A method and system for predicting lane capacity

Abstract

The application discloses a kind of lane traffic capacity prediction method and system, it is related to traffic engineering technical field, the method includes: obtaining preset traffic capacity;Obtain the camera monitoring video data under the first preset time window of the target lane;Predetermined virtual line set is set in the target lane;According to the camera monitoring video data, vehicle trajectory analysis is carried out, and target trajectory is obtained;Determine whether the target trajectory and the first predetermined virtual line in the predetermined virtual line set coincide, obtain first determination result;According to the first determination result, the preset traffic capacity is dynamically corrected, and the dynamic prediction result of the lane traffic capacity of the target lane is obtained.The application solves the technical problems existing in the prior art that only some general reference opinions can be provided, and the prediction accuracy and reliability are low, achieves the technical effect that the prediction result is accurate and the reliability is high.

Description

Technical Field

[0001] This invention relates to the field of traffic engineering technology, specifically to a method and system for predicting lane capacity. Background Technology

[0002] In recent years, my country's motor vehicle ownership has continued to grow, leading to increasing road traffic pressure. The assessment and prediction of lane capacity is of great significance for traffic management, road planning, and traffic safety. Currently, lane capacity prediction mainly relies on traffic simulation software. However, existing technologies suffer from limitations, offering only general references and exhibiting low prediction accuracy and reliability. Summary of the Invention

[0003] This application provides a lane capacity prediction method and system, which solves the technical problems of existing technologies that can only provide some general reference opinions and have low prediction accuracy and reliability, and achieves the technical effect of accurate prediction results and high reliability.

[0004] This application provides a lane capacity prediction method and system, the technical solution of which is as follows:

[0005] In a first aspect, embodiments of this application provide a lane capacity prediction method, the method comprising:

[0006] Obtain a preset traffic capacity, wherein the preset traffic capacity is the traffic capacity of the target lane under undisturbed conditions obtained based on the lane basic information of the target lane;

[0007] Acquire the camera monitoring video data of the target lane within a first preset time window;

[0008] A predetermined set of virtual lines is set in the target lane, and the predetermined set of virtual lines is a set of driving trajectories set based on the preset traffic capacity;

[0009] Based on the video surveillance data, the vehicle's driving trajectory is analyzed to obtain the target driving trajectory;

[0010] Determine whether the target driving trajectory coincides with the first predetermined virtual line in the predetermined virtual line set, and obtain a first determination result;

[0011] Based on the first judgment result, the preset traffic capacity is dynamically corrected to obtain a dynamic prediction result of the lane traffic capacity of the target lane.

[0012] Secondly, embodiments of this application provide a lane capacity prediction system, the system comprising:

[0013] A preset traffic capacity acquisition module is used to acquire a preset traffic capacity, which is the traffic capacity of the target lane under interference-free conditions obtained based on the lane basic information of the target lane.

[0014] The video data acquisition module is used to acquire camera monitoring video data of the target lane within a first preset time window;

[0015] A predetermined virtual line set setting module is used to set a predetermined virtual line set in the target lane, wherein the predetermined virtual line set is a set of driving trajectories set based on the preset traffic capacity.

[0016] A target driving trajectory acquisition module is used to analyze the vehicle driving trajectory based on the camera monitoring video data to acquire the target driving trajectory.

[0017] The first judgment result acquisition module is used to determine whether the target driving trajectory overlaps with the first predetermined virtual line in the predetermined virtual line set, and to acquire the first judgment result.

[0018] The lane capacity dynamic prediction module is used to dynamically correct the preset capacity based on the first judgment result to obtain the dynamic prediction result of the lane capacity of the target lane.

[0019] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0020] This application obtains the preset traffic capacity of the target lane under interference-free conditions based on the lane's basic information, then acquires camera monitoring video data of the target lane within a first preset time window, sets a predetermined set of virtual lines on the target lane, analyzes vehicle trajectories based on the camera monitoring video data to obtain the target driving trajectory, and then determines whether the target driving trajectory overlaps with a first predetermined virtual line in the predetermined set of virtual lines, obtaining a first judgment result. Based on the first judgment result, the preset traffic capacity is dynamically corrected to obtain a dynamic prediction result of the target lane's traffic capacity. This effectively solves the technical problems of existing technologies that can only provide some general reference opinions with low prediction accuracy and reliability, achieving the technical effect of accurate prediction results and high reliability. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic flowchart of a lane capacity prediction method provided in an embodiment of this application;

[0023] Figure 2 This is a schematic diagram of a lane capacity prediction system provided in an embodiment of this application.

[0024] Explanation of reference numerals in the attached diagram: Preset traffic capacity acquisition module 10, video data acquisition module 20, pre-set virtual line set setting module 30, target driving trajectory acquisition module 40, first judgment result acquisition module 50, lane traffic capacity dynamic prediction module 60. Detailed Implementation

[0025] This application provides a lane capacity prediction method and system to address the technical problems of existing technologies that can only provide some general reference opinions and have low prediction accuracy and reliability.

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0027] It should be noted that the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such process, method, product, or device.

[0028] Example 1

[0029] like Figure 1As shown in the embodiments of this application, by acquiring video monitoring data of the target lane, the vehicle driving trajectory of the target lane is analyzed, a predetermined virtual line is set in the target lane under interference-free conditions, and the actual vehicle driving trajectory of the target lane is compared and analyzed with the predetermined virtual line to obtain a judgment result. Based on the judgment result, the preset traffic capacity of the target lane is dynamically corrected to obtain a dynamic prediction result of the lane traffic capacity of the target lane.

[0030] First, the preset capacity of the target lane is obtained. Lane capacity refers to the maximum number of vehicles that can pass through a given point, lane, or cross-section on the road per unit time, representing the road's carrying capacity. In real life, lane capacity is generally affected by many factors, such as road geometry, road conditions, traffic conditions, and traffic light timing. Therefore, it is necessary to preset an ideal lane capacity under conditions without these interferences. The preset capacity is the capacity of the target lane under interference-free conditions, obtained based on the lane's basic information. This basic information includes lane length, lane width, lane material, lane markings, and lane speed limits, used for planning vehicle travel space on the road. The basic lane information affects the preset capacity of the lane. Therefore, the preset capacity is the maximum number of vehicles that can pass through a fixed lane per unit time under ideal conditions. For example, the preset capacity of the target lane is 800 vehicles / hour.

[0031] Then, the camera monitoring video data of the target lane under the first preset time window is obtained. The first preset time is a pre-set time period, including a fixed time period, such as 5 minutes, or a fixed time node, such as 8:00 am to 8:05 am. The camera monitoring video refers to the video recording taken by the traffic monitoring camera installed on the traffic light or other pole. By inputting the target lane and the first preset time on the background controller connected to the traffic monitoring camera, the camera monitoring video data of the target lane under the first preset time window can be extracted.

[0032] A predetermined set of virtual lines is set in the target lane, wherein the predetermined virtual lines are pre-set vehicle travel routes, such as virtual straight lines parallel to the target lane, and the predetermined set of virtual lines is a set of travel trajectories set based on the preset traffic capacity, such as a set of multiple virtual straight lines parallel to the target lane.

[0033] The vehicle's trajectory is analyzed based on the video surveillance data. By extracting the video surveillance data, the vehicle's route in the video surveillance video is analyzed to obtain the target trajectory, which is the trajectory of the vehicle in the target lane within the first preset time period.

[0034] Then, it is determined whether the target driving trajectory coincides with a first predetermined virtual line in the predetermined virtual line set, wherein the first predetermined virtual line is a virtual line in the predetermined virtual line set. By determining whether the target driving trajectory coincides with the first predetermined virtual line, a first judgment result is obtained, wherein the first judgment result is either the target driving trajectory coincides with the first predetermined virtual line or the target driving trajectory does not coincide with the first predetermined virtual line, that is, the first judgment result is yes or no.

[0035] Based on the first judgment result, the preset traffic capacity is dynamically adjusted. This dynamic adjustment is based on the first judgment result; if the first judgment result is yes, no adjustment is needed; if the first judgment result is no, adjustment is needed. By dynamically adjusting the preset traffic capacity, a dynamic prediction result of the target lane's traffic capacity can be obtained. This dynamic prediction result is a prediction of the trend of lane traffic capacity changes over a future time period, including increases or decreases in lane traffic capacity. This achieves the technical effect of accurate and highly reliable prediction results.

[0036] Preferably, obtaining the preset traffic capacity includes: obtaining the lane basic information, which includes lane width information, lane length information, and lane speed limit information. The lane width information refers to the width of the lane, for example, a lane width of 14 meters. The lane length information refers to the length of the target lane, which can be set according to specific needs. The lane speed limit information is the speed limit imposed on vehicles on the road, including minimum speed and maximum speed, for example, a maximum speed not exceeding 50 kilometers per hour. Obtaining a vehicle width threshold, where the vehicle width threshold refers to the maximum or minimum value of the vehicle's outer width, depending on the vehicle type, and combining this with the lane width information to obtain the number of passages per trip. The number of passages per trip can be calculated based on the lane width information and the vehicle width information; the larger the lane width, the larger the number of passages per trip, and vice versa. The vehicle length threshold of the target lane is obtained, where the vehicle length threshold refers to the maximum or minimum value of the vehicle's outer profile length, determined by the specific vehicle type. This threshold is then combined with the lane speed limit information, the lane length information, and the number of vehicles passing through in a single trip to calculate the preset traffic capacity. The preset traffic capacity is the number of vehicles passing through the target lane per unit time, used to characterize the lane's carrying capacity under ideal conditions. For example, under ideal conditions, assuming vehicles travel at a constant speed within the lane speed limit, the vehicle length is taken as the maximum value, and vehicle spacing is negligible, the preset traffic capacity is calculated as: (Vehicle speed - Lane length) ÷ Vehicle length × Number of vehicles passing through in a single trip. This achieves the technical effect of obtaining the preset traffic capacity of the target lane under ideal conditions.

[0037] In a preferred embodiment provided in this application, the step of analyzing the vehicle's driving trajectory based on the camera monitoring video data to obtain the target driving trajectory includes: extracting the camera monitoring video data frame by frame, including random frame-by-frame extraction or a preset time interval for extracting frames, such as 2 seconds, and then extracting the camera monitoring video frames frame by frame in chronological order to obtain a monitoring image sequence. The monitoring image sequence includes multiple frames. Since the camera monitoring video's shooting range is constant, the background in each frame is the same except for the vehicle. Multiple positions of the target vehicle are obtained based on the monitoring image sequence. The target vehicle's position is different in each frame, and these multiple positions correspond to the multiple frames, meaning each vehicle position uniquely corresponds to a specific frame. The multiple positions are then sequentially connected, either in chronological order or in the order of the vehicle's direction of travel, to obtain the target driving trajectory, i.e., the target vehicle's driving route map. This achieves the technical effect of extracting the target vehicle's driving route.

[0038] Preferably, obtaining the target driving trajectory includes: extracting a first image and a second image from the monitoring image sequence, wherein the first image and the second image are any two adjacent images in the monitoring image sequence. The position of the target vehicle in the first image is obtained, denoted as the first position, and the position of the target vehicle in the second image is obtained, denoted as the second position. This can be done using image processing software, either by manually marking the target vehicle in the first image and the second image or by automatically detecting it using an image processing algorithm, to obtain the position information of the target vehicle. The position distance is obtained by comparing the first position and the second position, and the distance between the target vehicles is calculated using geometric transformation and calculation formulas. The first acquisition time and the second acquisition time of the first image and the second image are obtained, and the time interval length is obtained by comparing them. The first acquisition time is the time to extract the first image, and the second acquisition time is the time to extract the second image. The time interval length between the two images is obtained by subtracting the two times. The target driving speed of the target vehicle is calculated by combining the time interval length and the position distance, wherein the target driving speed is the ratio of the position distance to the time interval length. Connecting the first and second positions yields the target driving trajectory, and the target driving speed is marked on the target driving trajectory. In other words, the target driving trajectory includes multiple position points of the target vehicle, and the target driving speed is marked between every two adjacent position points. This achieves the technical effect of extracting the target vehicle's driving route and speed.

[0039] In a preferred embodiment of this application, the step of dynamically correcting the preset traffic capacity based on the first judgment result to obtain a dynamic prediction result of the lane traffic capacity of the target lane includes: comparing the target driving speed with the lane speed limit information, subtracting the target driving speed from the lane speed limit information to obtain a first speed deviation, wherein the first speed deviation is used to characterize the deviation of the target driving speed from the lane speed limit information; the larger the first speed deviation, the greater the speed difference between the target driving speed and the lane speed limit information. If the first judgment result is yes, that is, the target driving trajectory coincides with the first predetermined virtual line in the predetermined virtual line set, the preset traffic capacity is dynamically corrected based on the first speed deviation. If the target driving speed is greater than the lane speed limit information, the traffic capacity of the target lane will increase; if the target driving speed is less than the lane speed limit information, the traffic capacity of the target lane will decrease. The preset traffic capacity is dynamically corrected based on the specific deviation between the target driving speed and the lane speed limit information. This achieves the technical effect of dynamically predicting lane traffic capacity.

[0040] Optionally, the method further includes: if the first judgment result is negative, i.e., the target driving trajectory does not coincide with the first predetermined virtual line in the predetermined virtual line set, obtaining the deviation trajectory between the target driving trajectory and the first predetermined virtual line. This deviation trajectory is obtained by comparing the target driving trajectory with the first predetermined virtual line. For example, the target driving trajectory is line segment 1, and the first predetermined virtual line is line segment 2. Since the target driving trajectory does not coincide with the first predetermined virtual line, line segment 1 and line segment 2 must intersect. By translation, the two line segments intersect at a point, thus obtaining the deviation trajectory between the two line segments. Based on the deviation trajectory, the abnormal lane location is located, and the width of the abnormal location is obtained. By comparing the target driving trajectory and the first predetermined virtual line, the position where the target driving trajectory begins to deviate from the first predetermined virtual line is found, thereby locating the abnormal lane location. The width of the abnormal location is the remaining width available for normal vehicle passage after an abnormal situation occurs in the lane. The larger the width of the abnormal location, the stronger the passage capacity. By combining the width of the abnormal location and the first speed deviation, the preset traffic capacity is dynamically corrected. When a lane anomaly occurs, the passable width at the abnormal location decreases, the first speed deviation increases, and consequently, the traffic capacity of the target lane decreases. By comprehensively analyzing the impact of changes in the width of the abnormal location and the first speed deviation on the traffic flow of the target lane, the preset traffic capacity is dynamically corrected. This achieves the technical effect of improving the accuracy of lane traffic capacity prediction.

[0041] Optionally, the method further includes: performing image segmentation and extraction on the abnormal lane location based on the camera monitoring video data, and then enlarging the image to obtain an abnormal image of the abnormal lane location; extracting the image of the lane anomaly from the camera monitoring video; extracting the image of the abnormal lane location region from the image using image segmentation technology; and enlarging the size of the extracted region using magnification or upsampling technology to obtain a clearer abnormal image of the abnormal lane location. Anomaly type identification is performed based on the abnormal image. A convolutional neural network (CNN) is constructed by preprocessing the historical lane anomaly image dataset and then inputting it into the CNN for training. The trained CNN can identify the lane anomaly type of the image, thereby obtaining anomaly type information, including lane obstruction due to traffic accidents, vehicles driving in the wrong direction, and obstacles in the lane. Historical road anomaly handling records for the target lane are obtained. These records, which include various anomaly handling records that have occurred on the target lane, are retrieved through a relevant system and matched against the anomaly type information. The historical road anomaly handling records are iterated and matched based on the anomaly type information until multiple historical road anomaly handling results with the same anomaly type information are found. The processing time of these multiple historical road anomaly handling results is obtained, and the average of these processing times is taken to obtain the anomaly handling time, which is the average processing time of historical anomalies of the same type. Based on the anomaly handling time, the traffic capacity recovery prediction for the target lane is performed. This traffic capacity recovery prediction is the estimated time required for the target lane to return to normal traffic flow. If the anomaly handling time is long, the time required for the target lane to return to normal traffic capacity is also long, thus predicting the time required for the target lane to restore its capacity. This achieves the technical effect of predicting the traffic capacity recovery of abnormal lanes.

[0042] Example 2

[0043] Based on the same inventive concept as the lane capacity prediction method in the foregoing embodiments, such as Figure 2 As shown, this application provides a lane capacity prediction system. The system and method embodiments in this application are based on the same inventive concept. The system includes:

[0044] A preset traffic capacity acquisition module 10 is used to acquire a preset traffic capacity, which is the traffic capacity of the target lane under interference-free conditions obtained based on the lane basic information of the target lane.

[0045] Video data acquisition module 20, the video data acquisition module 20 is used to acquire the camera monitoring video data of the target lane under a first preset time window;

[0046] A predetermined virtual line set setting module 30 is used to set a predetermined virtual line set in the target lane. The predetermined virtual line set is a set of driving trajectories set based on the preset traffic capacity.

[0047] The target driving trajectory acquisition module 40 is used to analyze the vehicle driving trajectory based on the camera monitoring video data to acquire the target driving trajectory.

[0048] The first judgment result acquisition module 50 is used to determine whether the target driving trajectory overlaps with the first predetermined virtual line in the predetermined virtual line set, and to acquire the first judgment result.

[0049] The lane capacity dynamic prediction module 60 is used to dynamically correct the preset capacity based on the first judgment result to obtain the dynamic prediction result of the lane capacity of the target lane.

[0050] Furthermore, the preset access capability acquisition module 10 is used to execute the following methods:

[0051] Obtain the lane basic information, which includes lane width information, lane length information, and lane speed limit information;

[0052] Obtain the vehicle width threshold and combine it with the lane width information to obtain the number of passages per time;

[0053] The vehicle length threshold of the target lane is obtained, and the preset traffic capacity is calculated by combining the lane speed limit information, the lane length information, and the number of single passages.

[0054] Furthermore, the target driving trajectory acquisition module 40 is used to perform the following method:

[0055] The video surveillance data is extracted frame by frame to obtain a monitoring image sequence, wherein the monitoring image sequence includes multiple frames of images;

[0056] Based on the monitored image sequence, multiple locations of the target vehicle are obtained, wherein the multiple locations correspond to the multiple frames of images. The multiple locations are sequentially connected to obtain the target driving trajectory.

[0057] Furthermore, the target driving trajectory acquisition module 40 is used to perform the following method:

[0058] Extract the first image and the second image from the monitoring image sequence;

[0059] The position of the target vehicle in the first image is obtained and denoted as the first position;

[0060] The position of the target vehicle in the second image is obtained and denoted as the second position;

[0061] The positional distance is obtained by comparing the first position and the second position;

[0062] The first acquisition time and the second acquisition time of the first image and the second image are obtained, and the time interval length is compared to obtain the second acquisition time.

[0063] The target speed of the target vehicle is calculated by combining the time interval length and the position spacing.

[0064] Connect the first position and the second position to obtain the target driving trajectory, and mark the target driving speed on the target driving trajectory.

[0065] Furthermore, the lane capacity dynamic prediction module 60 is used to perform the following method:

[0066] By comparing the target driving speed with the lane speed limit information, a first speed deviation is obtained;

[0067] If the first determination result is yes, the preset traffic capacity is dynamically corrected based on the first speed deviation.

[0068] Furthermore, the lane capacity dynamic prediction module 60 is used to perform the following method:

[0069] If the first determination result is negative, obtain the deviation trajectory between the target driving trajectory and the first predetermined virtual line;

[0070] Based on the deviation from the trajectory, the abnormal position of the lane is located, and the width of the abnormal position is obtained;

[0071] The preset passage capacity is dynamically corrected by combining the width of the abnormal location and the first speed deviation.

[0072] Furthermore, the lane capacity dynamic prediction module 60 is used to perform the following method:

[0073] Based on the video monitoring data, the abnormal location of the lane is segmented, extracted, and magnified to obtain an abnormal image of the abnormal location of the lane.

[0074] Anomaly type identification is performed based on the abnormal image to obtain anomaly type information;

[0075] Obtain historical road anomaly handling records for the target lane, and perform traversal matching on the historical road anomaly handling records based on the anomaly type information to obtain the anomaly handling duration.

[0076] Based on the anomaly handling time, the traffic capacity recovery prediction of the target lane is performed.

[0077] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0078] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0079] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for predicting lane capacity, characterized in that, The method includes: Obtaining a preset traffic capacity, wherein the preset traffic capacity is obtained based on the lane basic information of the target lane under undisturbed conditions, and obtaining the preset traffic capacity includes: Obtain the lane basic information, which includes lane width information, lane length information, and lane speed limit information; Obtain the vehicle width threshold and combine it with the lane width information to obtain the number of passages per time; The vehicle length threshold of the target lane is obtained, and the preset traffic capacity is calculated by combining the lane speed limit information, the lane length information and the number of single passages. Acquire the camera monitoring video data of the target lane within a first preset time window; A predetermined set of virtual lines is set in the target lane, and the predetermined set of virtual lines is a set of driving trajectories set based on the preset traffic capacity; Based on the video surveillance data, the vehicle's driving trajectory is analyzed to obtain the target driving trajectory, which includes: The video surveillance data is extracted frame by frame to obtain a monitoring image sequence, wherein the monitoring image sequence includes multiple frames of images; Multiple locations of the target vehicle are obtained based on the monitored image sequence, wherein the multiple locations correspond to the multiple image frames. The multiple locations are sequentially connected to obtain the target driving trajectory. Obtaining the target driving trajectory includes: Extract the first image and the second image from the monitoring image sequence; The position of the target vehicle in the first image is obtained and denoted as the first position; The position of the target vehicle in the second image is obtained and denoted as the second position; The positional distance is obtained by comparing the first position and the second position; The first acquisition time and the second acquisition time of the first image and the second image are obtained, and the time interval length is compared to obtain the second acquisition time. The target speed of the target vehicle is calculated by combining the time interval length and the position spacing. Connect the first position and the second position to obtain the target driving trajectory, and mark the target driving speed on the target driving trajectory; Determine whether the target driving trajectory coincides with the first predetermined virtual line in the predetermined virtual line set, and obtain a first determination result; Based on the first judgment result, the preset traffic capacity is dynamically corrected to obtain a dynamic prediction result of the lane traffic capacity of the target lane; the step of dynamically correcting the preset traffic capacity based on the first judgment result to obtain a dynamic prediction result of the lane traffic capacity of the target lane includes: By comparing the target driving speed with the lane speed limit information, a first speed deviation is obtained; If the first determination result is yes, the preset traffic capacity is dynamically corrected based on the first speed deviation; If the first determination result is negative, obtain the deviation trajectory between the target driving trajectory and the first predetermined virtual line; Based on the deviation from the trajectory, the abnormal position of the lane is located, and the width of the abnormal position is obtained; The preset passage capacity is dynamically corrected by combining the width of the abnormal location and the first speed deviation.

2. The method as described in claim 1, characterized in that, The method further includes: Based on the video monitoring data, the abnormal location of the lane is segmented, extracted, and magnified to obtain an abnormal image of the abnormal location of the lane. Anomaly type identification is performed based on the abnormal image to obtain anomaly type information; Obtain historical road anomaly handling records for the target lane, and perform traversal matching on the historical road anomaly handling records based on the anomaly type information to obtain the anomaly handling duration. Based on the anomaly handling time, the traffic capacity recovery prediction of the target lane is performed.

3. A lane capacity prediction method system, used to execute the method of claim 1, characterized in that, The system includes: A preset traffic capacity acquisition module is used to acquire a preset traffic capacity, which is the traffic capacity of the target lane under interference-free conditions obtained based on the lane basic information of the target lane. The video data acquisition module is used to acquire camera monitoring video data of the target lane within a first preset time window; A predetermined virtual line set setting module is used to set a predetermined virtual line set in the target lane, wherein the predetermined virtual line set is a set of driving trajectories set based on the preset traffic capacity. A target driving trajectory acquisition module is used to analyze the vehicle driving trajectory based on the camera monitoring video data to acquire the target driving trajectory. The first judgment result acquisition module is used to determine whether the target driving trajectory overlaps with the first predetermined virtual line in the predetermined virtual line set, and to acquire the first judgment result. The lane capacity dynamic prediction module is used to dynamically correct the preset capacity based on the first judgment result to obtain the dynamic prediction result of the lane capacity of the target lane.

Images