Urban traffic chaos measurement method and system based on vehicle trajectory and vehicle-mounted video

Abstract

The present invention discloses a method and system for measuring urban traffic chaos based on vehicle trajectory and vehicle-mounted video, the method comprising: extracting vehicle-mounted images from vehicle-mounted videos using timestamp information in trajectory data; extracting different types of traffic participants and road isolation features for segmenting the current vehicle driving area from the vehicle-mounted images, respectively, and screening the extracted traffic participants according to the segmentation results; calculating the urban traffic chaos index based on the screening results in combination with the information entropy formula, and binding the traffic chaos index to the urban roads using the trajectory data corresponding to the vehicle-mounted images and the map matching algorithm to obtain the degree of traffic chaos on the urban roads. The present invention realizes dynamic monitoring of urban traffic chaos in a low-cost, long-time-series and wide-coverage manner through vehicle trajectory and vehicle-mounted video data.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent transportation, and in particular relates to a method and system for measuring urban traffic chaos based on vehicle trajectories and vehicle-mounted videos. Background Art

[0002] Urban traffic chaos is an important factor affecting traffic efficiency and traffic safety. Measuring the degree of urban traffic chaos is of great significance for urban planning and traffic supervision. Existing research and technology mainly focus on the identification and prediction of traffic congestion. The research on the essential problem that causes congestion and affects traffic safety - traffic chaos - is not in-depth enough, and there is a lack of effective measurement indicators and calculation frameworks.

[0003] With the continuous development of computer vision technology, traffic monitoring equipment has become one of the main data sources for urban traffic status monitoring. However, due to the limited number and high cost of traffic monitoring equipment, it is difficult to achieve long-term and wide-coverage monitoring of urban traffic status. Summary of the invention

[0004] In order to overcome the deficiencies of the above-mentioned prior art, the present invention provides a method and system for measuring urban traffic chaos based on vehicle trajectory and on-board video, which realizes dynamic monitoring of urban traffic chaos in a low-cost, long-time and wide-coverage manner through vehicle trajectory and on-board video data.

[0005] According to one aspect of the present invention, a method for measuring urban traffic chaos based on vehicle trajectories and vehicle-mounted videos is provided, comprising:

[0006] Extract vehicle images from vehicle videos using timestamp information in trajectory data;

[0007] Extract different types of traffic participants and road isolation features for segmenting the current vehicle driving area from the vehicle-mounted image, and screen the extracted traffic participants according to the segmentation results;

[0008] According to the screening results, the urban traffic chaos index is calculated by combining the information entropy formula;

[0009] By using the trajectory data corresponding to the vehicle-mounted images and the map matching algorithm, the traffic chaos index is bound to the urban roads to obtain the degree of traffic chaos on the urban roads.

[0010] As a further technical solution, the method further includes:

[0011] The traffic chaos index on each road section is grouped according to time, and the total traffic chaos index on each road in each time period is obtained;

[0012] The maximum value in each group is taken as the traffic chaos index of the current road in the current time period, forming a distribution diagram of the urban traffic chaos index in a certain time period, and the degree of urban traffic chaos is measured according to the distribution diagram.

[0013] As a further technical solution, the timestamp information in the trajectory data is used to extract the vehicle image from the vehicle video, including: extracting the vehicle image corresponding to each GPS record from the vehicle video according to the timestamp information of each GPS record in the trajectory data, the time when the vehicle video starts recording, and the frame rate of the vehicle video.

[0014] As a further technical solution, the method further includes:

[0015] Obtaining sample data of different types of traffic participants, and using the sample data to train a YOLO v5s model to obtain a trained first model for extracting different types of traffic participants from the vehicle-mounted image;

[0016] Sample data of road isolation features are obtained, and the sample data is used to train the Deeplab v3+ model to obtain a trained second model for extracting road isolation features from the vehicle-mounted image to complete semantic segmentation.

[0017] As a further technical solution, the semantic segmentation results are used to screen the traffic participants within the current vehicle drivable area, including:

[0018] Binarize the semantic segmentation image;

[0019] The binarized image pixels are first expanded and then eroded;

[0020] Connected domains are marked based on the processed image, the area of ​​each connected domain is calculated, and connected domains whose areas do not meet the preset conditions are eliminated;

[0021] Perform straight line fitting based on the pixels in the retained connected domain to obtain the mask area;

[0022] The generated mask area is judged to intersect with the circumscribed rectangular frame of each extracted traffic participant, and the traffic participant targets with intersection are eliminated.

[0023] According to one aspect of the present invention, there is provided an urban traffic chaos measurement system based on vehicle trajectories and vehicle-mounted videos, comprising:

[0024] A first processing module, used for extracting a vehicle image from the vehicle video using the timestamp information in the trajectory data;

[0025] The second processing module is used to extract different types of traffic participants and road isolation features for segmenting the current vehicle driving area from the vehicle-mounted image, and screen the extracted traffic participants according to the segmentation results;

[0026] The third processing module is used to calculate the urban traffic chaos index based on the screening results and the information entropy formula;

[0027] The fourth processing module is used to bind the traffic chaos index with the urban road by using the trajectory data corresponding to the vehicle-mounted image and the map matching algorithm to obtain the traffic chaos degree of the urban road.

[0028] According to one aspect of the present invention specification, there is provided an electronic device, comprising: at least one processor, at least one memory and a communication interface; wherein the processor, memory and communication interface communicate with each other; the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the method.

[0029] According to one aspect of the present specification, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to execute the method described above.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] The present invention proposes a method for measuring urban traffic chaos based on vehicle trajectory and on-board video based on computer vision technology and information entropy theory. Firstly, the on-board image data is extracted from the on-board video using the timestamp information in the trajectory data; secondly, different types of traffic participants and road isolation features for segmenting the current vehicle driving area are extracted from the on-board image, and the traffic participants within the current vehicle driving area are screened; finally, the urban traffic chaos index is calculated using the information entropy formula, and the trajectory data corresponding to the on-board image and the map matching algorithm are used to realize the binding of the traffic chaos index with the urban roads.

[0032] The invention not only fills the gap in the measurement indicators and calculation framework of urban traffic chaos, but also provides new data indicators for urban traffic status monitoring, and further provides auxiliary decision-making data and technical method support for urban traffic congestion relief, traffic safety assurance and other aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief introduction is given below to the drawings used in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 A flow chart of a method for measuring urban traffic chaos based on vehicle trajectories and vehicle-mounted videos provided in an embodiment of the present invention.

[0035] Figure 2 A schematic diagram of a flow chart of calculating a city traffic chaos index according to a city traffic chaos measurement method based on vehicle trajectories and vehicle-mounted videos provided in an embodiment of the present invention.

[0036] Figure 3 A schematic diagram of a scenario for calculating the urban traffic chaos index provided by an embodiment of the present invention.

[0037] Figure 4 A schematic diagram of the structure of an urban traffic chaos measurement system based on vehicle trajectories and vehicle-mounted videos provided in an embodiment of the present invention.

[0038] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] It should be noted that:

[0040] In the era of intelligent connected cars, the popularity of on-board cameras has provided new data and ideas for urban traffic status monitoring, which has also made the joint mining of on-board images and vehicle trajectories a research hotspot: vehicle trajectories can be used to determine vehicle locations; on-board videos can reflect the traffic status of urban roads and assist in the precise positioning of vehicles in complex urban road environments. Therefore, based on the vehicle trajectories and on-board video data obtained by the dashcam, dynamic monitoring of urban traffic chaos can be achieved in a low-cost, long-time and wide-coverage manner.

[0041] The terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to the steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0042] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices. The flowcharts shown in the accompanying drawings are merely exemplary and do not necessarily include all the contents and operations / steps, nor do they necessarily have to be executed in the order described. For example, some operations / steps may be further decomposed, while some operations / steps may be combined or partially combined, so the actual execution order may change according to the actual situation.

[0043] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in 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. In addition, the technical features in the various embodiments or single embodiments provided by the present invention are arbitrarily combined with each other to form a new technical solution. This combination is not restricted by the sequence of steps and / or the structural composition mode, but must be based on the ability of ordinary technicians in this field to achieve. When the combination of technical solutions is contradictory or cannot be achieved, it should be considered that this combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0044] The embodiment of the present invention proposes a method for measuring urban traffic chaos based on vehicle trajectories and on-board videos based on computer vision technology and information entropy theory. The method can realize long-term and wide-area monitoring of urban traffic chaos, thereby providing a scientific basis for traffic planning and supervision.

[0045] The embodiment of the present invention provides a method for measuring urban traffic chaos based on vehicle trajectories and vehicle-mounted videos. Figure 1 As shown, the method includes: extracting vehicle images from vehicle videos using timestamp information in trajectory data; extracting different types of traffic participants and road isolation features for segmenting the current vehicle driving area from the vehicle images, and screening the extracted traffic participants according to the segmentation results; calculating the urban traffic chaos index based on the screening results in combination with the information entropy formula; using the trajectory data corresponding to the vehicle images and the map matching algorithm, binding the traffic chaos index to the urban roads, and obtaining the traffic chaos degree of the urban roads.

[0046] Taking the measurement of traffic chaos on some roads in Wuhan as an example, the specific implementation process is as follows: Figure 2 and Figure 3 As shown, the following steps are included:

[0047] Step 1: pre-process the collected vehicle trajectory data and vehicle video data. This step can be divided into the following steps:

[0048] Step 1.1, according to a vehicle trajectory map matching method integrating vehicle-mounted image semantics disclosed in Chinese patent application with application number 2022104913437 on August 30, 2022, the trajectory data is matched with the urban road network data to obtain a unique identifier of the road data corresponding to each trajectory point.

[0049] Step 1.2, extracting a vehicle image corresponding to each GPS record from the vehicle video according to the timestamp information of each GPS record, the time when the vehicle video starts recording, and the frame rate of the vehicle video.

[0050] It should be noted that the matching of trajectory data and urban road network data is to enable the calculated urban traffic chaos index to be bound to urban roads. This binding process can be achieved when the vehicle trajectory data and on-board video data are obtained (such as step 1.1 above), or it can be achieved after the urban traffic chaos index is calculated through the trajectory data corresponding to the on-board image and the map matching algorithm.

[0051] Step 2, data set preparation and model training, this step can be broken down into the following steps:

[0052] Step 2.1, based on the KITTI dataset, use the LabelImg tool to adjust the sample data. Specifically, bicycles and motorcycles are labeled together with the riders, and other samples such as cars, buses, trucks, and pedestrians are retained directly. The YOLO v5s model is trained using the labeled sample data to obtain the trained first model for extracting different types of traffic participants from vehicle-mounted images.

[0053] Step 2.2: Based on the panoramic data or driving image data obtained from the Internet, use the Labelme tool to annotate the five road isolation features in the image, including shoulder walls, isolation guardrails or isolation piles, curbstones, green plant isolation belts, and single and double yellow solid lines. Use the annotated sample data to train the Deeplab v3+ model, and obtain the trained second model for extracting road isolation features from vehicle-mounted images.

[0054] Step 3: Use the trained model to infer all vehicle images. This step can be divided into the following steps:

[0055] Step 3.1, using the model trained in step 2.1, identify traffic participants such as cars, buses, trucks, cyclists (including two-wheeled and three-wheeled bicycles), motorcyclists (including two-wheeled and three-wheeled electric vehicles or motorcycles), and pedestrians from the vehicle-mounted image and their circumscribed rectangular boxes in the vehicle-mounted image.

[0056] Step 3.2, using the model trained in step 2.2, extract road isolation features such as shoulder walls, isolation guardrails or isolation piles, curbs, green isolation belts, single and double yellow solid lines from the vehicle-mounted image, and obtain the semantic segmentation result image.

[0057] Step 4, using the semantic segmentation result image obtained in step 3.2 to screen the identified traffic participants, this step can be divided into the following steps:

[0058] Step 4.1, binarize the semantic segmentation image obtained in step 3.2, convert the pixels where the identified road isolation features are located to 255, and convert the other pixels to 0.

[0059] Step 4.2, the binarized image pixels are first expanded and then eroded to fill the holes in the connected pixels.

[0060] Step 4.3, based on the binary image processed in step 4.2, connected domains are marked, the area of ​​each connected domain is calculated, and connected domains whose area is less than 1 / 50 of the image area or located in the upper 1 / 4 and lower 1 / 4 of the image are eliminated.

[0061] Step 4.4, perform straight line fitting on the pixels in the connected domain retained in step 4.3, solve the intersection of the straight line and the connected domain circumscribed rectangle, calculate the slope of the fitted straight line based on the two intersection points, and draw straight lines perpendicular to the fitted straight line at the two intersection points. By judging the positive or negative of the slope, it can be determined whether the area above the fitted straight line is on the left or right side of the fitted straight line. Based on this, the area above the fitted line formed by the fitted straight line, the two vertical lines and the connected domain circumscribed rectangle is retained as the mask area.

[0062] Step 4.5, determine the intersection between the mask area generated in step 4.4 and the circumscribed rectangular frame of each traffic participant extracted in step 2, and eliminate the traffic participant targets that have intersections.

[0063] Step 5, count the number of each type of traffic participants in step 4, and calculate the urban traffic chaos index according to the following formula:

[0064]

[0065] Here, N refers to the number of different types of traffic participants. According to step 2.1, N=6. It represents the proportion of the i-th type of traffic participants, which is obtained by dividing the number of the i-th type of traffic participants in the image by the maximum number of times this type of traffic participant may appear in the image. The maximum number of times each type of traffic participant appears in the image is an empirical value, which can be slightly smaller than the actual number of times this type of traffic participant appears. In the embodiment of the present invention, the maximum possible number of times of cars, buses, trucks, cyclists, motorcyclists and pedestrians appear is 30, 10, 5, 15, 15, and 10, respectively. The degree of traffic chaos on the urban road represented by the vehicle-mounted image can be calculated by the formula.

[0066] Step 6: Based on steps 1-5, the road section information of each trajectory point and the traffic chaos index of the corresponding vehicle image can be obtained. The traffic chaos index on each road section is grouped according to time, and the total traffic chaos index on each road in each time period can be obtained. The maximum value in each group is taken as the traffic chaos index of the current road in the current time period, and the distribution map of the urban traffic chaos index in a certain time period can be obtained, thereby realizing the measurement of urban traffic chaos.

[0067] The implementation basis of each embodiment of the present invention is to implement programmed processing through a device with a processor function. Therefore, in engineering practice, the technical solutions and functions of each embodiment of the present invention are encapsulated into various modules. Based on this reality, on the basis of the above embodiments, an embodiment of the present invention provides an urban traffic chaos measurement system based on vehicle trajectory and vehicle-mounted video, which is used to execute the urban traffic chaos measurement method based on vehicle trajectory and vehicle-mounted video in the above method embodiment.

[0068] See also Figure 4 The system includes: a first processing module, which is used to extract vehicle images from vehicle videos using timestamp information in trajectory data; a second processing module, which is used to extract different types of traffic participants and road isolation features for segmenting the current vehicle driving area from the vehicle images, and screen the extracted traffic participants according to the segmentation results; a third processing module, which is used to calculate the urban traffic chaos index based on the screening results and in combination with the information entropy formula; a fourth processing module, which is used to bind the traffic chaos index to the urban roads using the trajectory data corresponding to the vehicle images and the map matching algorithm, and obtain the traffic chaos degree of the urban roads.

[0069] The urban traffic chaos measurement system based on vehicle trajectory and vehicle-mounted video provided by the embodiment of the present invention adopts the method of measuring the traffic chaos based on the vehicle trajectory and vehicle-mounted video to solve the problems existing in the long time series and wide coverage monitoring of urban traffic status. Figure 4 Several modules in it can realize dynamic monitoring of urban traffic chaos in a low-cost, long-time and wide-coverage manner based on the vehicle trajectory and on-board video data obtained by the driving recorder.

[0070] It should be noted that the system embodiment provided by the present invention is used to implement the method in the above method embodiment as well as the method in other method embodiments provided by the present invention. The only difference is that the corresponding functional modules are set. The principle is basically the same as the principle of the above system embodiment provided by the present invention. As long as the technical personnel in this field refer to the specific technical solutions in other method embodiments on the basis of the above system embodiment, obtain the corresponding technical means and the technical solutions composed of these technical means by combining technical features, and on the premise of ensuring the practicality of the technical solutions, they can improve the equipment in the above system embodiment to obtain the corresponding system embodiment, which is used to implement the methods in other method embodiments. For example:

[0071] Based on the content of the above system embodiment, as a preferred embodiment, the urban traffic chaos measurement system based on vehicle trajectory and vehicle-mounted video provided in the embodiment of the present invention further includes a fifth processing module for executing the following instructions:

[0072] The traffic chaos index on each road section is grouped according to time, and the total traffic chaos index on each road in each time period is obtained;

[0073] The maximum value in each group is taken as the traffic chaos index of the current road in the current time period, forming a distribution diagram of the urban traffic chaos index in a certain time period, and the degree of urban traffic chaos is measured according to the distribution diagram.

[0074] Based on the content of the above system embodiment, as a preferred embodiment, in the urban traffic chaos measurement system based on vehicle trajectory and vehicle-mounted video provided in the embodiment of the present invention, the first processing module is further used to execute the following instructions:

[0075] According to the timestamp information of each GPS record in the trajectory data, the time when the vehicle video starts recording, and the frame rate of the vehicle video, the vehicle image corresponding to each GPS record is extracted from the vehicle video.

[0076] Based on the content of the above system embodiment, as a preferred embodiment, the urban traffic chaos measurement system based on vehicle trajectory and vehicle video provided in the embodiment of the present invention, the second processing module is also used to execute the following instructions:

[0077] Obtaining sample data of different types of traffic participants, and using the sample data to train a YOLO v5s model to obtain a trained first model for extracting different types of traffic participants from the vehicle-mounted image;

[0078] Sample data of road isolation features are obtained, and the sample data is used to train the Deeplab v3+ model to obtain a trained second model for extracting road isolation features from the vehicle-mounted image to complete semantic segmentation.

[0079] Based on the content of the above system embodiment, as a preferred embodiment, the urban traffic chaos measurement system based on vehicle trajectory and vehicle video provided in the embodiment of the present invention, the second processing module is also used to execute the following instructions:

[0080] Binarize the semantic segmentation image;

[0081] The binarized image pixels are first expanded and then eroded;

[0082] Connected domains are marked based on the processed image, the area of ​​each connected domain is calculated, and connected domains whose areas do not meet the preset conditions are eliminated;

[0083] Perform straight line fitting based on the pixels in the retained connected domain to obtain the mask area;

[0084] The generated mask area is judged to intersect with the circumscribed rectangular frame of each extracted traffic participant, and the traffic participant targets with intersection are eliminated.

[0085] The method of the embodiment of the present invention is implemented by relying on electronic devices, so it is necessary to introduce the relevant electronic devices. Based on this purpose, the embodiment of the present invention provides an electronic device, such as Figure 5 As shown, the electronic device includes: at least one processor, a communication interface, at least one memory and a communication bus, wherein at least one processor, the communication interface and at least one memory communicate with each other through the communication bus, and the communication interface is respectively connected to at least one industrial camera and at least one GPS module. At least one processor calls the logic instructions in at least one memory to execute all or part of the steps of the method provided by each of the aforementioned method embodiments.

[0086] In addition, when the logic instructions in the above-mentioned at least one memory are implemented in the form of a software functional unit and sold or used as an independent product, they are stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or partly in other words, the part that contributes to the prior art or part of the technical solution is embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for enabling a computer device (a personal computer, a server, or a network device) to perform all or part of the steps of the method described in each method embodiment of the present invention. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, and various media for storing program codes.

[0087] The system embodiments described above are merely illustrative, wherein the units described as separate components are or are not physically separated, and the components shown as units are or are not physical units, located in one place, or distributed on multiple network units. Some or all of the modules are selected according to actual conditions to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement without creative effort.

[0088] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0090] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0091] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0092] In summary, the present invention discloses a method for measuring urban traffic chaos based on vehicle trajectory and on-board video. From the perspective of motor vehicles, the degree of traffic chaos on urban roads is evaluated based on the identification results of different types of traffic participants, filling the gap in the lack of indicators and calculation methods in the evaluation of urban traffic chaos. Specifically, based on the information entropy theory and the trajectory and on-board video data obtained from the driving recorder, the present invention proposes an indicator for measuring urban traffic chaos and its calculation framework: first, the on-board image data is extracted from the on-board video using the timestamp information in the trajectory data; second, different types of traffic participants and road isolation features for segmenting the current vehicle driving area are extracted from the on-board image, and the traffic participants in the current vehicle driving area are screened; finally, the urban traffic chaos index is calculated using the information entropy formula, and the trajectory data corresponding to the on-board image and the map matching algorithm are used to realize the binding of the traffic chaos index with the urban road. The urban traffic chaos measurement method proposed by the present invention can be further integrated in the driving recorder to provide auxiliary decision-making data and technical method support for alleviating urban congestion, ensuring traffic safety, and supporting urban planning and traffic management.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for measuring urban traffic chaos based on vehicle trajectories and on-board videos, characterized in that: include: Extract vehicle images from vehicle videos using timestamp information in trajectory data; Extract different types of traffic participants and road isolation features for segmenting the current vehicle driving area from the vehicle-mounted image, and screen the extracted traffic participants according to the segmentation results; According to the screening results, the urban traffic chaos index l is calculated by combining the information entropy formula tc : ， Where N refers to the number of different types of traffic participants, represents the proportion of the i-th type of traffic participants, and the number of the i-th type of traffic participants appearing in the image is t i Divide by the maximum number of times this type of traffic participant may appear in the image t max get; By using the trajectory data corresponding to the vehicle-mounted image and the map matching algorithm, the traffic chaos index is bound to the urban road to obtain the traffic chaos degree of the urban road, including: grouping the traffic chaos index on each road section according to time to obtain the total traffic chaos index on each road in each time period; taking the maximum value in each group as the traffic chaos index of the current road in the current time period, forming a distribution map of the urban traffic chaos index in a certain time period, and measuring the urban traffic chaos degree according to the distribution map.

2. The urban traffic chaos measurement method based on vehicle trajectory and vehicle-mounted video according to claim 1 is characterized in that: The vehicle image is extracted from the vehicle video using the timestamp information in the trajectory data, including: extracting the vehicle image corresponding to each GPS record from the vehicle video according to the timestamp information of each GPS record in the trajectory data, the time when the vehicle video starts recording, and the frame rate of the vehicle video.

3. The urban traffic chaos measurement method based on vehicle trajectory and vehicle video according to claim 1 is characterized in that: The method further comprises: Obtaining sample data of different types of traffic participants, and using the sample data to train a YOLO v5s model to obtain a trained first model for extracting different types of traffic participants from the vehicle-mounted image; Sample data of road isolation features are obtained, and the sample data is used to train the Deeplab v3+ model to obtain a trained second model for extracting road isolation features from the vehicle-mounted image to complete semantic segmentation.

4. The urban traffic chaos measurement method based on vehicle trajectory and vehicle video according to claim 3 is characterized in that: The semantic segmentation results are used to screen traffic participants within the current vehicle's drivable area, including: Binarize the semantic segmentation image; The binarized image pixels are first expanded and then eroded; Connected domains are marked based on the processed image, the area of ​​each connected domain is calculated, and connected domains whose areas do not meet the preset conditions are eliminated; Perform straight line fitting based on the pixels in the retained connected domain to obtain the mask area; The generated mask area is judged to intersect with the circumscribed rectangular frame of each extracted traffic participant, and the traffic participant targets with intersection are eliminated.

5. Urban traffic chaos measurement system based on vehicle trajectory and vehicle video, characterized by: include: A first processing module, used for extracting a vehicle image from the vehicle video using the timestamp information in the trajectory data; The second processing module is used to extract different types of traffic participants and road isolation features for segmenting the current vehicle driving area from the vehicle-mounted image, and screen the extracted traffic participants according to the segmentation results; The third processing module is used to calculate the urban traffic chaos index l based on the screening results and the information entropy formula tc : ， Where N refers to the number of different types of traffic participants, represents the proportion of the i-th type of traffic participants, and the number of the i-th type of traffic participants appearing in the image is t i Divide by the maximum number of times this type of traffic participant may appear in the image t max get; The fourth processing module is used to use the trajectory data corresponding to the vehicle-mounted image and the map matching algorithm to bind the traffic chaos index with the urban road to obtain the traffic chaos degree of the urban road, including: grouping the traffic chaos index on each road section according to time to obtain the total traffic chaos index on each road in each time period; taking the maximum value in each group as the traffic chaos index of the current road in the current time period, forming a distribution map of the urban traffic chaos index in a certain time period, and measuring the urban traffic chaos degree according to the distribution map.

6. An electronic device, characterized in that: include: At least one processor, at least one memory and a communication interface; wherein the processor, memory and communication interface communicate with each other; The memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the method according to any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, which cause the computer to execute the method of any one of claims 1 to 4.

Images