Vehicle right-of-way monitoring methods and computer devices

Abstract

This application discloses a vehicle right-of-way monitoring method and computer device. The vehicle right-of-way monitoring method includes: determining vehicles entering the target intersection and their movement information based on video monitoring data and electronic map data corresponding to the target intersection; identifying, when left-turning vehicles are present, a target oncoming straight-ahead vehicle whose trajectory intersects with the left-turning vehicle's trajectory during the left-turning vehicle's passage through the target intersection; determining a first time required for the left-turning vehicle to reach the intersection point and a second time required for the target oncoming straight-ahead vehicle to reach the intersection point in the corresponding sampling frame; and determining the right-of-way monitoring result based on the target first time and target second time corresponding to the target sampling frame. This enables the identification of right-of-way conflicts between left-turning vehicles and oncoming straight-ahead vehicles at the intersection, thereby allowing for more efficient and accurate monitoring of right-of-way at the intersection throughout the entire time period.

Description

Technical Field

[0001] This application relates to the field of traffic monitoring technology, and in particular to a vehicle right-of-way monitoring method and computer device. Background Technology

[0002] Urban road intersections are bottlenecks in the operation of urban road networks and key points of urban traffic congestion. Rationally organizing the passage space and order of various traffic flows can effectively improve the efficiency of intersections. Currently, the accuracy of vehicle right-of-way monitoring at intersections is low. Summary of the Invention

[0003] This application provides a vehicle right-of-way monitoring method and computer device, which determines the right-of-way monitoring result based on the target first duration and target second duration corresponding to the target sampling frame, so as to accurately identify right-of-way conflicts between left-turning vehicles and oncoming straight-going vehicles at intersections.

[0004] Firstly, a vehicle right-of-way monitoring method is provided, comprising: determining vehicles entering the target intersection and their motion information based on video monitoring data and electronic map data corresponding to the target intersection; if left-turning vehicles are among the vehicles, determining a target oncoming straight-ahead vehicle whose trajectory intersects with the trajectory of the left-turning vehicle during its passage through the target intersection; and determining, based on the motion information of the left-turning vehicles, a first duration required for the left-turning vehicle to reach the intersection point in each first sampling frame, wherein each first sampling frame is the time from the left-turning vehicle entering the target intersection to reaching the intersection point, as determined by the video monitoring data. The sampling frames determined from the data; based on the motion information of the target oncoming straight-ahead vehicles, the second duration required for the target oncoming straight-ahead vehicles to reach the intersection point in each second sampling frame is determined, wherein each second sampling frame is a sampling frame determined from the video monitoring data during the period from when the target oncoming straight-ahead vehicles enter the target intersection to when they reach the intersection point; a target sampling frame that meets the target conditions is determined from each first sampling frame, and a target first duration corresponding to the target sampling frame is determined from each first duration, and a target second duration corresponding to the target sampling frame is determined from each second duration; the right-of-way monitoring result is determined based on the target first duration and the target second duration.

[0005] In some embodiments, determining the right-of-way monitoring result based on the target first duration and the target second duration includes: determining the difference between the target second duration and the target first duration; if the difference is not less than a target threshold, determining that the left-turning vehicle has not violated the right-of-way; if the difference is less than the target threshold, determining whether the left-turning vehicle has violated the right-of-way based on the order in which the left-turning vehicle and the target oncoming straight-ahead vehicle arrive at the intersection point.

[0006] In some embodiments, determining whether the left-turning vehicle violated its right-of-way based on the order in which the left-turning vehicle and the oncoming straight-going vehicle arrived at the intersection point includes: determining that the left-turning vehicle violated its right-of-way if the left-turning vehicle arrived at the intersection point first; and determining that the left-turning vehicle did not violate its right-of-way if the left-turning vehicle did not arrive at the intersection point first.

[0007] In some embodiments, the target condition includes one of the following: the envelope area of ​​the left-turning vehicle begins to encroach on the straight lane where the target oncoming straight vehicle is located; the distance between the envelope area of ​​the left-turning vehicle and the straight lane is less than the target distance.

[0008] In some embodiments, the motion information includes position information and speed information. Determining the first time required for the left-turning vehicle to reach the intersection point in each first sampling frame based on the motion information of the left-turning vehicle includes: determining first speed data of the left-turning vehicle in the first sampling frame based on the speed information of the left-turning vehicle; determining a first distance between the left-turning vehicle and the intersection point in the first sampling frame based on the position information of the left-turning vehicle; and determining the first time based on the first speed data and the first distance.

[0009] The step of determining the second time required for the target oncoming straight-ahead vehicle to reach the intersection point in each second sampling frame based on the motion information of the target oncoming straight-ahead vehicle includes: determining the second speed data of the target oncoming straight-ahead vehicle in the second sampling frame based on the speed information of the target oncoming straight-ahead vehicle; determining the second distance between the target oncoming straight-ahead vehicle and the intersection point in the second sampling frame based on the position information of the target oncoming straight-ahead vehicle; and determining the second time based on the second speed data and the second distance.

[0010] In some embodiments, Formula 1 is used to determine each of the first durations and each of the second durations, wherein Formula 1 is specifically:

[0011]

[0012] Wherein, TTI represents the first duration or the second duration, and when TTI represents the first duration, l traj Vx represents the first distance. act and vy act These represent the velocity along the x-axis and the velocity along the y-axis in the first velocity data, respectively; in the case where TTI represents the second duration, l traj Vx represents the second distance. act and vy act These represent the velocity along the x-axis and the velocity along the y-axis in the second velocity data, respectively.

[0013] In some embodiments, each of the first distances and each of the second distances are determined using Formula Two, wherein Formula Two is specifically:

[0014]

[0015] Among them, l traj Indicates the first distance or the second distance, in l traj In the case of the first distance, N represents the number of the first sampling frames from the start of the current first sampling frame to the arrival of the left-turning vehicle at the intersection point, x k and y k These are the x-axis and y-axis coordinates of the left-turning vehicle in the k-th first sampling frame, with the current first sampling frame as the starting sampling frame. veh x represents the length of the left-turning vehicle. int and y int These are the x-axis and y-axis coordinates of the left-turning vehicle in the first sampling frame closest to the intersection point, respectively.

[0016] In l traj In the case of the second distance, N represents the number of the second sampling frames from the start of the current second sampling frame until the target oncoming straight-ahead vehicle reaches the intersection point, x k and y k These are the x-axis and y-axis coordinates of the target vehicle traveling straight ahead in the kth second sampling frame, with the current second sampling frame as the starting sampling frame. evh x represents the length of the oncoming straight-moving vehicle from the target. int and y int These are the coordinates of the target vehicle traveling straight in the opposite direction on the x and y axes in the second sampling frame closest to the intersection point.

[0017] In some embodiments, determining the target oncoming straight-ahead vehicle whose trajectory intersects with that of the left-turning vehicle during the passage of the target intersection includes: determining all oncoming straight-ahead vehicles corresponding to the left-turning vehicle during the passage of the target intersection; and determining the target oncoming straight-ahead vehicle from among the oncoming straight-ahead vehicles according to a target determination condition.

[0018] In some embodiments, the target determination conditions include: between the time frame when the left-turning vehicle enters the target intersection and the time frame when it leaves the target intersection, the envelope region of the left-turning vehicle always intersects with the area where the target intersection is located; between the time frame when the oncoming straight-ahead vehicle enters the target intersection and the time frame when it leaves the target intersection, the envelope region of the oncoming straight-ahead vehicle always intersects with the area where the target intersection is located; the intersection of each time frame when the left-turning vehicle passes through the target intersection and each time frame when the oncoming straight-ahead vehicle passes through the target intersection is not empty; and the driving trajectory of the left-turning vehicle intersects with the driving trajectory of the oncoming straight-ahead vehicle at a point.

[0019] In a second aspect, a computer device is provided, including a processor, a memory, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the vehicle right-of-way monitoring method as described in the first aspect.

[0020] By applying the above technical solutions, based on video monitoring data and electronic map data corresponding to the target intersection, the movement information of vehicles entering the target intersection and each vehicle is determined; when there are left-turning vehicles among the vehicles, the target oncoming straight-ahead vehicles whose trajectories intersect with the left-turning vehicles' trajectories during the time the left-turning vehicles pass through the target intersection are identified; based on the movement information of the left-turning vehicles, the first time required for the left-turning vehicles to reach the intersection point in each first sampling frame is determined, wherein each first sampling frame is the time from the left-turning vehicle entering the target intersection to reaching the intersection point, determined from the video monitoring data. The system determines the sampling frames; based on the motion information of oncoming straight-ahead vehicles, it determines the second duration required for each second sampling frame to reach the intersection point. Each second sampling frame is a sampling frame determined from video monitoring data from the time the oncoming straight-ahead vehicle enters the target intersection until it reaches the intersection point. It also determines target sampling frames that meet the target conditions from each first sampling frame, and determines the target first duration corresponding to the target sampling frame from each first duration, and the target second duration corresponding to the target sampling frame from each second duration. The right-of-way monitoring result is determined based on the target first duration and the target second duration. This enables the identification of right-of-way conflicts between left-turning vehicles and oncoming straight-ahead vehicles at intersections, thus allowing for more efficient and accurate monitoring of right-of-way at intersections throughout the day. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of this application, 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 recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of the vehicle right-of-way monitoring method according to an embodiment of this application;

[0023] Figure 2 This is a flowchart illustrating the determination of right-of-way monitoring results in an embodiment of this application;

[0024] Figure 3 This is a flowchart illustrating the determination of the first duration in an embodiment of this application;

[0025] Figure 4 This is a flowchart illustrating the determination of the second duration in an embodiment of this application;

[0026] Figure 5 This is a flowchart illustrating the determination of a target oncoming straight-moving vehicle according to an embodiment of this application.

[0027] Figure 6 This is a schematic diagram illustrating the principle of the vehicle right-of-way monitoring method according to an embodiment of this application;

[0028] Figure 7 This is a structural block diagram of a computer device according to an embodiment of this application. Detailed Implementation

[0029] Various embodiments and features of this application are described herein with reference to the accompanying drawings.

[0030] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this application will be apparent to those skilled in the art.

[0031] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0032] These and other features of this application will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0033] It should also be understood that although this application has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of this application.

[0034] The above and other aspects, features and advantages of this application will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0035] Specific embodiments of this application are described thereafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of this application, which can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the application. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but merely serve as the basis and representative basis for the claims to teach those skilled in the art to use this application in a variety of substantially any suitable detailed structures.

[0036] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in other embodiments,” all of which may refer to one or more of the same or different embodiments according to this application.

[0037] This application discloses a vehicle right-of-way monitoring method. Based on video monitoring data and electronic map data corresponding to a target intersection, it determines the vehicles entering the target intersection and their movement information. If left-turning vehicles are present, it identifies the oncoming straight-ahead vehicles whose trajectories intersect with the left-turning vehicles' trajectories during the left-turning vehicles' passage through the target intersection. It then determines the first time required for the left-turning vehicles to reach the intersection point and the second time required for the oncoming straight-ahead vehicles to reach the intersection point in the corresponding sampling frame. The right-of-way monitoring result is determined based on the first and second target timeframes corresponding to the target sampling frame. This method enables the identification of right-of-way conflicts between left-turning vehicles and oncoming straight-ahead vehicles at the intersection, thus allowing for more efficient and accurate monitoring of right-of-way at intersections throughout the entire time period.

[0038] like Figure 1 As shown, it includes the following steps:

[0039] Step S101: Based on the video monitoring data and electronic map data corresponding to the target intersection, determine the vehicles entering the target intersection and the movement information of each vehicle.

[0040] In this embodiment, the target intersection can be a crossroads or an intersection where right-of-way conflicts exist between left-turning and straight-going vehicles. Video monitoring data and electronic map data corresponding to the target intersection can be obtained through a roadside perception system installed at the target intersection. The roadside perception system may include one or more cameras and an electronic map module. The cameras are installed above each lane of the target intersection in the direction of oncoming traffic, ensuring that all cameras cover the entire area including the target intersection. The cameras are used to collect real-time images of their corresponding lanes, thereby obtaining video monitoring data. The electronic map module provides electronic map data corresponding to the target intersection. The electronic map data can be used to map the positions of vehicles in the video monitoring data, determining the vehicle's position and position changes on the electronic map. Based on the video monitoring data and electronic map data, the vehicles entering the target intersection and their movement information are determined. This vehicle movement information characterizes the movement of vehicles at the target intersection.

[0041] In some embodiments of this application, a vehicle is determined to have entered a target intersection when its bounding box intersects with the area where the target intersection is located. The intersection of the vehicle's bounding box and the area where the target intersection is located can be represented as:

[0042]

[0043] Where T(inIntersection) represents the intersection of the vehicle's envelope with the target intersection area, Car.Area is the planar area of ​​the vehicle's envelope projected perpendicularly to the ground, and Intersection.Area represents the area occupied by the target intersection. Optionally, the vehicle's envelope can be a rectangular area surrounding the vehicle, or it can be another shaped area surrounding the vehicle.

[0044] Step S102: If there is a left-turning vehicle among the vehicles, determine the target oncoming straight-going vehicle whose trajectory intersects with that of the left-turning vehicle while the left-turning vehicle is passing through the target intersection.

[0045] In this embodiment, the conflict of right-of-way between left-turning vehicles and oncoming straight-going vehicles is analyzed. According to existing traffic regulations, the right-of-way for left-turning vehicles is lower than that for oncoming straight-going vehicles that have been given the right of way.

[0046] A left-turning vehicle refers to a vehicle that needs to turn left during its journey. The process involves determining whether any vehicles entering the target intersection are left-turning vehicles. If a left-turning vehicle's bounding box no longer intersects with the area occupied by the target intersection, then the left-turning vehicle is considered to have left the target intersection. At this point, the video segment from the video monitoring data during the left-turning vehicle's passage through the target intersection is identified, and the oncoming straight-ahead vehicles whose trajectories intersect with the left-turning vehicle's trajectory in this video segment are identified. For example, Figure 6 This is a schematic diagram illustrating the principle of the vehicle right-of-way monitoring method according to an embodiment of this application, as shown below. Figure 6 As shown, the trajectories of left-turning vehicles and oncoming straight-going vehicles intersect at some point. Each left-turning vehicle can correspond to one or more oncoming straight-going vehicles.

[0047] Step S103: Based on the motion information of the left-turning vehicle, determine the first duration required for the left-turning vehicle to reach the intersection point in each first sampling frame, wherein each first sampling frame is a sampling frame determined from the video monitoring data during the period from when the left-turning vehicle enters the target intersection to when it reaches the intersection point.

[0048] In this embodiment, from the time a left-turning vehicle enters the target intersection to the time it reaches the intersection point, image frames of the video monitoring data are sampled to obtain each first sampling frame. In each first sampling frame, the left-turning vehicle is in a different position. Based on the motion information of the left-turning vehicle, the first time required for the left-turning vehicle to reach the intersection point from its corresponding position in each first sampling frame is determined.

[0049] Step S104: Based on the motion information of the target oncoming straight-ahead vehicle, determine the second duration required for the target oncoming straight-ahead vehicle to reach the intersection point in each second sampling frame, wherein each second sampling frame is a sampling frame determined from the video monitoring data from the time the target oncoming straight-ahead vehicle enters the target intersection until it reaches the intersection point.

[0050] In this embodiment, during the period from when the target oncoming straight-ahead vehicle enters the target intersection to when it reaches the intersection point, the image frames of the video monitoring data are sampled to obtain each second sampling frame. In each second sampling frame, the target oncoming straight-ahead vehicle is at a different position. Based on the motion information of the target oncoming straight-ahead vehicle, the second time required for the target oncoming straight-ahead vehicle to reach the intersection point from its corresponding position in each second sampling frame is determined.

[0051] In some embodiments of this application, each first duration forms a first TTI (Time to Intersection) sequence. left Each second duration forms a second TTI sequence. str , means as follows:

[0052]

[0053] Among them, f int,0 f is the frame number of the sampling frame corresponding to when the vehicle enters the target intersection. int,end This refers to the frame number of the sampling frame corresponding to when the vehicle leaves the target intersection. For example, such as... Figure 6 As shown, f int,0 f is the frame number of the sampling frame corresponding to the left-turning vehicle entering the target intersection. int,end This is the frame number of the sampling frame corresponding to the left-turning vehicle leaving the target intersection.

[0054] Step S105: Determine the target sampling frame that meets the target condition from each of the first sampling frames, determine the target first duration corresponding to the target sampling frame from each of the first durations, and determine the target second duration corresponding to the target sampling frame from each of the second durations.

[0055] In this embodiment, a target sampling frame that meets the target conditions is determined from each first sampling frame. The target sampling frame contains left-turning vehicles and target oncoming straight-going vehicles. Therefore, the target first duration corresponding to the target sampling frame can be determined from each first duration, and the target second duration corresponding to the target sampling frame can be determined from each second duration. It can be understood that the target first duration is the time required for a left-turning vehicle in the target sampling frame to reach the intersection point from its corresponding position, and the target second duration is the time required for a target oncoming straight-going vehicle in the target sampling frame to reach the intersection point from its corresponding position.

[0056] Step S106: Determine the right-of-way monitoring result based on the first target duration and the second target duration.

[0057] Based on the first and second target time periods, the right-of-way conflict between left-turning vehicles and oncoming straight-going vehicles is assessed to determine the right-of-way monitoring results. These results can then be displayed to users, allowing them to intuitively determine whether left-turning vehicles have violated right-of-way rules, thus improving the user experience. Alternatively, the right-of-way monitoring results can guide the decision-making of autonomous vehicles, thereby improving their reliability.

[0058] The vehicle right-of-way monitoring method of this application embodiment determines the vehicles entering the target intersection and their movement information based on video monitoring data and electronic map data corresponding to the target intersection; when there are left-turning vehicles among the vehicles, it determines the target oncoming straight-ahead vehicles whose travel trajectories intersect with the left-turning vehicles' travel trajectories during the left-turning vehicles' passage through the target intersection; based on the left-turning vehicles' movement information, it determines the first time required for the left-turning vehicles to reach the intersection point in each first sampling frame, wherein each first sampling frame is the time from the left-turning vehicle entering the target intersection to reaching the intersection point, based on the video monitoring data... Based on the sampling frames determined in the first sampling frame, and based on the motion information of the oncoming straight-ahead vehicles, the second duration required for the oncoming straight-ahead vehicles to reach the intersection point is determined in each second sampling frame. Each second sampling frame is a sampling frame determined from the video monitoring data from the time the oncoming straight-ahead vehicle enters the target intersection until it reaches the intersection point. Target sampling frames that meet the target conditions are determined from each first sampling frame, and the target first duration corresponding to the target sampling frame is determined from each first duration. The target second duration corresponding to the target sampling frame is determined from each second duration. The right-of-way monitoring result is determined based on the target first duration and the target second duration. This enables the identification of right-of-way conflicts between left-turning vehicles and oncoming straight-ahead vehicles at the intersection, thus allowing for more efficient and accurate monitoring of right-of-way at the intersection throughout the entire time period.

[0059] In some embodiments of this application, the step of determining the right-of-way monitoring result based on the first target duration and the second target duration is as follows: Figure 2 As shown, it includes the following steps:

[0060] Step S1061: Determine the difference between the target second duration and the target first duration.

[0061] In this embodiment, the difference is obtained by subtracting the first target duration from the second target duration.

[0062] Step S1062: If the difference is not less than the target threshold, it is determined that the left-turning vehicle has not violated the right-of-way.

[0063] The difference is compared with the target threshold. If the difference is not less than the target threshold, it is determined that the left-turning vehicle did not obstruct the passage of the oncoming straight-going vehicle, and the left-turning vehicle did not violate the right-of-way.

[0064] Step S1063: If the difference is less than the target threshold, determine whether the left-turning vehicle violates the right-of-way based on the order in which the left-turning vehicle and the target oncoming straight-ahead vehicle arrive at the intersection point.

[0065] In this embodiment, if the difference is less than the target threshold, the order in which the left-turning vehicle and the target oncoming straight-going vehicle arrive at the intersection point is determined, and whether the left-turning vehicle violates the right-of-way is determined based on this order.

[0066] By using the difference between the first and second target durations, and the order in which left-turning vehicles and oncoming straight-ahead vehicles arrive at the intersection, it is possible to efficiently and accurately determine whether a left-turning vehicle has violated its right-of-way.

[0067] In some embodiments of this application, the target threshold is 3.4s.

[0068] Alternatively, as an alternative, the absolute value of the difference between the first target duration and the second target duration can be determined first. If the absolute value of the difference is not less than the target threshold, it can be determined that the left-turning vehicle has not violated the right-of-way. If the absolute value of the difference is less than the target threshold, it can be determined whether the left-turning vehicle has violated the right-of-way based on the order in which the left-turning vehicle and the oncoming straight-going vehicle arrive at the intersection point.

[0069] In some embodiments of this application, determining whether the left-turning vehicle violates its right-of-way based on the order in which the left-turning vehicle and the oncoming straight-going vehicle arrive at the intersection includes:

[0070] If the left-turning vehicle arrives at the intersection point first, it is determined that the left-turning vehicle violated the right-of-way.

[0071] If the left-turning vehicle does not arrive at the intersection point first, it is determined that the left-turning vehicle has not violated the right-of-way.

[0072] In this embodiment, it is determined whether the left-turning vehicle arrives at the intersection point first. If the left-turning vehicle arrives at the intersection point first, it indicates that the left-turning vehicle is obstructing the passage of oncoming straight-ahead vehicles, and the left-turning vehicle is determined to have violated its right-of-way. If the left-turning vehicle does not arrive at the intersection point first, it indicates that the left-turning vehicle is not obstructing the passage of oncoming straight-ahead vehicles, and the left-turning vehicle is determined not to have violated its right-of-way, thereby achieving efficient determination of whether a left-turning vehicle has violated its right-of-way.

[0073] In some embodiments of this application, the target condition includes one of the following:

[0074] The envelope area of ​​the left-turning vehicle begins to encroach on the straight-going lane where the target oncoming straight-going vehicle is located;

[0075] The distance between the envelope area of ​​the left-turning vehicle and the straight-ahead lane is less than the target distance.

[0076] In this embodiment, the envelope region of the left-turning vehicle can be a rectangular region surrounding the left-turning vehicle, or it can be a region of other shapes surrounding the left-turning vehicle. The lane line of the straight-going lane where the target oncoming straight-going vehicle is located can be determined using video monitoring data. If the envelope region of the left-turning vehicle in the first sampling frame begins to intersect with the lane line of the straight-going lane, it is determined that the envelope region of the left-turning vehicle has begun to encroach on the straight-going lane, thus determining the first sampling frame as the target sampling frame. Alternatively, the distance between the envelope region of the left-turning vehicle in the first sampling frame and the lane line of the straight-going lane can also be determined. If this distance is less than a target distance, the first sampling frame is determined as the target sampling frame, thus allowing for more flexible and efficient determination of the target sampling frame. For example, such as... Figure 6 As shown, Figure 6 f in encroach This indicates the frame number of the target sampling frame, in which the envelope of the left-turning vehicle in the target sampling frame begins to intersect with the straight lane where the target oncoming straight vehicle is located.

[0077] In some embodiments of this application, the motion information includes position information and speed information. The step of determining the first time required for the left-turning vehicle to reach the intersection point in each first sampling frame, based on the motion information of the left-turning vehicle, is as follows: Figure 3 As shown, it includes the following steps:

[0078] Step S1031: Determine the first speed data of the left-turning vehicle in the first sampling frame based on the speed information of the left-turning vehicle.

[0079] In this embodiment, the motion information of the left-turning vehicle includes the position information and speed information of the left-turning vehicle, and the first speed data of the left-turning vehicle in the first sampling frame is determined based on the speed information of the left-turning vehicle.

[0080] Step S1032: Determine the first distance between the left-turning vehicle and the intersection point in the first sampling frame based on the position information of the left-turning vehicle.

[0081] The first distance between the left-turning vehicle and the intersection point in the first sampling frame is determined based on the position information of the left-turning vehicle and the position information of the intersection point.

[0082] Step S1033: Determine the first duration based on the first speed data and the first distance.

[0083] In this embodiment, the speed of the left-turning vehicle in the first sampling frame can be determined by the first speed data, and the first duration can be determined by dividing the first distance by the speed of the left-turning vehicle, thereby achieving efficient and accurate determination of each first duration.

[0084] Based on the motion information of the oncoming straight-ahead vehicles, the second time required for the oncoming straight-ahead vehicles to reach the intersection point in each second sampling frame is determined, such as... Figure 4 As shown, it includes the following steps:

[0085] Step S1041: Determine the second speed data of the target oncoming straight-ahead vehicle in the second sampling frame based on the speed information of the target oncoming straight-ahead vehicle.

[0086] In this embodiment, the motion information of the target oncoming straight-ahead vehicle includes the position information and speed information of the target oncoming straight-ahead vehicle. The second speed data of the target oncoming straight-ahead vehicle in the second sampling frame is determined based on the speed information of the target oncoming straight-ahead vehicle.

[0087] Step S1042: Determine the second distance between the target oncoming straight-ahead vehicle and the intersection point in the second sampling frame based on the position information of the target oncoming straight-ahead vehicle.

[0088] The second distance between the target vehicle traveling straight ahead and the intersection point in the first sampling frame is determined based on the position information of the target vehicle traveling straight ahead and the position information of the intersection point.

[0089] Step S1043: Determine the second duration based on the second speed data and the second distance.

[0090] In this embodiment, the speed of the oncoming straight-ahead vehicle in the second sampling frame can be determined by the second speed data, and the second duration can be determined by dividing the second distance by the speed of the oncoming straight-ahead vehicle, thereby achieving efficient and accurate determination of each second duration.

[0091] In some embodiments of this application, Formula 1 is used to determine each of the first durations and each of the second durations, wherein Formula 1 is specifically:

[0092]

[0093] Wherein, TTI represents the first duration or the second duration, and when TTI represents the first duration, l traj Vx represents the first distance. act and vy act These represent the velocity along the x-axis and the velocity along the y-axis in the first velocity data, respectively; in the case where TTI represents the second duration, l traj Vx represents the second distance.act and vy act These represent the velocity along the x-axis and the velocity along the y-axis in the second velocity data, respectively.

[0094] By utilizing Formula 1, the accuracy of each first duration and each second duration was improved.

[0095] In some embodiments of this application, each of the first distances and each of the second distances are determined using Formula 2, which is specifically:

[0096]

[0097] Among them, l traj Indicates the first distance or the second distance, in l traj In the case of the first distance, N represents the number of the first sampling frames from the start of the current first sampling frame to the arrival of the left-turning vehicle at the intersection point, x k and y k These are the x-axis and y-axis coordinates of the left-turning vehicle in the k-th first sampling frame, with the current first sampling frame as the starting sampling frame. veh x represents the length of the left-turning vehicle. int and y int These are the x-axis and y-axis coordinates of the left-turning vehicle in the first sampling frame closest to the intersection point, respectively.

[0098] In l traj In the case of the second distance, N represents the number of the second sampling frames from the start of the current second sampling frame until the target oncoming straight-ahead vehicle reaches the intersection point, x k and y k These are the x-axis and y-axis coordinates of the target vehicle traveling straight ahead in the kth second sampling frame, with the current second sampling frame as the starting sampling frame. veh x represents the length of the oncoming straight-moving vehicle from the target. int and y int These are the coordinates of the target vehicle traveling straight in the opposite direction on the x and y axes in the second sampling frame closest to the intersection point.

[0099] By utilizing Formula 2, the accuracy of each first distance and each second distance is further improved.

[0100] In some embodiments of this application, the determination of a target oncoming straight-ahead vehicle whose trajectory intersects with that of the left-turning vehicle during the passage of the target intersection is as follows: Figure 5 As shown, it includes the following steps:

[0101] Step S1021: Determine all oncoming straight-ahead vehicles corresponding to the left-turning vehicle during the time the left-turning vehicle passes through the target intersection.

[0102] In this embodiment, the period during which a left-turning vehicle passes through the target intersection is from the time the left-turning vehicle enters the target intersection to the time the left-turning vehicle leaves the target intersection. During this period, all oncoming straight-ahead vehicles corresponding to the left-turning vehicle are identified, and then, among these oncoming straight-ahead vehicles, target oncoming straight-ahead vehicles whose travel trajectories intersect with the travel trajectory of the left-turning vehicle are identified.

[0103] Step S1022: Determine the target oncoming straight-ahead vehicle from among the oncoming straight-ahead vehicles according to the target determination conditions.

[0104] In this embodiment, target determination conditions are used to determine each oncoming straight-ahead vehicle, and the target oncoming straight-ahead vehicle is determined based on the determination results, thereby determining the target oncoming straight-ahead vehicle more efficiently.

[0105] In some embodiments of this application, the target determination conditions include:

[0106] Between the time frame when the left-turning vehicle enters the target intersection and the time frame when it leaves the target intersection, the envelope region of the left-turning vehicle always intersects with the region where the target intersection is located, and...

[0107] Between the time frame when the oncoming straight-ahead vehicle enters the target intersection and the time frame when it leaves the target intersection, the envelope region of the oncoming straight-ahead vehicle always intersects with the region where the target intersection is located, and...

[0108] The intersection of the time frames of the left-turning vehicle passing through the target intersection and the time frames of the oncoming straight-through vehicle passing through the target intersection is not empty, and,

[0109] The trajectory of the vehicle turning left intersects with the trajectory of the vehicle going straight in the opposite direction.

[0110] In this embodiment, if the envelope region of a left-turning vehicle always intersects with the area of ​​the target intersection between the time frame when the vehicle enters the target intersection and the time frame when it leaves the target intersection, it indicates that the left-turning vehicle is always at the target intersection from the time frame it enters to the time frame when it leaves the target intersection. If the envelope region of an oncoming straight-ahead vehicle always intersects with the area of ​​the target intersection between the time frame when the vehicle enters the target intersection and the time frame when the vehicle on the opposite side of the intersection enters, it indicates that the vehicle on the opposite side of the intersection is always at the target intersection from the time frame it enters to the time frame when it leaves. If the intersection of each time frame when the left-turning vehicle passes through the target intersection and each time frame when the vehicle on the opposite side of the intersection passes through the target intersection is not empty, it indicates that the left-turning vehicle and the vehicle on the opposite side of the intersection interact in time. If the trajectory of the left-turning vehicle intersects with the trajectory of the vehicle on the opposite side of the intersection, it indicates that the left-turning vehicle and the vehicle on the opposite side of the intersection interact in space. By using the intersection of multiple different scenarios, it can be determined whether the target judgment conditions are met, thus achieving a more accurate identification of oncoming straight-moving vehicles.

[0111] In some embodiments of this application, the target determination condition can be expressed by Formula 3, which is specifically as follows:

[0112]

[0113] Among them, f 10 f represents the time frame when the left-turning vehicle enters the target intersection. lend f represents the time frame when the left-turning vehicle leaves the target intersection. s0 f represents the time frame when the oncoming straight-ahead vehicle enters the target intersection. send This represents the time frame when the oncoming straight-ahead vehicle leaves the target intersection, [f 10 f lend ] represents f 10 to f lend Between each time frame, [f s0 f send ] represents f s0 to f send Between time frames, Tgt left .Area represents the envelope area of ​​the left-turning vehicles, Intersection.InsideArea represents the area where the target intersection is located, and Tgt OSMV .Area represents the envelope area of ​​the oncoming straight-ahead vehicles, Tgt left .Traj represents the trajectory of the vehicle making the left turn, and Tgt represents the trajectory of the vehicle making the left turn. OSMV .Traj represents the trajectory of the opposing straight-moving vehicle.

[0114] Based on the same concept, embodiments of this application also provide a computer device, such as... Figure 7 As shown, it includes a processor and a memory, wherein the memory stores an executable program, and the processor executes the executable program to perform the steps of the vehicle right-of-way monitoring method as described in the various embodiments of this application.

[0115] The computer device in this application embodiment can be a terminal or other devices besides a terminal. For example, the computer device can be a mobile phone, tablet computer, laptop computer, handheld computer, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. The embodiments disclosed in this disclosure do not impose specific limitations.

[0116] The memory may include RAM (Random Access Memory) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0117] The processors mentioned above can be general-purpose processors, including CPUs, NPs (Network Processors), etc.; they can also be DSPs (Digital Signal Processors), ASICs (Application Specific Integrated Circuits), FPGAs (Field Programmable Gate Arrays), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0118] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0119] The above embodiments are merely exemplary embodiments of this application and are not intended to limit this application. The scope of protection of this application is defined by the claims. Those skilled in the art can make various modifications or equivalent substitutions to this application within its substance and scope of protection, and such modifications or equivalent substitutions should also be considered to fall within the scope of protection of this application.

Claims

1. A method for monitoring vehicle right-of-way, characterized in that, include: Based on video monitoring data and electronic map data corresponding to the target intersection, determine the vehicles entering the target intersection and the movement information of each vehicle; If there is a left-turning vehicle among the vehicles, identify the target oncoming straight-going vehicle whose trajectory intersects with that of the left-turning vehicle while the left-turning vehicle is passing through the target intersection. Based on the motion information of the left-turning vehicle, the first duration required for the left-turning vehicle to reach the intersection point in each first sampling frame is determined, wherein each first sampling frame is a sampling frame determined from the video monitoring data during the period from when the left-turning vehicle enters the target intersection to when it reaches the intersection point; Based on the motion information of the oncoming straight-ahead vehicle, the second duration required for the oncoming straight-ahead vehicle to reach the intersection point in each second sampling frame is determined, wherein each second sampling frame is a sampling frame determined from the video monitoring data from the time the oncoming straight-ahead vehicle enters the target intersection until it reaches the intersection point; From each of the first sampling frames, a target sampling frame that meets the target condition is determined, and from each of the first durations, a target first duration corresponding to the target sampling frame is determined, and from each of the second durations, a target second duration corresponding to the target sampling frame is determined; The right-of-way monitoring results are determined based on the first target duration and the second target duration.

2. The vehicle right-of-way monitoring method as described in claim 1, characterized in that, The step of determining the right-of-way monitoring result based on the first target duration and the second target duration includes: Determine the difference between the second target duration and the first target duration; If the difference is not less than the target threshold, it is determined that the left-turning vehicle has not violated the right-of-way. If the difference is less than the target threshold, it is determined whether the left-turning vehicle violated the right-of-way based on the order in which the left-turning vehicle and the oncoming straight-going vehicle arrived at the intersection point.

3. The vehicle right-of-way monitoring method as described in claim 2, characterized in that, The step of determining whether a left-turning vehicle violates its right-of-way based on the order in which the left-turning vehicle and the oncoming straight-going vehicle arrive at the intersection includes: If the left-turning vehicle arrives at the intersection point first, it is determined that the left-turning vehicle violated the right-of-way. If the left-turning vehicle does not arrive at the intersection point first, it is determined that the left-turning vehicle has not violated the right-of-way.

4. The vehicle right-of-way monitoring method as described in claim 1, characterized in that, The target condition includes one of the following: The envelope area of ​​the left-turning vehicle begins to encroach on the straight-going lane where the target oncoming straight-going vehicle is located; The distance between the envelope area of ​​the left-turning vehicle and the straight-ahead lane is less than the target distance.

5. The vehicle right-of-way monitoring method as described in claim 1, characterized in that, The motion information includes position information and speed information. The step of determining the first time required for the left-turning vehicle to reach the intersection point in each first sampling frame, based on the motion information of the left-turning vehicle, includes: The first speed data of the left-turning vehicle in the first sampling frame is determined based on the speed information of the left-turning vehicle. The first distance between the left-turning vehicle and the intersection point in the first sampling frame is determined based on the position information of the left-turning vehicle. The first duration is determined based on the first speed data and the first distance; The step of determining the second time required for the target vehicle to reach the intersection point in each second sampling frame based on the motion information of the target vehicle traveling straight ahead includes: The second speed data of the target oncoming straight-ahead vehicle in the second sampling frame is determined based on the speed information of the target oncoming straight-ahead vehicle; The second distance between the target vehicle traveling straight ahead and the intersection point in the second sampling frame is determined based on the position information of the target vehicle traveling straight ahead. The second duration is determined based on the second speed data and the second distance.

6. The vehicle right-of-way monitoring method as described in claim 5, characterized in that, The first duration and the second duration are determined using Formula 1, which is specifically as follows: Wherein, TTI represents the first duration or the second duration, and when TTI represents the first duration, l traj Vx represents the first distance. act and vy act These represent the velocity along the x-axis and the velocity along the y-axis in the first velocity data, respectively; in the case where TTI represents the second duration, l traj Vx represents the second distance. act and vy act These represent the velocity along the x-axis and the velocity along the y-axis in the second velocity data, respectively.

7. The vehicle right-of-way monitoring method as described in claim 5, characterized in that, Formula 2 is used to determine each of the first distances and each of the second distances, and Formula 2 is specifically as follows: Among them, l traj Indicates the first distance or the second distance, in l traj In the case of the first distance, N represents the number of the first sampling frames from the start of the current first sampling frame to the arrival of the left-turning vehicle at the intersection point, x k and y k These are the x-axis and y-axis coordinates of the left-turning vehicle in the k-th first sampling frame, with the current first sampling frame as the starting sampling frame. evh x represents the length of the left-turning vehicle. int and y int These are the x-axis and y-axis coordinates of the left-turning vehicle in the first sampling frame closest to the intersection point, respectively. In l traj In the case of the second distance, N represents the number of the second sampling frames from the start of the current second sampling frame until the target oncoming straight-ahead vehicle reaches the intersection point, x k and y k These are the x-axis and y-axis coordinates of the target vehicle traveling straight ahead in the kth second sampling frame, with the current second sampling frame as the starting sampling frame. veh x represents the length of the oncoming straight-moving vehicle from the target. int and y int These are the coordinates of the target vehicle traveling straight in the opposite direction on the x and y axes in the second sampling frame closest to the intersection point.

8. The vehicle right-of-way monitoring method as described in claim 1, characterized in that, The determination of the oncoming straight-going vehicles whose trajectories intersect with those of the left-turning vehicle during the passage of the target intersection includes: Identify all oncoming straight-ahead vehicles corresponding to the left-turning vehicle during the time the left-turning vehicle passes through the target intersection; The target oncoming straight-ahead vehicle is determined from the various oncoming straight-ahead vehicles according to the target determination criteria.

9. The vehicle right-of-way monitoring method as described in claim 8, characterized in that, The target determination criteria include: Between the time frame when the left-turning vehicle enters the target intersection and the time frame when it leaves the target intersection, the envelope region of the left-turning vehicle always intersects with the region where the target intersection is located, and... Between the time frame when the oncoming straight-ahead vehicle enters the target intersection and the time frame when it leaves the target intersection, the envelope region of the oncoming straight-ahead vehicle always intersects with the region where the target intersection is located, and... The intersection of the time frames of the left-turning vehicle passing through the target intersection and the time frames of the oncoming straight-through vehicle passing through the target intersection is not empty, and, The trajectory of the vehicle turning left intersects with the trajectory of the vehicle going straight in the opposite direction.

10. A computer device comprising a processor, a memory, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the vehicle right-of-way monitoring method as described in any one of claims 1-9.

Images