Road state monitoring system based on video image analysis

Abstract

The invention relates to a road state monitoring system based on video image analysis, which belongs to the technical field of road monitoring and comprises the following steps of: measuring the speed of a target truck vehicle on a key road section of an express lane; when the vehicle speed is lower than a preset speed threshold value, capturing a scene to obtain a captured video image; analyzing the traffic condition of the scene through the snapshot video image; and judging whether the target truck has traffic violation according to the traffic condition. According to the invention, the problem that traffic violation may be misjudged due to the fact that the influence caused by lane occupation cannot be judged according to actual traffic conditions in the prior art is solved. And identifying vehicle distribution information behind the target truck vehicle in the expressway, and predicting the probability of traffic congestion at present by adopting a Bayesian network model according to the vehicle distribution information. According to the method, the accuracy of traffic condition analysis is improved by using the Bayesian network model, and reference is provided for traffic decision making.

Description

Technical Field

[0001] The invention belongs to the technical field of road monitoring and relates to a road state monitoring system based on video image analysis. Background Art

[0002] Since trucks are generally large and carry relatively heavy cargo, they tend to travel at a slower speed. If they occupy the overtaking lane for a long time, it will pose a significant safety hazard to other traffic participants. Because in this case, other vehicles cannot overtake on the left and can only choose to overtake on the right. This driving style greatly increases the risk of multiple vehicle accidents such as rear-end collisions and scratches.

[0003] At present, local traffic police mainly rely on reports from the public and some checkpoints to take photos. However, this checkpoint photo-taking method can only determine whether the target vehicle occupies the lane, but cannot determine the impact of occupying the lane based on actual traffic conditions, which may lead to misjudgment of traffic violations. Summary of the invention

[0004] The present invention provides a road state monitoring system based on video image analysis, which aims to analyze the road state of key sections by using machine learning methods, and solve the problem of misjudgment of traffic violations in the prior art by quantifying the impact of lane occupation by target truck vehicles on traffic conditions.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The present application provides a road condition monitoring system based on video image analysis, including a speed measurement module, a capture module, an analysis module and a decision module, wherein the speed measurement module, the capture module, the analysis module and the decision module are communicatively connected, wherein:

[0007] The speed measurement module is used to measure the speed of target truck vehicles on key sections of the fast lane;

[0008] The capture module captures the scene to obtain a captured video image when the vehicle speed is lower than a preset speed threshold;

[0009] The analysis module analyzes the traffic conditions on site through the captured video image;

[0010] The decision module determines whether the target truck vehicle has traffic violations based on the traffic conditions.

[0011] Furthermore, the speed measurement of vehicles on the key section of the fast lane includes the following steps:

[0012] S1. Data collection: Install high-definition cameras at key sections, covering the entire lane from the start detection line to the end detection line;

[0013] S2, object detection: The YOLO algorithm is used to process the collected video stream to detect and identify the target truck vehicle;

[0014] S3, speed calculation: After the vehicle is detected, the vehicle position changes in consecutive frames are analyzed to calculate the current driving speed.

[0015] Furthermore, the key road sections include main roads, traffic intersections, expressway and highway entrances and exits, congestion hotspots, mountain roads and slope areas, and construction or obstacle areas.

[0016] Furthermore, the YOLO algorithm is used to process the collected video stream to detect and identify the vehicle, including the following steps:

[0017] S21. Data preparation: Collect image or video data containing vehicles, annotate the data using annotation tools, draw the bounding box of the vehicle, and annotate each box with corresponding labels to generate the annotation files required for training;

[0018] S22, data preprocessing: converting the labeled data into a text file format;

[0019] S23, Environment Configuration: Configure the training environment and install the TensorFlow or PyTorch deep learning framework;

[0020] S24, model training: set the configuration items for training, including network structure, input image size, learning rate, and batch size, and then run the training script, monitor the loss value and performance indicators, and ensure that the model gradually converges and reaches the expected accuracy;

[0021] S25. Model evaluation: After training, use the test set to evaluate the model and judge the performance of the model by calculating the mAP, Precision, and Recall indicators.

[0022] Furthermore, the captured video image is captured simultaneously by high-position and low-position cameras; wherein the high-position camera is used to identify the traffic flow and vehicle distribution on the road, and the low-position camera is used to identify vehicle details; the vehicle details include vehicle license plate and vehicle type.

[0023] Furthermore, analyzing the traffic conditions at the scene through the captured video image comprises the following steps:

[0024] T1. Identify the vehicle distribution information behind the target truck on the expressway, wherein the vehicle distribution information includes the number of vehicles, vehicle speeds, and corresponding vehicle behaviors; the vehicle behaviors include acceleration, deceleration, lane change, and overtaking;

[0025] T2. Predicting the probability of current traffic congestion based on the vehicle distribution information.

[0026] Furthermore, in step T2, predicting the probability of current traffic congestion according to the vehicle distribution information includes the following steps:

[0027] T21. Collecting traffic condition data of trucks occupying fast lanes in historical periods, wherein the traffic condition data includes vehicle distribution information and traffic congestion information; the traffic congestion information is divided into congested and non-congested;

[0028] T22, determine the Bayesian network structure with vehicle distribution information as the parent node and traffic congestion information as the child node;

[0029] T23, use maximum likelihood estimation to determine the conditional probability distribution between parent node and child node parameters, and complete the training of the Bayesian network model;

[0030] T24. Input the current vehicle distribution into the trained Bayesian network model to predict the probability of current traffic congestion.

[0031] Furthermore, judging whether the target truck vehicle has traffic violations based on the traffic conditions is specifically: when the probability of the current traffic congestion exceeds a preset first congestion threshold, judging whether the target truck vehicle has traffic violations.

[0032] Furthermore, when the decision module determines that the target truck vehicle has violated the traffic rules, it reminds the target truck vehicle not to occupy the fast lane through the traffic indicator light and retains the captured video image as the basis for the violation.

[0033] Furthermore, when the probability of the current traffic congestion exceeds a preset second congestion threshold, an alarm is automatically sent to the traffic management department to request handling of the traffic congestion.

[0034] Beneficial effects of the present invention:

[0035] (1) Measure the speed of a target truck vehicle on a key section of a fast lane; when the vehicle speed is lower than a preset speed threshold, capture the scene to obtain a captured video image; analyze the traffic conditions on the scene through the captured video image; and determine whether the target truck vehicle has violated a traffic violation based on the traffic conditions. The present invention solves the problem that the prior art cannot determine the impact of lane occupation based on actual traffic conditions, resulting in possible misjudgment of traffic violations.

[0036] (2) Identify the vehicle distribution information behind the target truck on the expressway, and use the Bayesian network model to predict the probability of current traffic congestion based on the vehicle distribution information. The present invention uses the Bayesian network model to improve the accuracy of traffic situation analysis and provide a reference for traffic decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0038] Figure 1 It is a structural diagram of a road condition monitoring system based on video image analysis in the present invention.

[0039] Figure 2 The figure is a flowchart of the steps of the test module in one embodiment of the present invention.

[0040] Figure 3 The present invention is a flow chart for predicting the probability of current traffic congestion based on vehicle distribution information. DETAILED DESCRIPTION

[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0042] See also Figure 1-Figure 3 The present application provides a road condition monitoring system based on video image analysis, including a speed measurement module, a capture module, an analysis module and a decision module, wherein the speed measurement module, the capture module, the analysis module and the decision module are communicatively connected, wherein:

[0043] The speed measurement module is used to measure the speed of target truck vehicles on key sections of the fast lane;

[0044] In this embodiment, the speed measurement module can timely detect and alarm the situation of slow lane occupation by real-time monitoring of vehicle speed, thereby improving the traffic efficiency of the road. The system uses a high-definition camera to capture vehicle images of a specific section of road, and performs object detection through a deep learning algorithm to ensure the accuracy of speed calculation. The system not only records data such as the speed, time and location of the vehicle, but also supports historical data query to provide data support for traffic management and planning. The dynamically adjusted slow threshold can be flexibly changed according to the actual traffic flow situation to ensure the effectiveness of monitoring. In addition, the speed measurement module is linked with equipment such as traffic lights, and can automatically adjust the signal when necessary to alleviate traffic congestion. By integrating into the intelligent traffic management system, the speed measurement module helps improve overall traffic efficiency and reduce traffic accidents and delays caused by slow driving. The implementation of this system not only optimizes traffic flow, but also provides a strong basis for further traffic law enforcement and promotes the development of dynamic intelligent traffic management.

[0045] Furthermore, the speed measurement of vehicles on the key section of the fast lane includes the following steps:

[0046] S1. Data collection: Install high-definition cameras at key sections to monitor passing vehicles in real time. The cameras cover the entire lane from the start detection line to the end detection line and have good night vision capabilities to ensure that high-definition video streams can be accurately captured under various lighting conditions. This step is the foundation of the system and provides a reliable information source for subsequent analysis and monitoring through high-quality video data.

[0047] S2. Object detection: The YOLO algorithm is used to process the collected video stream to detect and identify the target truck vehicle. This process involves using a trained model to identify the vehicle in each frame and track its movement trajectory. Through accurate object detection, the system can collect information about the driving conditions of each vehicle and provide the necessary data basis for speed calculation.

[0048] Furthermore, the YOLO algorithm is used to process the collected video stream to detect and identify the vehicle, including the following steps:

[0049] S21. Data preparation: First, you need to collect images or video data containing vehicles. Commonly used datasets include COCO and Pascal VOC. Then, use annotation tools to annotate the data, draw the bounding box of the vehicle, and annotate each box with the corresponding label to generate the annotation file required for training.

[0050] S22. Data preprocessing: In the data preprocessing stage, the labeled data is converted into the format required by YOLO, usually a text file with each line containing the class of an object and the relative coordinates of the bounding box. In addition, data enhancement can be performed, such as random cropping, rotation, and brightness adjustment, to increase the diversity of the data and thus improve the robustness of the model.

[0051] S23, Environment Configuration: Next, you need to configure the training environment and install deep learning frameworks such as TensorFlow or PyTorch. You can use open source implementations (such as YOLOv5) and download pre-trained models as basic weights to speed up convergence during training.

[0052] S24, Model training: During the model training phase, you need to set the training configuration items, including network structure, input image size, learning rate, batch size, etc. Then run the training script, monitor the loss value and performance indicators, and ensure that the model gradually converges and reaches the expected accuracy.

[0053] S25, Model evaluation: After training, the model is evaluated using the test set, and the performance of the model is judged by calculating indicators such as mAP (meanAverage Precision), Precision, and Recall. At the same time, the detection results are visualized to evaluate missed detections and false detections.

[0054] S26, Model deployment: Export the trained model to a format that can be used for reasoning, such as .pt or .onnx. This allows the model to be applied to real-time detection scenarios, such as processing video streams or image data to achieve rapid vehicle detection.

[0055] S27, Post-processing: In the post-processing stage, non-maximum suppression (NMS) is applied to remove bounding boxes with high overlap and only retain the boxes with the highest confidence. Finally, the detection results are visualized and the vehicle boxes and class labels are drawn on the image to facilitate analysis and presentation of the detection results.

[0056] S3, speed calculation: After detecting a vehicle, the system analyzes the vehicle position changes in consecutive frames to calculate the current driving speed. Usually, the speed is achieved by measuring the displacement of the vehicle within a specific time. The key to this step is accuracy and real-time performance to ensure that vehicles with speeds below the preset threshold can be detected in time, thereby identifying the behavior of slow lane occupation.

[0057] S4. Data recording and analysis: The system automatically records relevant information, including vehicle speed, time, location and other data. These records will be stored in the database for future query and analysis. By analyzing historical data, traffic management departments can identify traffic flow patterns and formulate reasonable management strategies to optimize traffic flow.

[0058] Furthermore, the key road sections include main roads, traffic intersections, expressway and highway entrances and exits, congestion hotspots, mountain roads and slope areas, and construction or obstacle areas.

[0059] In this embodiment, the main roads are the roads with the largest traffic volume in the city, which usually connect various important areas and are prone to traffic congestion and accidents. Therefore, monitoring on the main roads can effectively improve traffic efficiency.

[0060] Traffic intersections are places where multiple roads meet, vehicles turn and change lanes frequently, and accidents are prone to occur. Monitoring these areas can help manage traffic lights and strengthen traffic control to ensure safety.

[0061] At the entrance and exit areas of expressways and highways, the acceleration and deceleration behavior of vehicles is very critical. Monitoring these areas can help prevent traffic accidents and improve the overall safety of the road.

[0062] Congestion hotspots: Some historical congestion points, such as near schools, commercial areas and around large event venues, where traffic volume increases sharply during specific time periods, can be monitored to respond in advance.

[0063] Mountain roads and slope areas: These roads with complex terrain may cause traffic problems due to factors such as weather and road conditions. Monitoring these areas helps to detect and respond to sudden traffic jams or accidents in a timely manner.

[0064] Construction or Obstruction Zones: In areas where traffic construction or obstacles exist, vehicle speeds may be affected. Monitoring these sections can provide traffic managers with real-time information so that timely measures can be taken.

[0065] By monitoring these key road sections, urban traffic flow can be better analyzed and managed, and road safety and traffic efficiency can be improved.

[0066] The capture module captures the scene to obtain a captured video image when the vehicle speed is lower than a preset speed threshold;

[0067] In this embodiment, the capture module uses another batch of high-definition cameras for capture, and only when the vehicle speed is identified to be lower than the preset speed threshold, the scene is captured. The trigger mechanism of the capture module ensures that the camera does not work frequently under normal traffic flow conditions, thereby reducing unnecessary data redundancy and storage pressure. Only when the vehicle speed is identified to be lower than the preset threshold will the system activate the camera for shooting, which can effectively focus on situations that may require attention and ensure the rational use of monitoring resources. At the same time, the application of high-definition cameras also improves the clarity of the image and the ability to capture details, making subsequent analysis and processing more reliable.

[0068] Furthermore, the captured video image is captured simultaneously by high-position and low-position cameras; wherein the high-position camera is used to identify the traffic flow and vehicle distribution on the road, and the low-position camera is used to identify vehicle details; the vehicle details include vehicle license plate and vehicle type.

[0069] The analysis module analyzes the traffic conditions on site through the captured video image;

[0070] In this embodiment, the traffic conditions of the fast lane are analyzed by capturing video images, mainly focusing on the evaluation of vehicle flow, vehicle speed and violations. First, the number of vehicles entering the fast lane within a specific time period can be counted to determine the lane usage and peak period. If it is found that the vehicles in the lane are dense and the speed is significantly lower than the normal driving speed, it may indicate that the lane is seriously occupied. Secondly, the driving behavior of the vehicles in the video is analyzed to identify vehicles that illegally occupy the fast lane. For example, if non-fast lane vehicles frequently enter the fast lane or stop, slow down and other improper behaviors, it will cause overall traffic congestion. In addition, it can also be observed that the traffic is not smooth, braking and the distance between vehicles is too close due to lane occupation, which can reflect the efficiency of the use of the fast lane. Comprehensive analysis of these data will help identify possible traffic problems on the fast lane and provide improvement suggestions for traffic management departments, such as strengthening violation monitoring, increasing publicity of fast lane usage rules, and formulating reasonable traffic flow optimization measures to ensure the smooth and safe operation of the fast lane. These measures will help improve overall traffic efficiency and reduce congestion caused by lane occupation.

[0071] Furthermore, analyzing the traffic conditions at the scene through the captured video image comprises the following steps:

[0072] T1. Identify the vehicle distribution information behind the target truck on the expressway, wherein the vehicle distribution information includes the number of vehicles, vehicle speeds, and corresponding vehicle behaviors; the vehicle behaviors include acceleration, deceleration, lane change, and overtaking;

[0073] In this embodiment, by capturing and analyzing the vehicle information behind the target truck on the expressway through video images, real-time monitoring and evaluation of the traffic conditions in the area can be achieved. First, the system can identify and count the number of vehicles behind the target truck. This data can reflect the density of vehicles following the target truck within a specific time and help identify the status of traffic flow. Secondly, the measurement of vehicle speed is crucial to evaluating the smoothness of traffic flow. Through video analysis, the real-time speed data of each following vehicle can be obtained and compared with the speed of the target truck. This process can help determine the smoothness of the road and whether there is a risk of traffic congestion. In addition, analyzing vehicle behavior is an important part of a comprehensive understanding of traffic dynamics. The system can monitor the acceleration, deceleration, lane change and overtaking of each vehicle. For example, when the rear vehicle accelerates, it may indicate that the driver wants to overtake; while deceleration may mean that there is an obstacle or emergency ahead. At the same time, by detecting lane change behavior, it can be determined whether the rear vehicle attempts to overtake the target truck and whether its lane change is successful or not.

[0074] T2. Predicting the probability of current traffic congestion based on the vehicle distribution information.

[0075] Furthermore, in step T2, predicting the probability of current traffic congestion according to the vehicle distribution information includes the following steps:

[0076] T21. Collecting traffic condition data of trucks occupying fast lanes in historical periods, wherein the traffic condition data includes vehicle distribution information and traffic congestion information; the traffic congestion information is divided into congested and non-congested;

[0077] T22, determine the Bayesian network structure with vehicle distribution information as the parent node and traffic congestion information as the child node;

[0078] In this embodiment, constructing a Bayesian network based on vehicle distribution information and traffic congestion information can effectively reveal the causal relationship between the two. In this network, "vehicle distribution information" is the parent node, which contains data such as the number, type and speed of vehicles in a certain area; and "traffic congestion information" is the child node, indicating the current congestion status and degree. The network structure shows that vehicle distribution will directly affect the occurrence of traffic congestion: when the number of vehicles in a certain area increases or the type of vehicles changes, it may lead to a decrease in traffic smoothness, which in turn causes traffic congestion. Therefore, the Bayesian network can be expressed as "vehicle distribution information" pointing to "traffic congestion information", forming a causal chain.

[0079] In addition, after the network is established, conditional probabilities need to be defined for the relevant nodes, so that the possibility of traffic congestion under specific vehicle distribution conditions can be quantified. By learning from historical data, the network can be continuously updated and optimized to improve its predictive ability. This Bayesian network not only provides valuable decision-making support for traffic management departments, but also helps to identify potential sources of congestion in a timely manner, so as to adopt corresponding intervention strategies, such as adjusting traffic signals, issuing traffic warnings, and guiding vehicle diversion. Ultimately, with the help of this network, traffic management can deal with road congestion problems more scientifically and effectively, and improve traffic fluency and safety.

[0080] T23, use maximum likelihood estimation to determine the conditional probability distribution between parent node and child node parameters, and complete the training of the Bayesian network model;

[0081] In the training of the Bayesian network model, the maximum likelihood estimation (MLE) method can be used to effectively determine the conditional probability distribution between parent nodes and child nodes. Specifically, it is necessary to first collect relevant vehicle distribution information and traffic congestion information data, which can come from traffic monitoring systems, historical records or real-time sensors. By analyzing this data, we can establish a model relationship between vehicle distribution status and traffic congestion. In the MLE process, we aim to find the parameter value that maximizes the observed data, that is, the probability distribution of traffic congestion given the vehicle distribution. This can be done by calculating the frequency of traffic congestion conditions under different vehicle numbers, vehicle types, time periods, etc., and then constructing a conditional probability table (CPT).

[0082] After completing parameter estimation, the model will be able to reflect how changes in vehicle distribution affect the degree of traffic congestion, allowing the Bayesian network to make more accurate inferences and predictions. By continuously optimizing this model, traffic management departments can update conditional probabilities based on real-time data to provide dynamic response capabilities for urban traffic systems. Ultimately, the Bayesian network will play an important role in understanding and predicting the mechanism of traffic congestion, helping to achieve more efficient traffic management and planning, and improving the operational efficiency and safety of the overall traffic system.

[0083] Furthermore, the conditional probability distribution is calculated as follows:

[0084]

[0085] In the formula, P(U) represents the sum of a parameter U of a child node in all parent node parameters B. i The joint conditional probability under a (B i ) is a parameter U of the child node in a parameter B of the parent node i The probability of the following happening.

[0086] T24. Input the current vehicle distribution into the trained Bayesian network model to predict the probability of current traffic congestion.

[0087] In this embodiment, the Bayesian network model is a graphical model based on probabilistic reasoning, which is widely used to represent and reason about conditional dependencies between variables. It consists of a directed acyclic graph (DAG) and a conditional probability table (CPT). Each node in the graph represents a random variable, and the directed edges represent the causal relationship between the variables. This structure ensures the logic of causal reasoning and avoids circular dependencies. The conditional probability table of each node describes the probability distribution of the node under a given condition of its parent node (which directly affects its variables), helping us understand the changes in variables under different conditions. Bayesian networks are particularly good at handling uncertainty, and can calculate the posterior probability of the variable of interest through an inference algorithm, thereby making effective predictions and decisions. In addition, Bayesian networks allow learning based on actual data, build models by analyzing data, adjust the relationship between variables, and optimize conditional probability distribution. This makes the model adaptable in a dynamic environment. Its application areas are very wide, covering medical diagnosis, risk assessment, fault detection, and traffic flow prediction. Especially in traffic management, Bayesian networks can handle complex real-time data and provide a scientific basis for traffic congestion, accident risk, and flow optimization.

[0088] The decision module determines whether the target truck vehicle has traffic violations based on the traffic conditions.

[0089] Furthermore, judging whether the target truck vehicle has traffic violations based on the traffic conditions is specifically: when the probability of the current traffic congestion exceeds a preset first congestion threshold, judging whether the target truck vehicle has traffic violations.

[0090] In this embodiment, if the calculated congestion probability exceeds this threshold, it means that the traffic situation is serious and may lead to changes in traffic control measures. At this time, the behavior of the target truck needs to be further observed. Specifically, if the target truck still performs improper operations under severe congestion, it can be determined that the vehicle has traffic violations. This judgment not only relies on the calculation of probability, but also needs to be combined with the real-time location of the vehicle and related monitoring information to ensure the accuracy of the judgment.

[0091] Furthermore, when the decision module determines that the target truck vehicle has violated the traffic rules, it reminds the target truck vehicle not to occupy the fast lane through the traffic indicator light and retains the captured video image as the basis for the violation.

[0092] In this embodiment, when it is determined that the target truck has traffic violations, a series of measures can be taken to manage and punish it. First, use traffic lights to warn the truck not to occupy the fast lane. By setting a flashing red light or other obvious signals, the driver's attention can be effectively attracted, prompting him to follow traffic rules. This visual reminder method is particularly important on high-traffic roads and can effectively reduce traffic accidents caused by violations. Secondly, capturing video images as a basis for violations is another key link. Recording the road behavior of the target truck through surveillance cameras will provide important evidence for subsequent violation handling. These video materials can not only be used to review the authenticity of the violations, but also as a legal basis to ensure fairness when necessary.

[0093] Furthermore, when the probability of the current traffic congestion exceeds a preset second congestion threshold, an alarm is automatically sent to the traffic management department to request handling of the traffic congestion.

[0094] It should be noted that the second congestion threshold of the present embodiment is greater than the first congestion threshold. When the degree of traffic congestion exceeds the preset second congestion threshold, the system can automatically send an alarm request to the traffic management department so as to promptly handle and alleviate the congestion. The second congestion threshold is set relatively high, which means that the system will only actively issue an alarm when the traffic is extremely congested, thereby reducing false alarms caused by minor congestion. Specifically, the system can determine the degree of congestion by monitoring traffic flow and vehicle speed in real time. Once the monitored traffic status reaches the second congestion threshold, the system will automatically generate an alarm message, including detailed data such as the current traffic conditions, specific locations, congestion periods, and possible impact ranges. This information will be quickly sent to the traffic management department so that relevant personnel can intervene in a timely manner.

[0095] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A road condition monitoring system based on video image analysis, characterized in that: It includes a speed measurement module, a capture module, an analysis module and a decision module, wherein the speed measurement module, the capture module, the analysis module and the decision module are communicatively connected, wherein: The speed measurement module is used to measure the speed of target truck vehicles on key sections of the fast lane; The capture module captures the scene to obtain a captured video image when the vehicle speed is lower than a preset speed threshold; The analysis module analyzes the traffic conditions on site through the captured video image; The decision module determines whether the target truck vehicle has traffic violations based on the traffic conditions.

2. A road condition monitoring system based on video image analysis according to claim 1, characterized in that: The method of measuring the speed of vehicles on the key section of the fast lane includes the following steps: S1. Data collection: Install high-definition cameras at key sections, covering the entire lane from the start detection line to the end detection line; S2, object detection: The YOLO algorithm is used to process the collected video stream to detect and identify the target truck vehicle; S3, speed calculation: After the vehicle is detected, the vehicle position changes in consecutive frames are analyzed to calculate the current driving speed.

3. The road condition monitoring system based on video image analysis according to claim 1 is characterized in that: The key sections include main roads, traffic intersections, expressway and highway entrances and exits, congestion hotspots, mountain roads and slope areas, as well as construction or obstacle areas.

4. A road condition monitoring system based on video image analysis according to claim 2, characterized in that: The YOLO algorithm is used to process the collected video stream to detect and identify the vehicle, including the following steps: S21. Data preparation: Collect image or video data containing vehicles, annotate the data using annotation tools, draw the bounding box of the vehicle, and annotate each box with corresponding labels to generate the annotation files required for training; S22, data preprocessing: converting the labeled data into a text file format; S23, Environment Configuration: Configure the training environment and install the TensorFlow or PyTorch deep learning framework; S24, model training: set the configuration items for training, including network structure, input image size, learning rate, and batch size, and then run the training script, monitor the loss value and performance indicators, and ensure that the model gradually converges and reaches the expected accuracy; S25. Model evaluation: After training, use the test set to evaluate the model and judge the performance of the model by calculating the mAP, Precision, and Recall indicators.

5. The road condition monitoring system based on video image analysis according to claim 1 is characterized in that: The captured video images are captured simultaneously by high-position and low-position cameras; wherein the high-position camera is used to identify the traffic volume and vehicle distribution on the road, and the low-position camera is used to identify vehicle details; the vehicle details include vehicle license plate and vehicle type.

6. The road condition monitoring system based on video image analysis according to claim 1 is characterized in that: The method of analyzing the traffic conditions on site by using the captured video image comprises the following steps: T1. Identify the vehicle distribution information behind the target truck on the expressway, wherein the vehicle distribution information includes the number of vehicles, vehicle speeds, and corresponding vehicle behaviors; the vehicle behaviors include acceleration, deceleration, lane change, and overtaking; T2. Predicting the probability of current traffic congestion based on the vehicle distribution information.

7. A road condition monitoring system based on video image analysis according to claim 6, characterized in that: In step T2, predicting the probability of current traffic congestion according to the vehicle distribution information includes the following steps: T21. Collecting traffic condition data of trucks occupying fast lanes in historical periods, wherein the traffic condition data includes vehicle distribution information and traffic congestion information; the traffic congestion information is divided into congested and non-congested; T22, determine the Bayesian network structure with vehicle distribution information as the parent node and traffic congestion information as the child node; T23, use maximum likelihood estimation to determine the conditional probability distribution between parent node and child node parameters, and complete the training of the Bayesian network model; T24. Input the current vehicle distribution into the trained Bayesian network model to predict the probability of current traffic congestion.

8. The road condition monitoring system based on video image analysis according to claim 7 is characterized in that: The determining, based on the traffic conditions, whether the target truck vehicle has traffic violations is specifically: when the probability of the current traffic congestion exceeds a preset first congestion threshold, determining whether the target truck vehicle has traffic violations.

9. The road condition monitoring system based on video image analysis according to claim 1, characterized in that: When the decision module determines that the target truck vehicle has violated the traffic regulations, it reminds the target truck vehicle not to occupy the fast lane through the traffic indicator light and retains the captured video image as the basis for the violation.

10. The road condition monitoring system based on video image analysis according to claim 7, characterized in that: When the probability of the current traffic congestion exceeds a preset second congestion threshold, an alarm is automatically sent to the traffic management department to request handling of the traffic congestion.

Images