Congestion analysis method and system based on ETC portal data

Abstract

The invention belongs to the technical field of intelligent traffic, and particularly relates to a congestion analysis method and system based on ETC portal data. The method comprises the steps of determining ETC portal data monitoring equipment, acquiring traffic data, performing data fusion, performing congestion analysis and performing result display and application. The system comprises a traffic flow information acquisition module, a data analysis and processing module, a congestion identification module and a user interaction module which are connected in sequence, according to the method and the system, portal plate identification equipment and portal transaction equipment of an ETC portal on a provincial expressway are selected to construct an omnibearing monitoring network, real-time monitoring and data acquisition of road conditions are realized, the real-time monitoring mode ensures the real-time performance and accuracy of data, and the real-time monitoring effect of the ETC portal on the provincial expressway is improved. A traffic management department can know the real-time condition of a road in time, a constructed omnibearing monitoring network can comprehensively cover the whole road network, and comprehensive detection and analysis of traffic congestion are realized.

Description

Technical Field

[0001] This invention belongs to the field of intelligent transportation technology, specifically relating to a congestion analysis method and system based on ETC gantry data. Background Technology

[0002] To vigorously develop intelligent transportation, promote the digital transformation of highways, accelerate the construction and development of intelligent highways, improve the level of highway construction and operation management services, and provide information support for emergency response on expressways; it is possible to comprehensively control the status of the road network, improve the road network management capabilities, and enhance the level of public information services, ultimately achieving "knowable, measurable, controllable, and serviceable" expressway management, making road network operation safer and more efficient, public travel more convenient and comfortable, traffic management more scientific and intelligent, and smart roads more green and economical.

[0003] Highway congestion algorithms are an important application of smart highways. Existing traffic congestion analysis methods and systems collect traffic data and analyze road conditions using traffic monitoring equipment such as cameras and geomagnetic sensors placed at key road nodes. While this method provides some traffic congestion information, the limited number of data acquisition points makes it difficult to comprehensively cover the entire road network, resulting in blind spots in traffic congestion monitoring and analysis, and leading to biased analysis results. Summary of the Invention

[0004] This invention addresses the problem that existing traffic congestion analysis methods and systems cannot fully cover the entire road network, resulting in blind spots in traffic congestion monitoring and analysis, and leading to biased analysis results. It proposes a congestion analysis method and system based on ETC gantry data, which combines historical traffic data, gantry license plate data, and gantry transaction data for comprehensive judgment, improving the accuracy and reliability of the analysis and providing decision support for traffic management.

[0005] The technical solution claimed by this invention is as follows:

[0006] A congestion analysis method based on ETC gantry data includes the following steps:

[0007] S1: Determine ETC gantry data monitoring equipment: Select gantry identification equipment and gantry transaction equipment for ETC gantries on highways within the province to build a comprehensive monitoring network;

[0008] S2: Traffic Data Acquisition: The road images captured by the gantry license plate recognition device in S1 are analyzed in real time using optical flow method to detect and track vehicles on the road and generate gantry license plate recognition data; at the same time, the gantry transaction device acquires gantry transaction data; the gantry license plate recognition data includes key information such as the vehicle's motion trajectory, speed, and acceleration; the gantry transaction data includes real-time vehicle speed, traffic flow, and more detailed three-dimensional vehicle information;

[0009] S3: Data Fusion: The data fusion technology is used to integrate the gantry transaction data and gantry transaction data obtained in S2. Through algorithm processing, the gantry identification data and gantry transaction data are mutually supplemented and verified to obtain a road traffic dataset.

[0010] S4: Congestion Analysis: Based on the traffic dataset obtained in S3, congestion analysis algorithms are used to make judgments. By comprehensively analyzing historical traffic data, manually configured road conditions, and weather conditions obtained from external API interfaces and transferred to the internal network, multi-dimensional information is analyzed to determine the current road congestion status and further predict future traffic trends.

[0011] S5: Results Display and Application: Real-time display of congestion analysis data obtained from S4.

[0012] Preferably, the gantry sign recognition device in S1 serves as an image capture device, capturing high-definition images of the road; the gantry transaction device acquires traffic parameters such as vehicle speed and traffic flow.

[0013] Preferably, the location of the ETC gantry is determined based on the current installation location of highway gantry within the province.

[0014] S2 specifically involves: analyzing the road image using optical flow in image processing technology; identifying vehicle information using image recognition technology; detecting and tracking the displacement vectors of vehicle motion feature points on the road to calculate the optical flow field; analyzing and interpreting the optical flow field to obtain the target vehicle's trajectory and speed information; determining congestion based on the analysis of the vehicle's trajectory; and estimating the vehicle's direction and speed by calculating the instantaneous velocity field of pixels and features in the image, thereby obtaining the vehicle's dynamic information. The specific formula is as follows:

[0015]

[0016] In the formula: I represents pixel brightness; u represents the displacement of each pixel in the image in the horizontal direction (x-axis direction), which is the x-component of the optical flow vector v; v represents the displacement of each pixel in the image in the vertical direction (y-axis direction), which is the y-component of the optical flow vector v; t represents time;

[0017] Rearranging equation (1) yields expressions for u and v with respect to the coordinates of pixels x and y and time t. The rearranged equation is:

[0018]

[0019] Each pixel is derived from the image data. The value of is used to obtain the optical flow vector of the pixel through this equation, thereby analyzing the motion characteristics of the image to obtain key information such as the vehicle's motion trajectory, speed, and acceleration; the vehicle information includes license plate and color.

[0020] S3 specifically involves: analyzing the sequence of road images using the univariate image difference method in data fusion technology to detect and quantify changes between images, particularly changes in vehicle movement patterns related to traffic congestion. Road images are captured in real-time by a gantry-based sign recognition device, forming a series of temporally continuous image sequences. In this sequence, the time interval between two adjacent images is the reciprocal of the system's frame rate. By first outlining the pixels representing vehicle features, and then comparing them pixel by pixel, the difference between them is calculated. This difference reflects the changes in pixel values ​​in the image, thereby revealing changes in vehicle movement and traffic flow. The specific formula is as follows:

[0021] D(x,y,t)=I(x,y,t2)-I(x,y,t1) (2)

[0022] In the formula: D(x,y,t) represents the pixel value in the difference image at time t corresponding to pixel coordinates (x,y), and I(x,y,t2) and I(x,y,t1) represent the pixel values ​​in the two images at times t2 and t1 corresponding to pixel coordinates (x,y), respectively. The calculated difference image is analyzed to extract features related to traffic congestion, namely, vehicle stagnation and increased lane occupancy. The obtained traffic congestion features are then fused with the basic mileage and vehicle travel time obtained by the gantry trading equipment to calculate the interval speed and traffic flow, in order to form a more comprehensive road traffic dataset.

[0023] In the above method, S4 includes the following steps:

[0024] S41: Congestion Index Calculation: Based on the road traffic dataset obtained in S3, calculate the indicators reflecting the degree of road congestion; the indicators include: average vehicle speed and traffic density;

[0025] S42: Congestion Judgment: Based on the indicators calculated in S41, the congestion analysis algorithm is used to determine the current road congestion status. By comparing the real-time average vehicle speed and traffic flow density data with preset thresholds, if one or more parameters exceed or fall below the corresponding threshold, the road segment is determined to be in a congested state.

[0026] S43: Comprehensive judgment based on multi-dimensional information: Based on the congestion status judged in S42, the congestion analysis algorithm is further used to combine historical traffic data, manually configured road conditions, and weather conditions obtained through the interface to comprehensively judge the congestion status and obtain the congestion analysis results;

[0027] S44: Result Display: Visualize the congestion analysis results obtained from S43.

[0028] In the above method, S42 specifically involves: using a congestion analysis algorithm based on a threshold-based judgment method to determine the congestion status by setting thresholds for vehicle speed and traffic flow parameters. This is done by comparing real-time average vehicle speed and traffic flow density data with preset thresholds. If one or more parameters exceed or fall below their corresponding thresholds, the road segment is determined to be congested. The relationship between traffic flow and speed is as follows:

[0029]

[0030] Where: V represents speed; k is a constant; Q represents flow rate; the relationship between traffic flow density and flow rate is:

[0031] Q = ρ × V 平均 (4)

[0032] Where: Q represents flow rate; ρ represents traffic flow density; V 平均 It represents the average speed, which is determined by calculating traffic flow and density, and compared with a threshold to determine the current road congestion status.

[0033] The present invention also provides a congestion analysis system based on ETC gantry data, comprising a traffic flow information collection module, a data analysis and processing module, a congestion identification module and a user interaction module connected in sequence;

[0034] The traffic flow information collection module selects gantry sign recognition equipment and gantry transaction equipment of ETC gantries on provincial highways to build a comprehensive monitoring network; the gantry sign recognition equipment captures road images and generates gantry sign recognition data; the gantry transaction equipment collects gantry transaction data.

[0035] The data analysis and processing module performs real-time analysis of the road images using optical flow, detects and tracks vehicles on the road, and obtains key information such as vehicle trajectory, speed, and acceleration. Furthermore, it employs data fusion technology to integrate gantry transaction data and data collected by gantry license plate recognition equipment. Through algorithm processing, the gantry license plate recognition data and gantry transaction data complement and verify each other to obtain a more comprehensive and accurate road traffic dataset.

[0036] The congestion identification module uses the traffic dataset and congestion analysis algorithm to make judgments. It performs comprehensive analysis of multi-dimensional information, including historical traffic data, manually configured road conditions, and weather conditions obtained from external API interfaces and transferred to the internal network, to determine the current road congestion status and further predict future traffic trends.

[0037] The user interaction module displays the congestion analysis data identified by the congestion identification module in real time and supports interface interaction.

[0038] Preferably, the system further includes an early warning and handling module connected to the congestion identification module; the early warning and handling module automatically triggers an early warning mechanism based on the congestion status identified by the congestion identification module, sends early warning information to traffic management departments and relevant personnel, and provides corresponding handling suggestions according to the congestion situation.

[0039] Beneficial effects

[0040] This invention provides a congestion analysis method and system based on ETC gantry data. The method includes: selecting gantry identification devices and gantry transaction devices of ETC gantries on provincial highways to construct a comprehensive monitoring network, realizing real-time monitoring and data acquisition of road conditions. This real-time monitoring method ensures the timeliness and accuracy of the data, enabling traffic management departments to understand the real-time road conditions in a timely manner. The constructed comprehensive monitoring network can fully cover the entire road network, realizing comprehensive detection and analysis of traffic congestion. This solves the problem that existing traffic congestion analysis methods and systems are unable to fully cover the entire road network, resulting in blind spots in traffic congestion monitoring and analysis, and leading to biased analysis results. Real-time analysis of road images using optical flow methods detects and tracks vehicles on the road, acquiring key information such as vehicle trajectory, speed, and acceleration. Data fusion technology integrates gantry transaction data and data collected by gantry license plate recognition devices. Through algorithmic processing, the gantry license plate recognition data and gantry transaction data complement and verify each other, enabling comprehensive and accurate acquisition of key information on vehicle trajectory, speed, and traffic flow, providing reliable data support for congestion analysis. Furthermore, fusing image data acquired by gantry license plate recognition devices with traffic parameters acquired by gantry transaction devices forms a comprehensive road traffic dataset. This data fusion method not only enriches the data dimensions but also improves the comprehensive analytical capabilities. By applying congestion analysis algorithms, multi-dimensional information such as historical traffic data, manually configured road conditions, and weather conditions obtained through interfaces can be comprehensively considered to accurately determine road congestion status. This comprehensive analytical capability makes the analysis results more accurate and reliable, providing more scientific decision support for traffic management. The display and application of congestion analysis results provide powerful auxiliary decision support for traffic managers, allowing them to intuitively understand road congestion and take corresponding traffic management measures based on the analysis results. Attached Figure Description

[0041] Figure 1 This is a flowchart of the congestion analysis method based on ETC gantry data according to an embodiment of the present invention.

[0042] Figure 2This is a flowchart illustrating the congestion analysis method based on ETC gantry data according to an embodiment of the present invention.

[0043] Figure 3 This is a schematic diagram of a congestion analysis system based on ETC gantry data, according to an embodiment of the present invention.

[0044] Figure 4 This is a flowchart of the congestion analysis system based on ETC gantry data according to an embodiment of the present invention. Specific implementation methods

[0046] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions will be further described clearly and completely below with reference to the accompanying drawings.

[0047] First set of embodiments: Congestion analysis method based on ETC gantry data

[0048] This set of embodiments provides a congestion analysis method based on ETC gantry data, such as Figure 1-2 As shown, it includes the following steps:

[0049] S1: Determine ETC gantry data monitoring equipment: Select gantry sign recognition equipment and gantry transaction equipment for ETC gantries on provincial highways to construct a comprehensive monitoring network; the gantry sign recognition equipment serves as an image capture device, capturing high-definition images of the road; the gantry transaction equipment collects gantry transaction data to obtain vehicle speed and traffic flow in real time, perceive the distance between vehicles, and obtain more detailed three-dimensional vehicle information; the location of the ETC gantries is determined based on the current installation location of the gantry gantries on provincial highways; in a specific embodiment of the present invention, the gantry sign recognition equipment is selected as the image capture device to capture high-definition images of the road, and the gantry transaction equipment is selected to obtain traffic parameters such as vehicle speed and traffic flow, ensuring that the equipment can work normally and accurately acquire data, adjusting the angle and focal length of the gantry sign recognition equipment to make the acquired images clear and without blind spots, transmitting the gantry sign recognition data and gantry transaction data to the monitoring congestion analysis system, and accurately transmitting the data to the system for subsequent processing and analysis, adjusting and optimizing the equipment according to the actual situation to adapt to changes in traffic flow and road conditions.

[0050] S2: Traffic Data Acquisition: Real-time analysis of road images captured by the gantry sign recognition device described in S1 is performed using optical flow to detect and track vehicles on the road, acquiring key information such as vehicle trajectory, speed, and acceleration. Specifically, the road images are analyzed using optical flow in image processing technology; vehicle information is identified using image recognition technology; the displacement vectors of vehicle motion feature points on the road are detected and tracked to calculate the optical flow field; the trajectory and speed information of the target vehicles are obtained through analysis and interpretation of the optical flow field; congestion is assessed based on the analysis of vehicle trajectories; and the vehicle's direction and speed are estimated by calculating the instantaneous velocity field of pixels and features in the image, thereby acquiring dynamic vehicle information. The specific formula is as follows:

[0051]

[0052] In the formula: I represents pixel brightness; u represents the displacement of each pixel in the image in the horizontal direction (x-axis direction), which is the x-component of the optical flow vector v; v represents the displacement of each pixel in the image in the vertical direction (y-axis direction), which is the y-component of the optical flow vector v; t represents time;

[0053] Rearranging equation (1) yields expressions for u and v with respect to the coordinates of pixels x and y and time t. The rearranged equation is:

[0054]

[0055] Each pixel is derived from the image data. The value of the value is used to obtain the optical flow vector of the pixel through the equation, thereby analyzing the motion characteristics of the image and obtaining key information such as the vehicle's motion trajectory, speed, and acceleration. At the same time, the gantry trading equipment obtains real-time vehicle speed, traffic flow, and more detailed three-dimensional vehicle information, providing intuitive data support for traffic managers and strong support for analysis in complex traffic scenarios; the vehicle information includes license plate and color.

[0056] S3: Data Fusion: Data fusion technology is used to integrate the gantry transaction data and gantry signage. Through algorithmic processing, the gantry signage data and gantry transaction data are mutually supplemented and verified to obtain a more comprehensive and accurate road traffic dataset. Specifically, the univariate image difference method in data fusion technology is used to analyze the sequence of road images to detect and quantify changes between images, especially changes in vehicle movement patterns related to traffic congestion. Road images are captured in real time by gantry signage devices, forming a series of time-continuous image sequences. In the sequence, the time interval between two adjacent images is the reciprocal of the system's frame rate. By first outlining the pixels of vehicle features, and then comparing them pixel by pixel, the difference between them is calculated. The difference reflects the changes in pixel values ​​in the image, thereby revealing the changes in vehicle movement and traffic flow. The specific formula is as follows:

[0057] D(x,y,t)=I(x,y,t2)-I(x,y,t1) (2)

[0058] In the formula: D(x,y,t) represents the pixel value in the difference image at time t corresponding to pixel coordinates (x,y), and I(x,y,t2) and I(x,y,t1) represent the pixel values ​​in the two images at times t2 and t1 corresponding to pixel coordinates (x,y), respectively. The calculated difference image is analyzed to extract features related to traffic congestion, namely, vehicle stagnation and increased lane occupancy. The obtained traffic congestion features are then fused with the basic mileage and vehicle travel time obtained by the gantry trading equipment to calculate the interval speed and traffic flow, in order to form a more comprehensive road traffic dataset.

[0059] The road traffic dataset includes: vehicle trajectory, speed, vehicle speed, and traffic flow.

[0060] S4: Congestion Analysis: Based on the traffic dataset obtained in S3, congestion analysis algorithms are used to determine the current road congestion status and predict future traffic trends. This involves comprehensive analysis of historical traffic data, manually configured road conditions, and weather information obtained from external API interfaces and transferred to the internal network for multi-dimensional information analysis. The analysis includes the following steps:

[0061] S41: Congestion Index Calculation: Based on the road traffic dataset obtained in S3, calculate the indicators reflecting the degree of road congestion; the indicators include: average vehicle speed and traffic density;

[0062] S42: Congestion Assessment: Based on the indicators calculated in S41, a congestion analysis algorithm is used to assess the current road congestion status. A congested state is determined when the average vehicle speed is below a set threshold and the traffic flow density exceeds a set threshold. Specifically, the congestion analysis algorithm uses a threshold-based assessment method to determine congestion status by setting thresholds for vehicle speed and traffic flow parameters. Real-time average vehicle speed and traffic flow density data are compared with preset thresholds. If one or more parameters exceed or fall below their corresponding thresholds, the road segment is determined to be congested. The relationship between traffic flow and speed is as follows:

[0063]

[0064] Where: V represents speed; k is a constant; Q represents flow rate; the relationship between traffic flow density and flow rate is:

[0065] Q = ρ × V 平均 (4)

[0066] Where: Q represents flow rate; ρ represents traffic flow density; V 平均 It represents the average speed, and by calculating traffic flow and density and comparing it with a threshold, it accurately judges the current road congestion status.

[0067] S43: Comprehensive judgment based on multi-dimensional information: Based on the congestion status judged in S42, the congestion analysis algorithm is further used to combine historical traffic data, manually configured road conditions, and weather conditions obtained through the interface to comprehensively judge the congestion status and obtain the congestion analysis results;

[0068] S44: Display of Judgment Results: Visualize the congestion analysis results obtained from S43 to provide traffic managers with intuitive congestion information.

[0069] S5: Results Display and Application: Real-time display of congestion analysis data obtained from S4. This intuitive congestion information can provide decision support for traffic managers, helping them to better allocate traffic resources, optimize traffic flow, and adjust road management plans according to real-time traffic conditions to alleviate traffic congestion.

[0070] Second embodiment: Congestion analysis system based on ETC gantry data

[0071] This set of embodiments provides a congestion analysis system based on ETC gantry data, such as Figure 3-4 As shown, it includes a traffic flow information collection module, a data analysis and processing module, a congestion identification module, and a user interaction module connected in sequence;

[0072] The traffic flow information collection module selects gantry sign recognition equipment and gantry transaction equipment of ETC gantries on provincial highways to build a comprehensive monitoring network; the gantry sign recognition equipment captures road images and generates gantry sign recognition data; the gantry transaction equipment collects gantry transaction data.

[0073] The data analysis and processing module performs real-time analysis of the road images using optical flow, detects and tracks vehicles on the road, and obtains key information such as vehicle trajectory, speed, and acceleration. Furthermore, it employs data fusion technology to integrate gantry transaction data and data collected by gantry license plate recognition equipment. Through algorithm processing, the gantry license plate recognition data and gantry transaction data complement and verify each other to obtain a more comprehensive and accurate road traffic dataset.

[0074] The congestion identification module uses the traffic dataset and congestion analysis algorithm to make judgments. It performs comprehensive analysis of multi-dimensional information, including historical traffic data, manually configured road conditions, and weather conditions obtained from external API interfaces and transferred to the internal network, to determine the current road congestion status and further predict future traffic trends.

[0075] The user interaction module displays the congestion analysis data identified by the congestion identification module in real time and supports interface interaction.

[0076] The system also includes an early warning and response module connected to the congestion identification module; the early warning and response module automatically triggers an early warning mechanism based on the congestion status identified by the congestion identification module, sends early warning information to traffic management departments and relevant personnel, and provides corresponding response suggestions according to the congestion situation.

[0077] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made to it in form and detail without departing from the scope defined by the claims of the present invention.

Claims

1. A congestion analysis method based on ETC gantry data, characterized in that: The steps include: S1: Determine the ETC gantry data monitoring equipment: Select the gantry sign recognition equipment and gantry transaction equipment of the ETC gantries on the provincial highways to build a comprehensive monitoring network; S2: Obtaining traffic data: The road image captured by the gantry plate recognition device in S1 is analyzed in real time by the optical flow method, the vehicles on the road are detected and tracked, and the gantry plate recognition data is generated; at the same time, the gantry transaction device obtains the gantry transaction data; the gantry plate recognition data includes key information such as the movement trajectory, speed, and acceleration of the vehicle; the gantry transaction data includes real-time vehicle speed, traffic volume, and more detailed three-dimensional vehicle information; S3: Data fusion: Data fusion technology is used to integrate the gantry transaction data obtained in S2 and the gantry transaction data. Through algorithm processing, the gantry license plate recognition data and the gantry transaction data complement and verify each other to obtain a road traffic data set; S4: Congestion analysis: Based on the traffic data set obtained in S3, the congestion analysis algorithm is used to make judgments. By transferring the historical traffic data, manually configured road conditions, and weather conditions obtained through the external network API interface to the internal network, a comprehensive analysis of multi-dimensional information is performed to determine the current road congestion situation and further predict future traffic trends; S5: Result display and application: Real-time display of the congestion analysis data obtained in S4.

2. The congestion analysis method based on ETC gantry data according to claim 1 is characterized in that: The gantry plate recognition device described in S1 is used as an image capture device to capture high-definition images of the road; the gantry transaction device obtains traffic parameters such as vehicle speed and traffic flow.

3. The congestion analysis method based on ETC gantry data according to claim 1 or 2, characterized in that: The position of the ETC gantry is determined according to the current installation position of the gantry on the provincial highway.

4. The congestion analysis method based on ETC gantry data according to claim 3 is characterized in that: S2 specifically includes: analyzing the road image by the optical flow method in the image processing technology, identifying the vehicle information by the image recognition technology, detecting and tracking the displacement vector of the vehicle motion feature points on the road to calculate the optical flow field, obtaining the motion trajectory and speed information of the target vehicle by analyzing and interpreting the optical flow field, judging the congestion situation based on the analysis of the vehicle motion trajectory, and estimating the motion direction and speed of the vehicle by calculating the instantaneous velocity field of the pixel points and features in the image, thereby obtaining the dynamic information of the vehicle. The specific formula is as follows: Where: I represents pixel brightness; u represents the horizontal displacement (x-axis direction) of each pixel in the image, which is the x component of the optical flow vector v; v represents the vertical displacement (y-axis direction) of each pixel in the image, which is the y component of the optical flow vector v; t represents time; The expression of u and v with respect to the x, y pixel coordinates and time t is obtained by transposing the terms in formula (1). The transposed formula is: According to the image data, each pixel and The value of is used to obtain the optical flow vector of the pixel point through the equation, so as to analyze the motion characteristics of the image and obtain the key information of the vehicle's motion trajectory, speed, and acceleration; the vehicle information includes the license plate and color.

5. The congestion analysis method based on ETC gantry data according to claim 1 or 4, characterized in that: S3 is specifically: using the univariate image difference method in data fusion technology to analyze the sequence of road images to detect and quantify the changes between images, especially the changes in vehicle motion patterns related to traffic congestion, and capturing road images in real time through the gantry license plate recognition device to form a series of time-continuous image sequences; in the sequence, the interval time length between two adjacent images is the inverse of the system's frame rate, and the pixels of vehicle features are first framed and then compared pixel by pixel to calculate the difference between them. The difference reflects the change in pixel values ​​in the image, thereby revealing the changes in vehicle motion and traffic flow. The specific formula is: D(x,y,t)=I(x,y,t2)-I(x,y,t1) (2) Where: D(x,y,t) represents the pixel value in the difference image corresponding to time t at the pixel coordinate (x,y), I(x,y,t2) and I(x,y,t1) represent the pixel values ​​in the two images corresponding to time t2 and t1 at the pixel coordinate (x,y), respectively. The calculated difference image is analyzed to extract the features related to traffic congestion, namely, stagnation of vehicle movement and increase in lane occupancy. The obtained traffic congestion features are integrated with the basic mileage obtained by the gantry trading equipment, the interval speed and traffic volume calculated by the vehicle travel time, so as to form a more comprehensive road traffic data set.

6. The congestion analysis method based on ETC gantry data according to claim 5 is characterized in that: S4 includes the following steps: S41: Calculation of congestion index: Based on the road traffic data set obtained in S3, calculate an index reflecting the degree of road congestion; the index includes: average vehicle speed and traffic flow density; S42: Congestion judgment: Based on the indicators calculated in S41, the congestion analysis algorithm is used to judge the congestion status of the current road. By comparing the real-time average vehicle speed and traffic flow density data with the preset thresholds, if one or more parameters exceed or fall below the corresponding thresholds, it is determined that the road section is in a congested state; S43: Comprehensive judgment of multi-dimensional information: Based on the congestion status judged in S42, a congestion analysis algorithm is further used to combine historical traffic data, manually configured road conditions, and multi-dimensional information of weather conditions obtained through an interface to comprehensively judge the congestion status and obtain a congestion analysis result; S44: Display of judgment results: Visually display the congestion analysis results obtained in S43.

7. The congestion analysis method based on ETC gantry data according to claim 1 is characterized in that: S42 is specifically: using the congestion analysis algorithm based on the threshold judgment method to judge the congestion state by setting the threshold of the vehicle speed and traffic flow parameters, and by comparing the real-time vehicle average speed and traffic flow density data with the preset thresholds, if one or more parameters exceed or fall below the corresponding thresholds, it is determined that the road section is in a congested state, and the relationship between the flow and the speed is: Where: V represents speed; k is a constant; Q represents flow rate; the relationship between traffic flow density and flow rate is: Q=ρ×V 平均 (4) Where: Q represents flow; ρ represents traffic flow density; V 平均 It indicates the average speed, which is determined by the calculated traffic flow and density, and compared with the threshold to determine the current road congestion.

8. A congestion analysis system based on ETC gantry data, characterized in that: It includes a traffic information collection module, a data analysis and processing module, a congestion identification module and a user interaction module which are connected in sequence; The traffic information collection module selects the gantry sign recognition equipment and gantry transaction equipment of the ETC gantries on the provincial highway to build an all-round monitoring network; the gantry sign recognition equipment captures road images and generates gantry sign recognition data; the gantry transaction equipment collects gantry transaction data; The data analysis and processing module uses the optical flow method to perform real-time analysis on the road image, detect and track vehicles on the road, and obtain key information such as the vehicle's motion trajectory, speed, and acceleration; and further uses data fusion technology to integrate the gantry transaction data and the data collected by the gantry license plate recognition device. Through algorithm processing, the gantry license plate recognition data and the gantry transaction data complement and verify each other, thereby obtaining a more comprehensive and accurate road traffic data set; The congestion identification module uses the congestion analysis algorithm to make a judgment based on the traffic data set, and conducts a comprehensive analysis of multi-dimensional information by transferring historical traffic data, manually configured road conditions, and weather conditions obtained through the external network API interface to the internal network to judge the current road congestion situation and further predict future traffic trends; The user interaction module displays the congestion analysis data identified by the congestion identification module in real time and supports interface interaction.

9. The congestion analysis system based on ETC gantry data according to claim 8, characterized in that: The system also includes an early warning and disposal module connected to the congestion identification module; the early warning and disposal module automatically triggers an early warning mechanism based on the congestion situation identified by the congestion identification module, sends early warning information to the traffic management department and relevant personnel, and provides corresponding disposal suggestions based on the congestion situation.

Images