A method and system for monitoring the congestion state of intelligent transportation

Abstract

This application relates to the technical field of traffic status monitoring, and specifically relates to a method and system for monitoring the congestion status of intelligent transportation. The method includes: collecting traffic road images on the road surface in real time; evenly dividing the traffic road images into sub-images, and identifying each vehicle area in each sub-image; determining the local distribution coefficient of each vehicle area; obtaining the vehicle congestion area within each sub-image; analyzing the change trend of all the local distribution coefficients within each sub-image and the proportion of the vehicle congestion area to determine the road complexity of each sub-image; using the road complexity to determine the scale parameter in the image enhancement algorithm and performing image enhancement on the traffic road images; based on the enhanced traffic road images, combining with a neural network, obtaining the vehicle occupancy rate in the traffic road images, and determining the traffic congestion status at each moment. Thereby improving the accuracy of monitoring the traffic congestion status.

Description

Technical Field

[0001] This application relates to the technical field of traffic status monitoring, and specifically relates to a method and system for monitoring the congestion status of intelligent transportation. Background Art

[0002] With the improvement of living standards and the continuous growth of traffic demand, the problem of traffic congestion has become increasingly prominent, seriously affecting people's travel efficiency and the overall operation efficiency of the city. Especially during special periods such as holidays, the problem of traffic congestion is even more prominent. As a new type of traffic management model, intelligent transportation can better exert the transportation efficiency of the traffic system, which is of great significance for improving traffic operation efficiency and traffic safety.

[0003] In recent years, computer vision technology has developed rapidly, and image-based traffic monitoring methods have increasingly highlighted their unique advantages. By using high-definition cameras installed along the road to obtain real-time traffic images, automatic monitoring of traffic congestion conditions can be achieved. However, in the actual monitoring process, due to the different degrees and states of vehicle aggregation in different sections, when using traditional image processing technology for image enhancement, due to the difference in vehicle density and the change in driving patterns, if the same scale parameters are used, it is difficult to accurately highlight the detailed features in the image, thereby affecting the accuracy of traffic congestion status monitoring. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a method and system for monitoring the congestion status of intelligent transportation, and the specific technical solutions adopted are as follows:

[0005] In the first aspect, an embodiment of this application provides a method for monitoring the congestion status of intelligent transportation, and this method includes the following steps:

[0006] Collect real-time traffic road images on the road surface;

[0007] The process of monitoring the traffic congestion status based on the traffic road images is as follows:

[0008] Divide the traffic road images into sub-images evenly, and identify each vehicle area in each sub-image; analyze the distance relationship and driving direction difference between each vehicle area and its adjacent vehicle areas to obtain the local distribution coefficient of each vehicle area;

[0009] Based on the local distribution coefficients of all vehicle areas in each sub-image, determine the vehicle congestion areas in each sub-image; analyze the change trend of all the local distribution coefficients in each sub-image and the proportion of the vehicle congestion areas to determine the road complexity of each sub-image;

[0010] Determine the scale parameter in the image enhancement algorithm using the road complexity, and perform image enhancement on the traffic road image; based on the enhanced traffic road image, determine the traffic congestion status at each moment.

[0011] In one embodiment, the determination of each vehicle area includes:

[0012] Perform edge detection and connected component analysis on each sub-image to obtain each connected component, and use each connected component as each vehicle area.

[0013] In one embodiment, the determination of the local distribution coefficient includes:

[0014] For each sub-image, calculate the metric distance between the center coordinates of each vehicle area and its neighboring vehicle areas; calculate the sum value of the areas of each vehicle area and its neighboring vehicle areas; calculate the ratio of the sum value to the metric distance to obtain the fusion result of the ratio of each vehicle area to all its neighboring vehicle areas;

[0015] Based on the driving direction deviation between each vehicle area and all its neighboring vehicle areas, determine the direction offset degree of each vehicle area;

[0016] Combine the fusion result and the direction offset degree to obtain the local distribution coefficient of each vehicle area.

[0017] In one embodiment, the direction offset degree is the normalized result of the mean of the driving direction angles between each vehicle area and all its neighboring vehicle areas.

[0018] In one embodiment, the local distribution coefficient is the product of the fusion result and the direction offset degree.

[0019] In one embodiment, the determination of the vehicle congestion area includes:

[0020] Use the clustering algorithm to divide the local distribution coefficients of all vehicle areas in each sub-image into various categories, calculate the mean value of all the local distribution coefficients within each category, and mark the vehicle areas within the category with the maximum mean value as the vehicle congestion areas.

[0021] In one embodiment, the determination of the road complexity includes:

[0022] Calculate the average value of all the local distribution coefficients in each sub-image, obtain the proportion of the vehicle congestion area in all vehicle areas within each sub-image, and obtain the fitting line after arranging all the local distribution coefficients in each sub-image in ascending order;

[0023] The road complexity is positively correlated with both the average value and the proportion, and negatively correlated with the slope of the fitting line.

[0024] In one embodiment, the scale parameter is a negatively correlated mapping result of the road complexity.

[0025] In one embodiment, the determining the traffic congestion status at each moment includes:

[0026] Based on the enhanced traffic road image and combined with a neural network, the vehicle occupancy rate in the traffic road image is obtained. Specifically:

[0027] For the enhanced traffic road image at each moment, calculate the ratio of the number of pixel points in all vehicle regions to the number of all pixel points in the traffic road image as the vehicle occupancy rate on the road at each moment;

[0028] If the vehicle occupancy rate is greater than or equal to a preset threshold, it is determined that the traffic state at the corresponding moment is congested; otherwise, it is determined that it is not congested.

[0029] In a second aspect, an embodiment of the present application further provides an intelligent traffic congestion status monitoring system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method described in any one of the above are implemented.

[0030] The present application has at least the following beneficial effects:

[0031] The present application collects real-time traffic road images of the road surface; evenly divides the traffic road images into sub-images, and identifies each vehicle region in each sub-image; analyzes the distance relationship and driving direction difference between each vehicle region and its adjacent vehicle regions to obtain the local distribution coefficient of each vehicle region; the local distribution coefficient reflects the density of vehicles and the degree of chaos of vehicle driving within the local range of each vehicle region, improving the reliability of determining the congestion degree of the vehicle region; further, based on the local distribution coefficients of all vehicle regions in each sub-image, the vehicle congestion regions in each sub-image are determined; analyzes the change trend of all the local distribution coefficients in each sub-image and the proportion of the vehicle congestion regions to determine the road complexity of each sub-image; the road complexity reflects the complexity of the vehicle region distribution in each sub-image and reflects the possibility of vehicle congestion in the corresponding sub-image, improving the accuracy of judging the vehicle congestion state; uses the road complexity to determine the scale parameter in the image enhancement algorithm and performs image enhancement on the traffic road image; by flexibly adjusting the scale parameter in the image enhancement algorithm, the image enhancement effect is improved, and the detail features in the traffic road image are accurately highlighted, facilitating the determination of the traffic congestion state; based on the enhanced traffic road image and combined with a neural network, the vehicle occupancy rate in the traffic road image is obtained to determine the current traffic congestion state; ultimately, the accuracy of traffic congestion state monitoring is improved. Brief Description of the Drawings

[0032] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0033] Figure 1 It is a flowchart of the steps of a method for monitoring the congestion status of intelligent transportation provided by an embodiment of the present application;

[0034] Figure 2 It is a flowchart for determining the scale parameter. Detailed Embodiments

[0035] In order to further elaborate on the technical means and effects adopted by the present application to achieve the intended invention purpose, the following will, in conjunction with the drawings and preferred embodiments, describe in detail the specific embodiments, structures, features and effects of a method and system for monitoring the congestion status of intelligent transportation proposed according to the present application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs.

[0037] The following will specifically describe the specific solutions of a method and system for monitoring the congestion status of intelligent transportation provided by the present application in conjunction with the drawings.

[0038] Please refer to Figure 1 , which shows a flowchart of the steps of a method for monitoring the congestion status of intelligent transportation provided by an embodiment of the present application. The method includes the following steps:

[0039] S1, collect traffic road images on the road surface in real time.

[0040] In this embodiment, the congestion status of traffic roads in the city is monitored. First, high-definition cameras are evenly arranged along the road to capture traffic images of the traffic roads. The capture time interval of the high-definition cameras is 1 minute, and the obtained traffic road images are RGB color images. In order to facilitate the monitoring of the congestion status of traffic roads and reduce the subsequent calculation cost, the obtained RGB color traffic road images are converted into grayscale images by the weighted average method. The weighted average method is a well-known technology, and the specific process will not be elaborated here. The implementer can set the capture time interval according to the actual situation, and this embodiment does not limit it here.

[0041] S2, evenly divide the traffic road image into sub-images, and identify each vehicle area in each sub-image; analyze the distance relationship and driving direction difference between each vehicle area and its adjacent vehicle areas to obtain the local distribution coefficient of each vehicle area.

[0042] In order to further analyze the distribution state of motor vehicles in the local area of the traffic road image, in this embodiment, image segmentation technology is used to divide the collected traffic road image into N sub-images of equal size. In this embodiment, the number of N is set to 64, and the implementer can set it according to the actual situation, and this embodiment does not limit it here. Among them, the image segmentation technology is publicly known, and this embodiment will not elaborate on it in detail here.

[0043] First, take each sub-image of the traffic road image as input, and use edge detection and connected component analysis algorithms to obtain each connected component in each sub-image. Denote each connected component as each vehicle area, and use the center coordinates of the minimum bounding rectangle of each connected component to represent the position of each connected component. Among them, edge detection and connected component analysis are both well-known technologies, and this embodiment will not elaborate on them specifically.

[0044] Secondly, since the sizes of different types of vehicles are different and the vehicles in the sub-images may be incomplete due to image segmentation, in this embodiment, the number of pixel points in each connected component is counted as the area of each connected component. The purpose of analyzing the image features based on the distribution of connected components in the image is to reflect the congestion state characteristics of the local area of the road by analyzing the connected components in the local area in combination with the differences in the number of vehicles and vehicle types under the traffic congestion state.

[0045] Specifically, when the traffic road is in a congested state, due to traffic congestion, it is difficult for vehicles to move forward. Therefore, the vehicles in the traffic road image are densely distributed, the distance between vehicles is small, and the vehicles move slowly or even stop. And traffic congestion may also cause some motor vehicles to occupy the non-motor vehicle lane, further increasing the motor vehicle occupancy rate of the road, that is, increasing the local distribution density between the connected components in the traffic road image.

[0046] Therefore, taking the nth sub-image in the traffic road image as an example, based on the K-nearest neighbor search algorithm, the central position of each connected region in the nth sub-image is used as the input to obtain the nearest region of each connected region. In this embodiment, the number of the nearest neighbor connected regions is set to K = 8, and the implementer can set it according to the actual situation. And calculate the distance d between the central position of each connected region and the central position of the nearest neighbor connected region. When the traffic is congested, since the distance between vehicles is small, the value of d becomes smaller. However, due to the different sizes of vehicles on the traffic road, the sizes of the connected regions in the sub-image are inconsistent. When the vehicle is large, the area of the connected region corresponding to the motor vehicle will become larger, and thus the distance d between the connected regions will become larger. Therefore, considering the local density of the local area in the traffic road image during the actual driving process and the regional change differences caused by vehicle types, the congestion density of the local area is analyzed. Among them, the K-nearest neighbor search algorithm is a well-known existing technology, and the specific process will not be elaborated here.

[0047] In addition, traffic congestion will also make the running trajectories of vehicles unstable, and there are phenomena such as cutting in line and seizing lanes by some motor vehicles. However, when the traffic road is in a normal traffic state, there are fewer vehicles on the road at this time, the distance between vehicles is large, and thus the vehicle occupancy rate on the road is low, and the motor vehicle drives smoothly forward in the current driving lane, and there are few phenomena of cutting in line and changing lanes.

[0048] Based on the above analysis, this embodiment first analyzes based on the distribution state of the local area in the traffic road image. Considering that there are phenomena of cutting in line and seizing lanes by vehicles during traffic congestion, the phenomenon of cutting in line and seizing lanes will cause the motor vehicle to change its forward direction, making the difference in the forward direction between the motor vehicle cutting in line and seizing lanes and its nearest neighbor motor vehicle larger, and thus making the local area of the traffic road image more complex, that is, the behavior of cutting in line and changing lanes will increase the difference in the main direction between the connected region and its neighboring connected region in the traffic road image.

[0049] Therefore, taking the ith connected region in the nth sub-image in the traffic road image as an example, this embodiment uses the optical flow method to detect each connected region, that is, the driving direction of each vehicle. Among them, the optical flow method for detecting the driving direction of vehicles is a well-known existing technology, and this embodiment will not elaborate on it here. Calculate the local distribution coefficient of each vehicle region, specifically:

[0050] For each sub-image, calculate the metric distance between the central coordinates of each vehicle region and its neighboring vehicle regions; calculate the sum value of the areas of each vehicle region and its neighboring vehicle regions; calculate the ratio of the sum value to the metric distance, and obtain the fusion result of the ratio of each vehicle region to all its neighboring vehicle regions;

[0051] Determine the direction offset of each vehicle area based on the driving direction deviation between each vehicle area and all its neighboring vehicle areas; the direction offset is the normalized result of the mean of the driving direction angles between each vehicle area and all its neighboring vehicle areas;

[0052] Combine the fusion result and the direction offset to obtain the local distribution coefficient of each vehicle area.

[0053] It should be noted that fusion means combining multiple variables, and specifically, calculations can be performed in ways such as addition, multiplication, or a combination of addition and multiplication. In this embodiment, addition is used as the calculation method for fusion, and the Euclidean distance is used as the measurement of distance. Implementers can choose other feasible distance calculation methods according to the actual situation, and this embodiment does not limit it here.

[0054] Specifically, the specific calculation method of the local distribution coefficient of each vehicle area is as follows:

[0055] In the formula, MTC n,i is the local distribution coefficient of the i-th vehicle area in the n-th sub-image of the traffic road image, A n,i is the area of the i-th vehicle area in the n-th sub-image of the traffic road image, A n,i,j is the area of the j-th neighboring vehicle area of the i-th vehicle area in the n-th sub-image of the traffic road image, d n,i,j is the measurement distance between the i-th vehicle area and its j-th neighboring vehicle area in the n-th sub-image of the traffic road image, K is the number of neighboring vehicle areas of the i-th vehicle area in the n-th sub-image of the traffic road image, and in this embodiment, K = 8, is the mean of the driving direction angles between the i-th vehicle area and all its neighboring vehicle areas in the n-th sub-image of the traffic road image, Norm() is the normalization function. is the driving direction deviation, is the fusion result.

[0056] It should be understood that when the local area of the n-th sub-image of the traffic road image is relatively complex, the distance d n,i,j between the i-th connected domain and its j-th neighboring connected domain in the sub-image becomes smaller; however, due to the different sizes of different connected domains, a larger connected domain will make the distance d n,i,j between the centers of adjacent connected domains become larger. Therefore, in this embodiment, the area between adjacent connected domains is used as a weight to correct the phenomenon that when the distance between adjacent connected domains is relatively close, the distance d n,i,j becomes larger due to the larger area of the connected domain, that is, the smaller the distance d n,i,j between the i-th connected domain and its j-th neighboring connected domain, the larger the connected domain area A n,i +An,i,j The larger it is, the greater the local distribution density of the $i$-th connected region. At the same time, when traffic congestion occurs on a traffic road, some vehicles will cut in line and jostle for lanes, and this phenomenon will cause a change in the forward direction between the $i$-th vehicle region and its neighboring vehicle regions, that is, the driving direction deviation of the $i$-th vehicle region calculated becomes larger, and further the local distribution coefficient MTC of the $i$-th vehicle region in the $n$-th sub-image of the traffic road image finally calculated n,i is larger.

[0057] S3. Based on the local distribution coefficients of all vehicle regions in each sub-image, determine the vehicle congestion regions in each sub-image; analyze the change trend of all the local distribution coefficients in each sub-image and the proportion of the vehicle congestion regions to determine the road complexity of each sub-image.

[0058] Furthermore, since in a traffic road, the vehicle density is different between different positions, that is, there are large differences in the local distribution coefficients corresponding to different connected regions in the $n$-th sub-image, so arrange the local distribution coefficients of all vehicle regions in the $n$-th sub-image of the traffic road image from small to large, and denote the arranged data as the data sequence $\alpha$ of the $n$-th sub-image n . Using the data sequence $\alpha$ n as the input, perform linear fitting by the least squares method to obtain the slope $b$ of the fitting line n , and then calculate the mean value of the data sequence $\alpha$ n . The smaller the slope $b$ of the fitting line n and the larger the mean value of the local distribution coefficients of all vehicle regions in the $n$-th sub-image , the more complex the distribution between vehicle regions in the $n$-th sub-image, and the greater the possibility of traffic congestion.

[0059] Furthermore, using the data sequence $\alpha$ n as the input, perform clustering by the K-means clustering algorithm, set the number of clusters $K = 2$, and obtain the clustered data of the data sequence $\alpha$ n . Calculate the mean value of all local distribution coefficients in each cluster. Denote the cluster with the largest mean value as the crowded cluster, denote the vehicle regions corresponding to all local distribution coefficients in the crowded cluster as the vehicle congestion regions, and denote the cluster with the smallest mean value as the sparse cluster. Therefore, the more the number in the crowded cluster, the denser the local distribution of vehicle regions in the $n$-th sub-image. So in this embodiment, further calculate the proportion $r$ of the number of data in the crowded cluster to the total data volume of the data sequence $\alpha$ n . n Among them, the least squares method and the K-means clustering algorithm are both well-known existing technologies, and this embodiment will not elaborate on them here.

[0060] Based on the above analysis, calculate the road complexity of each sub-image, where the road complexity is positively correlated with the mean value and the above-mentioned ratio, and negatively correlated with the slope of the fitted straight line. The specific calculation method is as follows:

[0061] In the formula, TCBR n is the road complexity of the nth sub-image in the traffic road image, is the mean value of the local distribution coefficients of all vehicle regions in the nth sub-image in the traffic road image, and r n is the proportion of the number of data in the crowded clustering cluster of the nth sub-image in the traffic road image to the total data volume of the data sequence α n b n is the slope of the fitted straight line of the data sequence of the nth sub-image in the traffic road image. β is a preset value greater than 0 to avoid the denominator being 0. In this embodiment, β = 0.01, and the implementer can set it according to the actual situation, and this embodiment does not limit it here.

[0062] It should be understood that when traffic congestion occurs in the nth sub-image of the traffic road image, the local distribution density between vehicle regions in the nth sub-image increases, thereby increasing the average value of the local distribution coefficients corresponding to all vehicle regions in the calculated nth sub-image and the difference between the local distribution coefficients corresponding to each vehicle region in the nth sub-image is small, thereby making the slope b n of the fitted straight line of the calculated data sequence α n smaller; the more densely the vehicle regions are locally distributed in the nth sub-image, the greater the proportion of the number of vehicle regions in the crowded clustering cluster of the nth sub-image; thereby making the calculated road complexity TCBR n of the nth sub-image larger.

[0063] S4. Use the road complexity to determine the scale parameter in the image enhancement algorithm, and perform image enhancement on the traffic road image; based on the enhanced traffic road image, combine with a neural network to obtain the vehicle occupancy rate in the traffic road image, and determine the traffic congestion state at each moment.

[0064] Correspondingly, the road complexity of each sub-image in the traffic road image can be calculated. The road complexity fully considers the local distribution state between vehicle regions in the sub-image and the differences between the vehicle region distributions at different positions on the road. Therefore, the road complexity can accurately reflect the complexity of different regions in the traffic road image.

[0065] Further, in this embodiment, the traffic road image is filtered based on the road complexity and combined with the single-scale SSR algorithm. Since the greater the road complexity of the sub-image in the traffic road image, the more complex the local area of the sub-image is. Therefore, when the road complexity TCBR corresponding to the nth sub-image n is greater, a smaller scale parameter σ should be set to better highlight the local features of the image and retain more details. On the contrary, when the road complexity TCBR n corresponding to the nth sub-image is smaller, the road complexity is lower at this time, and the corresponding traffic state is smoother. At this time, the scale parameter can be adjusted to be lower than when the road complexity is higher, so as to highlight the global features of the image.

[0066] In addition, in this embodiment, the value range of the scale parameter σ in the single-scale SSR algorithm is 80 - 100, and the implementer can set the value range of the scale parameter according to the actual situation. Therefore, this embodiment performs a negative correlation mapping on the road complexity of each calculated sub-image, specifically, obtaining the reciprocal of the road complexity of each sub-image, and mapping the reciprocal to between 80 - 100 through the linear transformation method to obtain the scale parameter. Using the obtained scale parameter and combining with the single-scale SSR algorithm, each sub-image is enhanced, and finally, the traffic road image after image enhancement is obtained. Among them, the single-scale SSR algorithm and the linear transformation method are both existing well-known technologies, and this embodiment will not elaborate on them in detail here. The flowchart for determining the scale parameter is as Figure 2 shown.

[0067] Further, this embodiment monitors the traffic road congestion phenomenon, and uses a CNN neural network to extract each vehicle in the traffic road image after image enhancement to obtain the vehicle regions in the traffic road image after image enhancement. Among them, the loss function of the CNN neural network uses cross-entropy during training. The CNN neural network and the training process of the CNN neural network are both existing well-known technologies, and this embodiment will not elaborate on them in detail here. The implementer can choose other existing feasible neural networks by himself.

[0068] For each enhanced traffic road image at each moment, calculate the ratio of the number of pixel points in all vehicle regions in it to the number of all pixel points in the traffic road image as the vehicle occupancy rate on the road at each moment. If the vehicle occupancy rate is greater than or equal to the preset threshold T, it is determined that the traffic road state at this moment is congested; otherwise, it is determined that the traffic road state at this moment is not congested.

[0069] In this embodiment, T = 0.75, and the implementer can set it according to the actual situation, and this embodiment does not limit it here.

[0070] Based on the same inventive concept as the above method, an embodiment of the present application further provides an intelligent traffic congestion status monitoring system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above methods for monitoring the intelligent traffic congestion status are implemented.

[0071] It should be noted that: the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0072] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

[0073] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for monitoring the congestion status of intelligent transportation, characterized in that, The method includes the following steps: Collect traffic road images of the road surface in real time; The process of monitoring the traffic congestion state based on the traffic road images is as follows: Divide the traffic road image into sub-images evenly, and identify each vehicle area in each sub-image; for each sub-image, calculate the metric distance between the center coordinates of each vehicle area and its neighboring vehicle areas; calculate the sum of the areas of each vehicle area and its neighboring vehicle areas; calculate the ratio of the sum value to the metric distance to obtain the fusion result of the ratio of each vehicle area to all its neighboring vehicle areas, and take the normalized result of the average of the driving direction angles between each vehicle area and all its neighboring vehicle areas as the direction offset of each vehicle area, and determine the product of the fusion result and the direction offset as the local distribution coefficient of each vehicle area; Based on the local distribution coefficients of all vehicle areas in each sub-image, determine the vehicle congestion areas in each sub-image; analyze the change trend of all the local distribution coefficients in each sub-image and the proportion of the vehicle congestion areas to determine the road complexity of each sub-image; Use the road complexity to determine the scale parameter in the image enhancement algorithm and perform image enhancement on the traffic road image; based on the enhanced traffic road image, determine the traffic congestion state at each moment.

2. The intelligent traffic congestion state monitoring method according to claim 1, characterized in that The determination of each vehicle area includes: Perform edge detection and connected component analysis on each sub-image to obtain each connected component, and use each connected component as each vehicle area.

3. The intelligent traffic congestion state monitoring method according to claim 1, characterized in that, The determination of the vehicle congestion area includes: Use a clustering algorithm to divide the local distribution coefficients of all vehicle areas in each sub-image into various categories, calculate the average value of all the local distribution coefficients in each category, and mark the vehicle areas in the category with the maximum average value as the vehicle congestion areas.

4. The intelligent traffic congestion status monitoring method according to claim 1, characterized in that The determination of the road complexity includes: Calculate the average value of all the local distribution coefficients in each sub-image, obtain the proportion of the vehicle congestion areas in all vehicle areas in each sub-image, and obtain the fitting line after arranging all the local distribution coefficients in each sub-image in ascending order; The road complexity is positively correlated with both the average value and the proportion, and negatively correlated with the slope of the fitting line.

5. The intelligent traffic congestion state monitoring method according to claim 1, characterized in that, The scale parameter is the negative correlation mapping result of the road complexity.

6. The intelligent traffic congestion state monitoring method according to claim 1, characterized in that, The determination of the traffic congestion state at each moment includes: Based on the enhanced traffic road image and combined with a neural network, obtain the vehicle occupancy rate in the traffic road image, specifically: For the enhanced traffic road image at each moment, calculate the ratio of the number of pixel points of all vehicle areas in it to the number of all pixel points in the traffic road image as the vehicle occupancy rate on the road at each moment; If the vehicle occupancy rate is greater than or equal to a preset threshold, determine that the traffic state at the corresponding moment is congested, otherwise, determine it as non-congested.

7. An intelligent traffic congestion status monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1-6.

Images