obtained, the contact risk index of the two different detection frames is calculated, and it is determined whether they overlap; if they overlap, the same vehicle detection frame and / or the pedestrian detection frame in different perspectives are matched by a key point matching algorithm to obtain the mapped detection frame; and the detection frame is projected into the world coordinate system to obtain the traffic element point cloud; the point cloud overlap ratio is calculated, and if the point cloud overlap ratio is greater than a predetermined overlap threshold, an accident is marked; if the point cloud overlap ratio is less than or equal to the predetermined overlap threshold, a dent detection is performed on the vehicle detection frame by a vehicle dent detection model; if the detection result is a dented vehicle, the vehicle detection frame is marked as an accident.

7. The data resource collection and annotation method based on big data mining according to claim 6 is characterized in that: The specific process of calculating the point cloud overlap ratio and marking the accident includes: Obtain the vehicle detection frame and the pedestrian detection frame in the first-perspective traffic image, and determine whether the two different detection frames overlap; calculate the contact risk index according to the position coordinates of the two detection frames; if the contact risk index is greater than a predetermined risk threshold, obtain the mapped detection frames of the two detection frames in another M-1-perspective traffic images through a key point matching algorithm; project the pixel coordinates of the corresponding detection frame or the mapped detection frame into the world coordinate system according to the built-in parameters of different cameras, and obtain the traffic element point cloud of the pedestrian or vehicle corresponding to the detection frame; calculate the corresponding point cloud overlap ratio; if the point cloud overlap ratio is greater than the predetermined overlap threshold, merge the corresponding detection frames and mark them as accidents.

8. The data resource collection and annotation method based on big data mining according to claim 6 is characterized in that: The specific process of performing sag detection on the vehicle detection frame by using the vehicle sag detection model includes: The vehicle dent detection model is constructed and trained on a public data set of automobile damage; the vehicle dent detection model includes a feature extraction module, a multi-view feature fusion module and a classifier; if the point cloud overlap ratio is less than or equal to the predetermined overlap threshold, a multi-view vehicle image corresponding to the vehicle detection frame is obtained; the multi-view vehicle image is input into the feature extraction module, and the edge, texture and shape features of the vehicle image are obtained through a multi-layer convolutional neural network to obtain a multi-view feature map; the multi-view feature map is input into the multi-view feature fusion module, and the feature maps of different views are spatially aligned through a key point matching algorithm, and the multi-view feature maps are spatially fused in combination with an attention mechanism and feature weighting to obtain a multi-view fusion map; the multi-view fusion map is nonlinearly mapped with the classifier to obtain the vehicle category of the multi-view vehicle image; if the vehicle category is a dented vehicle, the corresponding vehicle detection frame is marked as an accident.

9. The data resource collection and annotation method based on big data mining according to claim 1 is characterized in that: The specific implementation process of performing the environmental consistency check on the congestion annotation result according to the vehicle flow data and the vehicle speed data is as follows: According to the congestion marking results from different perspectives, the congested road section, congestion time and driving direction are determined; the traffic flow data and the vehicle speed data are combined to obtain the congested traffic flow and the average congested vehicle speed of the congested road section in the driving direction within a predetermined time before and after the congestion time; the monthly average traffic flow and the monthly average vehicle speed of the congested road section in the driving direction are calculated; if the congested traffic flow is less than or equal to the monthly average traffic flow, or the average congested vehicle speed is greater than the monthly average vehicle speed, it indicates that the congestion marking result is wrong, and the corresponding image is fed back to the management personnel.

10. The data resource collection and annotation method based on big data mining according to claim 1, characterized in that: The specific implementation process of performing the annotation conflict check in combination with the congestion annotation result and the accident annotation result is as follows: If the congestion annotation result and the accident annotation result exist in the same group of traffic images, the corresponding congestion annotation box and accident annotation box in the traffic image of the same perspective are obtained, and it is determined whether they overlap; if the congestion annotation box and the accident annotation box overlap, the annotation overlap rate is calculated; if the annotation overlap rates in the traffic images of different perspectives are all greater than the predetermined annotation overlap threshold, it indicates that there is a conflict between the congestion annotation result and the accident annotation result, and the corresponding image is fed back to the management personnel.

Images