Curve traffic jam evaluation system and method
Through the analysis based on the density gradient model, it is determined whether the vehicle density and average speed meet the Hopf bifurcation conditions, predict the changes in curve traffic states and select control solutions, which solves the problem of difficult to effectively analyze and predict curve traffic congestion states in the prior art, and achieves accurate prediction and control of curve traffic congestion states.
Patent Information
- Application Number
- CN202411971733.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-04-18
AI Technical Summary
The prior art is difficult to effectively analyze and predict curved traffic congestion, resulting in an increase in traffic accidents and environmental pollution.
Based on the density gradient model, by analyzing the vehicle density and average speed, we judge whether the Hopf bifurcation conditions of the density gradient model are met, so as to predict the changes in curve traffic state and select a control scheme to delay or eliminate congestion state.
Accurate prediction and control of traffic congestion status in curves has been achieved, reducing the risks of traffic accidents and environmental pollution.
Smart Images
Figure CN119851468A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of traffic congestion analysis, and in particular to a curve traffic congestion evaluation system and method. Background Art
[0002] Road congestion is a common problem in the road traffic system. It not only affects the smoothness of traffic, but also may cause traffic accidents and even have a negative impact on the environment. There are many reasons for road congestion, including too many vehicles, unreasonable road design, improper setting of traffic lights, etc. The existing way to average whether a road is congested is to measure the density and driving speed of vehicles. However, the speed and density of vehicles are non-line variables, which change with time and space. In order to solve this problem, bifurcation theory has attracted the attention of many researchers. Bifurcation theory is a mathematical theory that studies the behavior of nonlinear systems. It can be used to analyze and understand mutation phenomena in the system. It can be applied to the analysis of road congestion. By analyzing the nonlinear parameters in road traffic, it is possible to understand and analyze road traffic behavior and predict the congestion state of the road.
[0003] Since the speed of vehicles on curves is relatively slow and the driver's field of vision is limited, it is a road section that is prone to congestion. Therefore, we apply the bifurcation theory to the analysis and evaluation of the congestion status of curves and analyze the causes of congestion on curves. Summary of the invention
[0004] The present invention is based on a density gradient model and analyzes the conditions satisfying the Hopf bifurcation of the density gradient model, thereby obtaining the critical value causing the change in the curve traffic state and further analyzing the cause of the curve state change (from non-congested to congested).
[0005] The technical solution proposed by the present invention is: a method for evaluating traffic congestion on a curved road, the method comprising: Obtain road network data information from the database and convert the road network data information into vector data format; Collect high-definition video data within a preset time period of the road section to be tested at a set frequency; extract multiple identification features from the high-definition video data; According to the obtained identification features, the road network data matching the identification features of the road section to be tested are screened out from the road network data information to form a road network data set of the road section to be tested; Extracting multiple key road network features from the road network data set of the road section to be tested to form a key road network feature set, wherein the key road network features include the starting coordinates, the ending coordinates, the starting road name, the ending road name, the curve radius, the curve length, the number of lanes in the curve, and the speed limit of the curve; Analyze high-definition video data in combination with key road network features to obtain vehicle status data within the curve; Analyze vehicle status data to obtain vehicle density and average vehicle speed on the road section to be tested; Constructing a density gradient model with vehicle density and vehicle average speed as variables, performing bifurcation analysis through the density gradient model, and determining whether the obtained vehicle density and / or vehicle average speed meets the Hopf bifurcation condition of the density gradient model; According to the judgment result of the previous step, the corresponding control scheme is selected to delay or eliminate the congestion state.
[0006] Preferably, each frame of image is extracted from the video data using computer vision technology; A plurality of identification features are extracted from each frame of the image, wherein the identification features include a road name, a curve mark, and a ramp mark.
[0007] Preferably, extracting a plurality of identification features from each frame of image, wherein the identification features include road names, curve signs and ramp signs, comprises the following steps: Convert each extracted frame image into a grayscale image and use a convenient detection algorithm to highlight the edges in the image; Use the pre-trained Haar cascade classifier to detect the sign area in the image, and perform binarization on the detected sign area; Use morphological operations to improve character segmentation, use regular expressions to extract strings within the sign area, and obtain road names or ramp characters; Remove noise and correct spelling errors from the recognized string data; Convert each extracted frame image into HSV color space; In the HSV color space, separate the black area or the white area, and highlight the separated black area or the white area through morphological operations; Use OpenCV to detect contours, identify and extract arrows and arcs, and output curve recognition feedback values based on the recognition results. ; The initial value of the curve recognition feedback value is 0, and if the curve mark is successfully recognized, the curve recognition feedback value is assigned 1; Make the recognized character string and feedback value into recognition feature vector ,in, , Respectively represent the names of two roads connected by a curve.
[0008] Preferably, the step of selecting road network data matching the identification feature of the road section to be tested from the road network data information according to the acquired identification feature comprises the following steps: Get the recognition feature vector ; Select multiple key road network features to form a key road network feature vector ;in, Respectively represent the starting road name and the ending road name of the curve; Calculate the cosine similarity between the identification feature vector and the key road network feature vector. If the cosine similarity is greater than the similarity threshold, the key road network feature vector is considered to be related to the identification feature vector. According to the key network feature vector, the relevant network features are extracted from the key network feature set, and the elements in the key network vector are combined with the relevant network features to form the curve network feature vector of the tested section. ; in, Respectively represent the road name starting from the curve and the destination road name The starting and ending curves length, radius, number of lanes and speed limit; According to the name of the starting road, query the road network data related to the name of the starting road from the road network database to form a starting road network feature set, wherein the starting road network feature set includes a width of one, a number of lanes, a length, and a speed limit value of one of the starting road; According to the name of the destination road, the road network data related to the name of the destination road is queried from the road network database to form a destination road network feature set, which includes the width 2, the number of lanes 2, the length 2 and the speed limit value 2 of the starting road.
[0009] Preferably, the step of forming a road network data set of a road section to be tested comprises the following steps: Obtain the curve road network feature vector of the road section to be tested, the starting road network feature set and the end road network feature set; Select a starting road and an end road of a preset length and a curve to form a road section to be tested; Construct the road network dataset of the road section to be tested, specifically: Obtain the starting road network feature set and the end road network feature set; Modify the length of the starting road network feature set to a preset length; Modify the length 2 in the road network feature set of the destination road to the preset length; The modified starting road network feature set, the modified end road network feature set and the curve road network feature vector of the road section to be tested are used to form a road network data set of the road section to be tested.
[0010] Preferably, the step of analyzing the high-definition video data in combination with key road network features to obtain vehicle status data in a curve includes the following steps: Divide the high-definition video data of the road section to be monitored into multiple continuous frame images; Extract curve radius, curve length and speed limit value from key road network feature set; Combined with the curve radius and curve length, the continuous frame images are used to calculate the angular velocity, vehicle speed 1, and vehicle density 1 of the vehicle in the curve of the road section to be tested; Calculating a vehicle density 2 and a vehicle speed 2 of vehicles within a starting point road within a preset length; The vehicle density three and the vehicle speed three of the vehicles in the destination road within the preset length are calculated.
[0011] Preferably, the analyzing of the vehicle status data to obtain the vehicle density and the average speed of the vehicles on the road section to be tested comprises the following steps: Set the vehicle density threshold and speed threshold. If vehicle density 1, vehicle density 2 and vehicle density 3 all exceed the vehicle density threshold, the vehicle density of the road section to be tested will be ,in, Represent the weights of vehicle density 1, vehicle density 2, and vehicle density 3 respectively, They represent vehicle density one, vehicle density two and vehicle density three respectively; If the speeds 1, 2, and 3 are all less than the speed threshold, the average speed of the road section to be tested is ,in, They represent vehicle speed one, vehicle speed two and vehicle speed three respectively; If the speed 1, speed 2 and speed 3 are not all less than the speed threshold, the average speed of the road section to be tested is ,in Respectively represent the weights of vehicle speed 1, vehicle speed 2, and vehicle speed 3; The minimum value among vehicle density 1, vehicle density 2 and vehicle density 3 is selected as the critical vehicle density .
[0012] Preferably, constructing a density gradient model with vehicle density and vehicle average speed as variables, performing bifurcation analysis through the density gradient model, and judging whether the acquired vehicle density and / or vehicle average speed meets the Hopf bifurcation condition of the density gradient model comprises the following steps: Construct a density gradient model: ;in, is the optimal speed function; They represent vehicle density, vehicle speed, time parameter, and space parameter respectively; represents a sticky variable; ,in, is the maximum vehicle density, Indicates free speed.
[0013] A sticky variable threshold is set. If the sticky variable obtained after substituting the average vehicle speed and vehicle density of the road section to be tested is greater than the sticky variable threshold, it is judged that the input average vehicle speed and density meet the Hopf bifurcation condition of the gradient density model; that is, the average vehicle speed and / or vehicle density at this time is the transition point of the congestion state of the road section to be tested, that is, the road section to be tested is about to change from a non-congested state to a congested state; The selecting of a corresponding control scheme to delay or eliminate an unstable bifurcation point comprises: Reduce the number of vehicles entering the starting road of the road section to be tested to reduce vehicle density 2 and vehicle density 1; Reduce the number of vehicles entering the terminal road of the road section to be measured to reduce vehicle density three and measurement density one.
[0014] The present invention also provides a curve traffic congestion evaluation system, and the system is used to execute the curve traffic congestion evaluation method.
[0015] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for evaluating curve traffic congestion.
[0016] Beneficial effects of the present invention: 1. The present invention decomposes a plurality of continuous frame images from the high-definition video information of the road section to be measured, and obtains the density of vehicles in the curve by analyzing the continuous frame images. In addition, by combining the curve structure parameters obtained from the road network information, including the length and radius of the curve, the speed of the vehicle in the curve in the three sections of entering the curve section, in the curve, and exiting the curve section can be obtained. The measured vehicle density is processed and input into the density gradient model to determine whether the conditions for the Hopf bifurcation of the density gradient function are met, so as to predict the change of the road congestion state.
[0017] 2. The present invention obtains the name of the road, the curve identification mark and the ramp identification information from the high-definition video information through image processing technology, determines whether the road here is a curve, and queries the characteristics of the road from the road network database according to the obtained road name; the curve and the curve starting road and curve end road connected to the curve are used as the sections to be tested. In the analysis, the vehicle density and vehicle speed of the section before entering the curve are taken into account, and by assigning weight values, the degree of influence of the two on the congestion state in the curve is reflected, so that our analysis of curve congestion is more comprehensive. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 The present invention is a flow chart of a method for evaluating curve traffic congestion. DETAILED DESCRIPTION
[0019] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.
[0020] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.
[0021] refer to Figure 1 The technical solution provided by the present invention is: a method for evaluating curve traffic congestion, comprising the following steps: 1. Obtain road network data information from the database and convert the road network data information into vector data format; 2. Collect high-definition video data within a preset time period of the road section to be tested at a set frequency; extract multiple identification features from the high-definition video data, specifically: use computer vision technology to extract each frame of image from the video data; extract multiple identification features from each frame of image, the identification features including road names, curve signs and ramp signs.
[0022] Because the road name is usually indicated by the road sign on the ground or the road sign in the air. When obtaining the road name: Convert each extracted frame of image into a grayscale image, and use a convenient detection algorithm to highlight the edges in the image; use a pre-trained Haar cascade classifier to detect the sign area in the image, and perform binarization on the detected sign area; use morphological operations to improve the character segmentation effect, use regular expressions to extract the string in the sign area, and obtain the road name or ramp character; remove noise and correct spelling errors from the recognized string data. The obtained string is the road name.
[0023] On open roads, curve signs are usually indicated by ground signs and aerial signs. Curve signs are usually indicated by white turn arrows, black or yellow broken lines or curved lines. Therefore, when identifying curve signs, the following steps are used: Convert each extracted frame image into HSV color space; separate the black area or white area in the HSV color space, and highlight the separated black area or white area through morphological operation; Use OpenCV to detect contours, identify and extract arrows and arcs, and output curve recognition feedback values based on the recognition results. ; The initial value of the curve recognition feedback value is 0. If the curve mark is successfully recognized, the curve recognition feedback value is assigned 1.
[0024] Finally, the recognized string and feedback value are used to generate the recognition feature vector ,in, , Respectively represent the names of two roads connected by a curve.
[0025] 3. According to the obtained identification features, the road network data matching the identification features of the road section to be tested are selected from the road network data information to form a road network data set of the road section to be tested; the following steps are included: Get the recognition feature vector ; Select multiple key road network features to form a key road network feature vector ;in, Respectively represent the starting road name and the ending road name of the curve; Calculate the cosine similarity between the identification feature vector and the key road network feature vector. If the cosine similarity is greater than the similarity threshold, the key road network feature vector is considered to be related to the identification feature vector. According to the key network feature vector, the relevant network features are extracted from the key network feature set, and the elements in the key network vector are combined with the relevant network features to form the curve network feature vector of the tested section. ;in, Respectively represent the road name starting from the curve and the destination road name The starting and ending curves length, radius, number of lanes and speed limit; According to the name of the starting road, query the road network data related to the name of the starting road from the road network database to form a road network feature set of the starting road, wherein the road network feature set of the starting road includes a width of one, a number of lanes of one, a length of one, and a speed limit of one of the starting road; according to the name of the end road, query the road network data related to the name of the end road from the road network database to form a road network feature set of the end road, wherein the road network feature set of the end road includes a width of two, a number of lanes of two, a length of two, and a speed limit of two of the starting road; Obtain the curve road network feature vector of the road section to be tested, the starting road network feature set, and the end road network feature set.
[0026] Select the starting road, the end road and the curve of the preset length to form the road section to be tested; construct the road network dataset of the road section to be tested, specifically: Obtain the starting road network feature set and the end road network feature set; modify the length one in the starting road network feature set to a preset length; modify the length two in the end road network feature set to a preset length; use the modified starting road network feature set and the modified end road network feature set as well as the curved road network feature vector of the section to be tested to form a network data set for the section to be tested.
[0027] 4. Extract multiple key road network features from the road network data set of the road section to be tested to form a key road network feature set, wherein the key road network features include the starting coordinates, end coordinates, starting road name, end road name, curve radius, curve length, number of lanes in the curve and curve speed limit.
[0028] 5. Analyze the high-definition video data in combination with key road network features to obtain vehicle status data in the curve, including the following steps: divide the high-definition video data of the road section to be monitored into multiple continuous frame images; extract the curve radius, curve length and speed limit value from the key road network feature set; Combined with the curve radius and curve length, continuous frame images are used to calculate the angular velocity, vehicle speed one, and vehicle density one of vehicles in the curve of the tested section; vehicle density two and vehicle speed two of vehicles in the starting road within the preset length are calculated; vehicle density three and vehicle speed three of vehicles in the end road within the preset length are calculated.
[0029] The preset length here can be selected as needed, extending from the connection point with the curve to the starting road and the end road respectively for a distance, for example, 200 meters.
[0030] 6. Analyze vehicle status data to obtain the vehicle density and average speed of the road section to be tested; set the vehicle density threshold and speed threshold. If vehicle density 1, vehicle density 2 and vehicle density 3 all exceed the vehicle density threshold, the vehicle density of the road section to be tested is increased to 1. ,in, Represent the weights of vehicle density 1, vehicle density 2, and vehicle density 3 respectively, They represent vehicle density one, vehicle density two and vehicle density three respectively; If the speeds 1, 2, and 3 are all less than the speed threshold, the average speed of the road section to be tested is ,in, They represent vehicle speed one, vehicle speed two and vehicle speed three respectively; If the speed 1, speed 2 and speed 3 are not all less than the speed threshold, the average speed of the road section to be tested is ,in Respectively represent the weights of vehicle speed 1, vehicle speed 2, and vehicle speed 3; The minimum value among vehicle density 1, vehicle density 2 and vehicle density 3 is selected as the critical vehicle density .
[0031] 7. Construct a density gradient model with vehicle density and vehicle average speed as variables, perform bifurcation analysis through the density gradient model, and determine whether the obtained vehicle density and / or vehicle average speed meets the Hopf bifurcation condition of the density gradient model.
[0032] Specifically: Construct a density gradient model: ;in, is the optimal speed function; They represent vehicle density, vehicle speed, time parameter, and space parameter respectively; represents a sticky variable; ,in, is the maximum vehicle density, represents free speed; A sticky variable threshold is set. If the sticky variable obtained after substituting the average vehicle speed and vehicle density of the road section to be tested is greater than the sticky variable threshold, the input average vehicle speed and density are judged to meet the Hopf bifurcation condition of the gradient density model; that is, the average vehicle speed and / or vehicle density at this time is the transition point of the congestion state of the road section to be tested, that is, the road section to be tested is about to change from a non-congested state to a congested state.
[0033] Hopf bifurcation is an important nonlinear dynamic phenomenon that usually occurs in a system of differential equations with nonlinear coupling terms. When a certain parameter changes, the stability of the system will change, resulting in significant changes in the behavior of the system.
[0034] In Hopf bifurcation, this transition is usually associated with oscillation phenomenon, so Hopf bifurcation is also called oscillatory bifurcation. For example, a differential equation with nonlinear coupling terms, where μ is a control parameter. This equation describes a two-degree-of-freedom system on a plane, whose equilibrium point (0,0) is unstable. When the value of μ changes, the stability of the system changes, resulting in a significant change in the behavior of the system. Specifically, when μ exceeds a certain critical value, the equilibrium point will undergo Hopf bifurcation, which means that the system switches from one stable state to another, and a periodic oscillation solution appears. The existence of Hopf bifurcation may cause traffic flow to change from a stable state to an oscillatory state, thereby causing traffic congestion. On curved roads, due to factors such as road curvature and limited vision, the interaction between vehicles is more complex and more likely to trigger the Hopf bifurcation phenomenon. Therefore, we use the Hopf bifurcation theory to study the congestion phenomenon of road systems and obtain the bifurcation points that cause road traffic to change state.
[0035] 8. According to the judgment result of the previous step, select the corresponding control scheme to delay or eliminate the congestion state. Reduce the number of vehicles entering the starting road of the section to be tested to reduce vehicle density 2 and vehicle density 1; reduce the number of vehicles entering the terminal road of the section to be tested to reduce vehicle density 3 and measurement density 1.
[0036] The present invention also provides a curve traffic congestion evaluation system, and the system is used to execute the curve traffic congestion evaluation method.
[0037] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for evaluating curve traffic congestion.
[0038] In the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present application are executed. It should be noted that the computer-readable medium mentioned above in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.
[0039] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0040] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be subject to any changes or modifications.
Claims
1. A method for evaluating traffic congestion on a curved road, characterized in that: The method comprises: Obtain road network data information from the database and convert the road network data information into vector data format; Collect high-definition video data within a preset time period of the road section to be tested at a set frequency; extract multiple identification features from the high-definition video data; According to the obtained identification features, the road network data matching the identification features of the road section to be tested are screened out from the road network data information to form a road network data set of the road section to be tested; Extracting multiple key road network features from the road network data set of the road section to be tested to form a key road network feature set; the key road network features include the starting point coordinates, the end point coordinates, the starting road name, the end road name, the curve radius, the curve length, the number of lanes in the curve and the curve speed limit; Analyze high-definition video data in combination with key road network features to obtain vehicle status data within the curve; Analyze vehicle status data to obtain vehicle density and average vehicle speed on the road section to be tested; Constructing a density gradient model with vehicle density and vehicle average speed as variables, performing bifurcation analysis through the density gradient model, and determining whether the obtained vehicle density and / or vehicle average speed meets the Hopf bifurcation condition of the density gradient model; According to the judgment result of the previous step, the corresponding control scheme is selected to delay or eliminate the congestion state.
2. A curve traffic congestion evaluation method according to claim 1, characterized in that: Use computer vision techniques to extract each frame of image from video data; A plurality of identification features are extracted from each frame of the image, wherein the identification features include a road name, a curve mark, and a ramp mark.
3. A curve traffic congestion evaluation method according to claim 2, characterized in that: The step of extracting a plurality of identification features from each frame of image, wherein the identification features include road names, curve signs, and ramp signs, comprises the following steps: Convert each extracted frame image into a grayscale image and use a convenient detection algorithm to highlight the edges in the image; Use the pre-trained Haar cascade classifier to detect the sign area in the image, and perform binarization on the detected sign area; Use morphological operations to improve character segmentation, use regular expressions to extract strings within the sign area, and obtain road names or ramp characters; Remove noise and correct spelling errors from the recognized string data; Convert each extracted frame image into HSV color space; In the HSV color space, separate the black area or the white area, and highlight the separated black area or the white area through morphological operations; Use OpenCV to detect contours, identify and extract arrows and arcs, and output curve recognition feedback values based on the recognition results. ; The initial value of the curve recognition feedback value is 0, and if the curve mark is successfully recognized, the curve recognition feedback value is assigned 1; Make the recognized character string and feedback value into recognition feature vector ,in, , Respectively represent the names of two roads connected by a curve.
4. A curve traffic congestion evaluation method according to claim 3, characterized in that: The method of selecting road network data matching the identification feature of the road section to be tested from the road network data information according to the obtained identification feature comprises the following steps: Get the recognition feature vector ; Select multiple key road network features to form a key road network feature vector ;in, Respectively represent the starting road name and the ending road name of the curve; Calculate the cosine similarity between the identification feature vector and the key road network feature vector. If the cosine similarity is greater than the similarity threshold, it is considered that the key road network feature vector is related to the identification feature vector. According to the key network feature vector, the relevant network features are extracted from the key network feature set, and the elements in the key network vector are combined with the relevant network features to form the curve network feature vector of the tested section. ; in, Respectively represent the road name starting from the curve and the destination road name The starting and ending curves length, radius, number of lanes and speed limit; According to the name of the starting road, query the road network data related to the name of the starting road from the road network database to form a starting road network feature set, wherein the starting road network feature set includes a width of one, a number of lanes, a length, and a speed limit value of one of the starting road; According to the name of the destination road, the road network data related to the name of the destination road is queried from the road network database to form a destination road network feature set, which includes the width 2, the number of lanes 2, the length 2 and the speed limit value 2 of the starting road.
5. A curve traffic congestion evaluation method according to claim 4, characterized in that: The step of forming a road network data set for a road section to be tested comprises the following steps: Obtain the curve road network feature vector of the road section to be tested, the starting road network feature set and the end road network feature set; Select a starting road and an end road of a preset length and a curve to form a road section to be tested; Construct the road network dataset of the road section to be tested, specifically: Obtain the starting road network feature set and the end road network feature set; Modify the length of the starting road network feature set to a preset length; Modify the length 2 in the road network feature set of the destination road to the preset length; The modified starting road network feature set, the modified end road network feature set and the curve road network feature vector of the road section to be tested are used to form a road network data set of the road section to be tested.
6. A curve traffic congestion evaluation method according to claim 5, characterized in that: The method of analyzing the high-definition video data in combination with key road network features to obtain vehicle status data in a curve includes the following steps: Divide the high-definition video data of the road section to be monitored into multiple continuous frame images; Extract curve radius, curve length and speed limit value from key road network feature set; Combined with the curve radius and curve length, the continuous frame images are used to calculate the angular velocity, vehicle speed 1, and vehicle density 1 of the vehicle in the curve of the road section to be tested; Calculating a vehicle density 2 and a vehicle speed 2 of vehicles within a starting point road within a preset length; The vehicle density three and the vehicle speed three of the vehicles in the destination road within the preset length are calculated.
7. A curve traffic congestion evaluation method according to claim 6, characterized in that: The step of analyzing the vehicle status data to obtain the vehicle density and average speed of the vehicle on the road section to be tested includes the following steps: Set the vehicle density threshold and speed threshold. If vehicle density 1, vehicle density 2 and vehicle density 3 all exceed the vehicle density threshold, the vehicle density of the road section to be tested will be ,in, Represent the weights of vehicle density 1, vehicle density 2, and vehicle density 3 respectively, They represent vehicle density one, vehicle density two and vehicle density three respectively; If the speeds 1, 2, and 3 are all less than the speed threshold, the average speed of the road section to be tested is ,in, They represent vehicle speed one, vehicle speed two and vehicle speed three respectively; If the speeds 1, 2, and 3 are not all less than the speed threshold, the average speed of the road section to be tested is ,in Respectively represent the weights of vehicle speed 1, vehicle speed 2, and vehicle speed 3; The minimum value among vehicle density 1, vehicle density 2 and vehicle density 3 is selected as the critical vehicle density .
8. A curve traffic congestion evaluation method according to claim 7, characterized in that: The step of constructing a density gradient model with vehicle density and vehicle average speed as variables, performing bifurcation analysis through the density gradient model, and determining whether the acquired vehicle density and / or vehicle average speed meets the Hopf bifurcation condition of the density gradient model comprises the following steps: Construct a density gradient model: ;in, is the optimal speed function; They represent vehicle density, vehicle speed, time parameter, and space parameter respectively; represents a sticky variable; ,in, is the maximum vehicle density, represents free speed; A sticky variable threshold is set. If the sticky variable obtained after substituting the average vehicle speed and vehicle density of the road section to be tested is greater than the sticky variable threshold, it is judged that the input average vehicle speed and density meet the Hopf bifurcation condition of the gradient density model; that is, the average vehicle speed and / or vehicle density at this time is the transition point of the congestion state of the road section to be tested, that is, the road section to be tested is about to change from a non-congested state to a congested state; The selecting of a corresponding control scheme to delay or eliminate an unstable bifurcation point comprises: Reduce the number of vehicles entering the starting road of the road section to be tested to reduce vehicle density 2 and vehicle density 1; Reduce the number of vehicles entering the terminal road of the road section to be measured to reduce vehicle density three and measurement density one.
9. A curve traffic congestion evaluation system, characterized in that: The system is used to execute a curve traffic congestion evaluation method as described in any one of claims 1-8 above.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a curve traffic congestion evaluation method as described in any one of claims 1 to 8.