Traffic Conflict Recognition Method, Device, Storage Medium and Electronic Device

Abstract

The present invention discloses a traffic conflict recognition method, device, storage medium and electronic device. Among them, the above method includes: obtaining vehicle trajectory data of a level crossing in a target city within a preset time period, and road basic data of the level crossing; determining the speed, heading angle and heading of each vehicle according to the vehicle trajectory data and the road basic data; wherein, the heading angle is the included angle between the head direction of the vehicle and a preset direction; determining whether a traffic conflict occurs between a first vehicle and a second vehicle by using a preset conflict recognition model based on the headings of the first vehicle and the second vehicle; wherein, the first vehicle and the second vehicle are different vehicles in the vehicle trajectory data; if so, determining the time, location and conflict type of the traffic conflict between the first vehicle and the second vehicle. The present invention solves the technical problem in the related art that traffic conflict recognition cannot be performed between vehicles at a lane level in urban intersections.

Description

Technical Field

[0001] The present invention relates to the technical field of position processing, and in particular, to a traffic conflict recognition method, device, storage medium, and electronic device. Background Art

[0002] Urban road intersections are an important part of urban traffic. They not only connect complex road networks but also gather and disperse vehicles and pedestrians from different directions. Whether they can operate normally directly determines the smoothness and safety of the roads connected to them. And traffic conflicts at intersections are one of the keys to evaluating the operation efficiency and safety of urban road intersections. Currently, the related technologies mainly focus on the research of traffic conflicts under signal control, while the research on traffic conflicts at intersections is relatively less. Most of them focus on the construction of safety evaluation index systems and evaluation methods, and the model methods used are relatively complex and difficult to be directly used in practical applications. Therefore, there is currently no effective technical means to identify traffic conflicts between vehicles at urban intersections. Summary of the Invention

[0003] Embodiments of the present invention provide a traffic conflict recognition method, device, storage medium, and electronic device to at least solve the technical problem in the related technologies that traffic conflicts between vehicles at lane-level urban intersections cannot be recognized.

[0004] According to one aspect of the embodiments of the present invention, a traffic conflict recognition method is provided, including: obtaining vehicle trajectory data of an intersection of a target city within a preset time period, and road basic data of the intersection; determining the speed, heading angle, and heading of each vehicle according to the vehicle trajectory data and the road basic data; where the heading angle is the angle between the front direction of the vehicle and a preset direction; determining whether a traffic conflict occurs between a first vehicle and a second vehicle by using a preset conflict recognition model based on the headings of the first vehicle and the second vehicle; where the conflict recognition model is a recognition model for judging whether the two vehicles collide according to the time to collision (TTC) value of the two vehicles, and the first vehicle and the second vehicle are different vehicles in the vehicle trajectory data; if so, determining the time, position, and conflict type of the traffic conflict between the first vehicle and the second vehicle.

[0005] According to another aspect of the embodiments of the present invention, there is also provided a traffic conflict recognition device, including: a first acquisition unit configured to acquire vehicle trajectory data of a level crossing in a target city within a preset time period, and road basic data of the level crossing; a first determination unit configured to determine the speed, heading angle, and heading of each vehicle according to the vehicle trajectory data and the road basic data; wherein the heading angle is the angle between the front direction of the vehicle and a preset direction; a second determination unit configured to determine whether a traffic conflict occurs between a first vehicle and a second vehicle based on the headings of the first vehicle and the second vehicle by using a preset conflict recognition model; wherein the conflict recognition model is a recognition model for determining whether the two vehicles collide according to the time to collision (TTC) value of the two vehicles, and the first vehicle and the second vehicle are different vehicles in the vehicle trajectory data; a third determination unit configured to determine the time, location, and conflict type of the traffic conflict between the first vehicle and the second vehicle.

[0006] According to still another aspect of the embodiments of the present invention, there is also provided an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned traffic conflict recognition method through the computer program.

[0007] According to still another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, and the computer program is configured to execute the above-mentioned traffic conflict recognition method when running.

[0008] In the embodiments of the present invention, a method is adopted, which includes acquiring vehicle trajectory data of a level crossing in a target city within a preset time period, and road basic data of the level crossing; determining the speed, heading angle, and heading of each vehicle according to the vehicle trajectory data and the road basic data; wherein the heading angle is the angle between the front direction of the vehicle and a preset direction; determining whether a traffic conflict occurs between a first vehicle and a second vehicle based on the headings of the first vehicle and the second vehicle by using a preset conflict recognition model; wherein the conflict recognition model is a recognition model for determining whether the two vehicles collide according to the time to collision (TTC) value of the two vehicles, and the first vehicle and the second vehicle are different vehicles in the vehicle trajectory data; if so, determining the time, location, and conflict type of the traffic conflict between the first vehicle and the second vehicle. In the above method, since it is determined whether a traffic conflict occurs between the first vehicle and the second vehicle based on the headings of the first vehicle and the second vehicle and the time to collision (TTC), and by using a preset conflict recognition model, traffic conflicts at urban road intersections can be effectively recognized, which helps to manage urban road congestion, and further solves the technical problem in the related art that traffic conflict recognition cannot be performed between vehicles at lane-level urban intersections. Description of the Drawings

[0009] The accompanying drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0010] Figure 1 is a schematic diagram of an application environment of an alternative traffic conflict recognition method according to an embodiment of the present invention;

[0011] Figure 2 is a schematic diagram of an application environment of another alternative traffic conflict recognition method according to an embodiment of the present invention;

[0012] Figure 3 is a schematic flowchart of an alternative traffic conflict recognition method according to an embodiment of the present invention;

[0013] Figure 4 is a schematic flowchart of another alternative traffic conflict recognition method according to an embodiment of the present invention;

[0014] Figure 5 is a schematic diagram of a TTC calculation method of an alternative traffic conflict recognition method according to an embodiment of the present invention;

[0015] Figure 6 is a schematic diagram of a TTC calculation method of another alternative traffic conflict recognition method according to an embodiment of the present invention;

[0016] Figure 7 is a schematic diagram of a TTC calculation method of another alternative traffic conflict recognition method according to an embodiment of the present invention;

[0017] Figure 8 is a schematic diagram of a traffic conflict recognition model of another alternative traffic conflict recognition method according to an embodiment of the present invention;

[0018] Figure 9 is a schematic diagram of the spatial distribution of different conflict types of an alternative traffic conflict recognition method according to an embodiment of the present invention;

[0019] Figure 10 is a schematic diagram of the spatial distribution of a merging conflict of another alternative traffic conflict recognition method according to an embodiment of the present invention;

[0020] Figure 11 is a schematic diagram of the spatial distribution of a diverging conflict of another alternative traffic conflict recognition method according to an embodiment of the present invention;

[0021] Figure 12 is a schematic diagram of the spatial distribution of an intersection conflict of another alternative traffic conflict recognition method according to an embodiment of the present invention;

[0022] Figure 13 It is a schematic diagram of the time distribution of another optional different type of traffic conflict according to an embodiment of the present invention;

[0023] Figure 14 It is a schematic structural diagram of an optional traffic conflict recognition device according to an embodiment of the present invention;

[0024] Figure 15 It is a schematic structural diagram of an optional electronic device according to an embodiment of the present invention. Detailed implementation manners

[0025] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0027] According to one aspect of the embodiments of the present invention, a traffic conflict recognition method is provided. As an optional implementation manner, the above traffic conflict recognition method can be but is not limited to being applied to, for example Figure 1In the application environment shown. The application environment includes: a terminal device 102 for human-computer interaction with the user, a network 104, and a server 106. There can be human-computer interaction between the user 108 and the terminal device 102, and a traffic conflict recognition application program runs in the terminal device 102. The above terminal device 102 includes a human-computer interaction screen 1022, a processor 1024, and a memory 1026. The human-computer interaction screen 1022 is used to display the vehicle trajectory data of the level crossings in multiple target cities and the road basic data of the level crossings, the time, location, and conflict type of traffic conflicts; the processor 1024 is used to obtain the vehicle trajectory data of the level crossings in the target city and the road basic data of the level crossings. The memory 1026 is used to store the vehicle trajectory data of the level crossings in the target city and the road basic data of the level crossings.

[0028] In addition, the server 106 includes a database 1062 and a processing engine 1064. The database 1062 is used to store the vehicle trajectory data of the level crossings in the target city and the road basic data of the level crossings. The processing engine 1064 is used to determine the speed, heading angle, and heading of each vehicle according to the vehicle trajectory data and the road basic data; wherein, the heading angle is the included angle between the front direction of the vehicle and a preset direction; based on the headings of the first vehicle and the second vehicle, use a preset conflict recognition model to determine whether the first vehicle and the second vehicle have a traffic conflict; wherein, the conflict recognition model is a recognition model for judging whether the two vehicles collide according to the time to collision (TTC) value of the two vehicles, and the first vehicle and the second vehicle are different vehicles in the vehicle trajectory data; if so, determine the time, location, and conflict type of the traffic conflict between the first vehicle and the second vehicle; display the time, location, and conflict type of the traffic conflict on the client of the above terminal device 102.

[0029] In one or more embodiments, the above traffic conflict recognition method of the present application can be applied to Figure 2 the application environment shown. As Figure 2 shown, there can be human-computer interaction between the user 202 and the user device 204. The user device 204 includes a memory 206 and a processor 208. In this embodiment, the user device 204 can, but is not limited to, refer to and execute the operations performed by the above terminal device 102 to obtain the time, location, and conflict type of traffic conflicts occurring at the level crossings in the target city.

[0030] Optionally, the above-mentioned terminal device 102 and user device 204 include, but are not limited to, terminals such as mobile phones, set-top boxes, televisions, tablet computers, laptops, PCs, in-vehicle electronic devices, and wearable devices. The above-mentioned network 104 may include, but is not limited to, a wireless network or a wired network. Among them, the wireless network includes: WIFI and other networks that implement wireless communication. The above-mentioned wired network may include, but is not limited to: wide area network, metropolitan area network, and local area network. The above-mentioned server 106 may include, but is not limited to, any hardware device that can perform calculations. The above-mentioned server may be a single server, or a server cluster composed of multiple servers, or a cloud server. The above is only an example, and this embodiment does not make any limitations thereto.

[0031] As an alternative implementation, as Figure 3 shown, an embodiment of the present invention provides a traffic conflict recognition method, including the following steps:

[0032] S302, obtain the vehicle trajectory data of the intersection in the target city within a preset time period, and the road basic data of the intersection.

[0033] Specifically, in the embodiment of the present invention, it includes, but is not limited to, using video and radar detection devices deployed at intersections to collect the time and position information of passing vehicles, and using this as the vehicle trajectory data. The road basic data of the intersection here includes lane division data and lane function data. For example, the number of import lanes and export lanes at the intersection, and the lane function data includes the direction signs of the import lanes and the direction signs of the export lanes, etc. For example, the vehicle trajectory data includes the data structure of vehicle trajectory points shown in Table 1.

[0034] Table 1

[0035]

[0036] Table 1 (continued)

[0037]

[0038] S304, determine the speed, heading angle, and heading of each vehicle according to the vehicle trajectory data and the road basic data; where the heading angle is the included angle between the front direction of the vehicle and a preset direction.

[0039] Specifically, it includes, but is not limited to, obtaining the speed of the vehicle according to the distance between the trajectories of the vehicle in two time periods, or obtaining the speed of the vehicle through a speed measurement radar; here, the direction of the preset direction can be determined according to actual operation needs. For example, as shown in Table 2, the heading angle includes, but is not limited to, the clockwise included angle between the front direction of the vehicle and the due north direction. Here, θ can take an empirical value of 10°.

[0040] Table 2

[0041] Serial number Course Starting course angle End course angle 1 North to east [180 - θ, 180 + θ] [90 - θ, 90 + θ] 2 North to west [180 - θ, 180 + θ] [270 - θ, 270 + θ] 3 East to south [270 - θ, 270 + θ] [180 - θ, 180 + θ] 4 East to north [270 - θ, 270 + θ] [360 - θ, 360] ∪ [0, θ] 5 South to east [360 - θ, 360] ∪ [0, θ] [90 - θ, 90 + θ] 6 South to west [360 - θ, 360] ∪ [0, θ] [270 - θ, 270 + θ] 7 West to north [90 - θ, 90 + θ] [360 - θ, 360] ∪ [0, θ] 8 West to south [90 - θ, 90 + θ] [180 - θ, 180 + θ] 9 North to south [180 - θ, 180 + θ] [180 - θ, 180 + θ] 10 South to north [360 - θ, 360] ∪ [0, θ] [360 - θ, 360] ∪ [0, θ] 11 East to west [270 - θ, 270 + θ] [270 - θ, 270 + θ] 12 West to east [90 - θ, 90 + θ] [90 - θ, 90 + θ]

[0042] S306, determine whether there is a traffic conflict between the first vehicle and the second vehicle by using a preset conflict recognition model based on the headings of the first vehicle and the second vehicle; wherein, the conflict recognition model is a recognition model for judging whether the two vehicles collide according to the time to collision (TTC) value of the two vehicles, and the first vehicle and the second vehicle are different vehicles in the vehicle trajectory data.

[0043] Specifically, the embodiments of the present invention include but are not limited to using the time to collision (TTC) as a metric for traffic conflicts, taking the headings of the two vehicles as the basis for judging the types of traffic conflicts, and using a preset conflict recognition model to identify traffic conflicts between different vehicles with different types of headings in the public area of the intersection.

[0044] S308, if so, determine the time, location and type of the traffic conflict between the first vehicle and the second vehicle.

[0045] In the embodiments of the present invention, the types of vehicle traffic conflicts include but are not limited to diverging conflicts, merging conflicts, crossing conflicts, etc.

[0046] In the embodiments of the present invention, vehicle trajectory data of the intersections in the target city within a preset time period and road basic data of the intersections are acquired; the speed, heading angle and heading of each vehicle are determined according to the vehicle trajectory data and the road basic data; wherein, the heading angle is the angle between the head direction of the vehicle and a preset direction. Determine whether there is a traffic conflict between the first vehicle and the second vehicle by using a preset conflict recognition model based on the headings of the first vehicle and the second vehicle; wherein, the conflict recognition model is a recognition model for judging whether the two vehicles collide according to the time to collision (TTC) value of the two vehicles, and the first vehicle and the second vehicle are different vehicles in the vehicle trajectory data; if so, determine the time, location and type of the traffic conflict between the first vehicle and the second vehicle. In the above method, since it is determined whether there is a traffic conflict between the first vehicle and the second vehicle based on the headings and the time to collision (TTC) of the first vehicle and the second vehicle and by using a preset conflict recognition model, traffic conflicts at urban traffic intersections can be effectively identified, which helps to manage urban road congestion, and further solves the technical problem in the related art that traffic conflict recognition between vehicles at urban intersections based on lane level cannot be achieved.

[0047] In one or more embodiments, determining the heading of each vehicle according to the vehicle trajectory data and the road basic data includes:

[0048] Determine a first set of target vehicles in the vehicle trajectory data whose starting points and ending points are both on the lane, and determine a second set of target vehicles in the vehicle trajectory data other than the first set of target vehicles;

[0049] If the starting point and the ending point of the current vehicle in the first set of target vehicles are on the same import lane, determine the heading of the current vehicle according to the function of the import lane.

[0050] If the starting point of the current vehicle is on the import lane and the ending point is on the export lane, determine the heading of the current vehicle according to the heading angles corresponding to the starting point and the ending point of the current vehicle.

[0051] Determine the headings of the vehicles in the second set of target vehicles according to the heading angles corresponding to the starting points and ending points of each vehicle in the second set of target vehicles.

[0052] Specifically, each vehicle in the first set of target vehicles is a vehicle that does not cross the stop line on the lane at the intersection. Each vehicle in the second set of target vehicles here includes, but is not limited to, vehicles that cross the stop line at the intersection, such as vehicles waiting to turn left or vehicles in the center of the intersection.

[0053] In the embodiments of the present invention, for example, when the starting point and the ending point are on the same import lane, then it is necessary to judge the heading of the vehicle according to the lane function. For example, if the function of the lane is straight, dedicated right, or dedicated left, then its heading is east to west, east to north, east to south, etc.

[0054] Suppose the starting point of the vehicle is on the import lane and the ending point is on the export lane. As shown in Table 2, judge the heading of the current vehicle according to the heading angles of the starting point and the ending point of the vehicle.

[0055] Suppose at least one of the starting point and the ending point of the trajectory is not on the lane, then judge its heading according to the heading angles of the starting point and the ending point of the vehicle trajectory, as shown in Table 2.

[0056] In one or more embodiments, the determining whether a traffic conflict occurs between the first vehicle and the second vehicle by using a preset conflict recognition model includes:

[0057] Determine a third set of target vehicles in the common area; wherein, the common area is a rectangular area enclosed by the intersection stop line of the intersection and its extension line.

[0058] Specifically, for example, as Figure 9 shown, the vehicles in the rectangular area are the above-mentioned third set of target vehicles.

[0059] According to the preset corresponding relationship table between headings and conflict types, determine the set of heading pairs that meet the preset traffic conflict rules in the third target vehicle set at preset time intervals, and determine the two vehicles corresponding to each heading pair in the set of heading pairs.

[0060] Specifically, in the embodiment of the present invention, as shown in Table 3, Table 3 is the preset corresponding relationship table between headings and conflict types. Select all the headings and the vehicles they contain in the third target vehicle set that may have traffic conflicts at preset time intervals. It can be selected second by second. All the vehicles in two headings that may have conflicts (such as east to west and south to west) are used as the two vehicles corresponding to a navigation pair.

[0061] Based on the preset TTC algorithm, determine the TTC set corresponding to each heading pair in the set of heading pairs. The TTC set includes the TTC values between the two vehicles at multiple collision angles.

[0062] Select the minimum value of the TTC values of the current two vehicles at multiple collision angles as the final value of the TTC of the current two vehicles; when the final value of the TTC of the current two vehicles is less than or equal to the preset threshold, determine that the current two vehicles have a traffic conflict.

[0063] Specifically, for example, for the two vehicles of a heading pair, such as the heading pair of north to east and east to west. There are 3 vehicles, A, B, and C, going north to east, and 2 vehicles, E and F, going east to west. The two vehicles included in this heading pair are: AE, AF, BE, BF, CE, and CF. Each vehicle includes 4 vertices and 4 edges. Here, in turn, 1 vertex of one vehicle is respectively calculated with the 4 edges of the other vehicle through the TTC algorithm to obtain 8 TTC values. Assume that AE is the current two vehicles being calculated. Select the minimum TTC value at multiple collision angles as the predicted value of the current vehicle AE. When the predicted value is less than or equal to the preset threshold, determine that the current two vehicles AE have a traffic conflict. The preset threshold usually takes an empirical value of 1.5 seconds.

[0064] In one or more embodiments, the determining the TTC set corresponding to each heading pair based on the preset TTC algorithm includes:

[0065] Respectively obtain the moving coordinate information of the two vehicles corresponding to the current heading pair in the two-dimensional coordinate system constructed in the horizontal plane; wherein, the moving coordinate information includes the coordinate information from the starting point to the ending point of the vehicle trajectory data.

[0066] Based on the speeds and vertex coordinate information of the two vehicles, calculate in turn the time taken for the vertex closest to one vehicle from the starting point to the ending point of the driving trajectories of the two vehicles to coincide with one edge of the other vehicle.

[0067] Use the said duration as the TTC value of the corresponding two vehicles at this collision angle with the current heading, and determine the multiple TTC values of the two vehicles obtained as the TTC set of the two vehicles.

[0068] In the embodiments of the present invention, as Figure 5 shown, calculate in sequence the duration when one vertex of one of the two vehicles corresponding to the current heading coincides with the four sides of the other vehicle, and determine it as the TTC set of the two vehicles according to the above multiple durations.

[0069] In one or more embodiments, the separately obtaining the moving coordinate information of the two vehicles corresponding to the current heading in the two-dimensional coordinate system constructed in the horizontal plane, and calculating the duration when the vertex of one vehicle closest to the other vehicle on the driving trajectories of the two vehicles from the starting point to the ending point coincides with one side of the other vehicle, and using the duration as the TTC value of the two vehicles corresponding to the current heading at this collision angle, includes:

[0070] As Figure 5 shown, obtain the moving coordinate information of one side P1P2 of one of the two vehicles corresponding to the current heading, and the coordinate information of a point P0 closest to P1P2 of the other vehicle;

[0071] Determine the coordinate information of P0, P1, and P2 after moving when the two vehicles collide after t time according to formula (1):

[0072]

[0073] wherein, the coordinate of P0 is (x0, y0), the coordinate of P1 is (x1, y1), the coordinate of P2 is (x2, y2), the speed of the vehicle where P0 is located is v, the speed of the vehicle where P1P2 is located is u, v x and v y are respectively the components of the speed v on the x and y axes, u x and u y are respectively the components of the speed u on the x and y axes, after t time, P0, P1, and P2 move to P′0, P′1, and P′2 respectively, and their coordinates are (x′0, y′0), (x′1, y′1), and (x′2, y′2) respectively;

[0074] When P′0, P′1, and P′2 are collinear, determine that the two vehicles collide, and determine the slope k of the line segment where P′0, P′1, and P′2 are collinear based on formula (2):

[0075]

[0076] Substitute formula (1) into formula (2) to obtain formula (4),

[0077]

[0078] By resolving formula (4), formula (3) can be obtained, and based on formula (3), the TTC value of the two vehicles corresponding to the current heading at this collision angle is determined;

[0079]

[0080] Among them, the t value in formulas (1) and (2) is the TTC value in formula (3).

[0081] In one or more embodiments, the determining the TTC set of the two vehicles corresponding to each heading pair based on a preset TTC algorithm further includes:

[0082] Respectively obtain the moving coordinate information of the two vehicles corresponding to the current heading pair in the two-dimensional coordinate system constructed in the horizontal plane; among them, the moving coordinate information includes the coordinate information from the starting point to the ending point of the vehicle trajectory data;

[0083] Based on the speeds of the two vehicles and the moving coordinate information of the vertices, sequentially calculate the area of the triangle formed by the vertex closest to one vehicle to the other vehicle and one side of the other vehicle in the driving trajectories of the two vehicles from the starting point to the ending point;

[0084] When the vertex closest to one vehicle to the other vehicle and one side of the other vehicle satisfy a preset coordinate size relationship, determine the duration between the starting moment of the two vehicles and the moment when the area of the triangle becomes zero;

[0085] Take the duration as the TTC value of the two vehicles corresponding to the current heading pair at this collision angle, and determine the multiple TTC values of the two vehicles obtained as the TTC set of the two vehicles.

[0086] Specifically, for example, as Figure 6 shown, the TTC value is obtained by the following method. When the two vehicles approach, the area of ΔP0P1P2 enclosed by P0, P1, and P2 gradually shrinks. The area of ΔP′0P′1P′2 can be represented by the difference between the right trapezoid MNP′2P′0, the right triangle MP′1P′0, and the right triangle NP′1P′2.

[0087]

[0088] The result of formula (5) can be expressed by a determinant as:

[0089]

[0090] Since the value of the determinant may be negative, an absolute value is added outside the determinant, as shown in formula (7).

[0091]

[0092] Formula (7) can be transformed into Formula (8).

[0093]

[0094] If vehicle 1 and vehicle 2 collide at a certain time, then the area of ΔP′0P′1P′2 is 0, that is

[0095]

[0096] In practice, there will be situations as Figure 7 shown, that is, when the area of ΔP′0P′1P′2 is 0, the two vehicles do not collide. Therefore, it is necessary to constrain the position of point P′0, and the constraint condition is as shown in Formula (10).

[0097]

[0098] In summary, the collision time t of the two vehicles, that is, the TTC value, can be calculated according to Formulas (8), (9), and (10), as shown in Formula (11). The TTC threshold is taken as 1.5 s, that is, if t is less than or equal to 1.5 s, then it is considered that the two vehicles have a traffic conflict.

[0099]

[0100] In one or more embodiments, determining the conflict type of traffic conflict between the first vehicle and the second vehicle includes: determining the conflict type of traffic conflict between the first vehicle and the second vehicle based on the headings of the first vehicle and the second vehicle. Specifically, as shown in Table 3, determine the conflict type of traffic conflict between the first vehicle and the second vehicle based on the headings of the two vehicles.

[0101] Table 3

[0102]

[0103] Table 3 (continued)

[0104]

[0105] In one or more embodiments, the above traffic conflict recognition method further includes:

[0106] Obtaining traffic conflict data of the intersection during a historical time period; determining the frequently occurring target conflict types of the intersection and the corresponding target heading pairs and the number of traffic conflicts occurring for the target heading pairs according to the traffic conflict data.

[0107] Specifically, for example, traffic conflict data at a level crossing within the past day with the current time as the node is obtained, and based on the traffic conflict data, the target conflict type, the target heading pair, and the number of traffic conflicts occurring for the target heading pair are determined. Here, the target conflict type includes the conflict types with a relatively large number of traffic conflicts, the target heading pair is the navigation pair with a relatively large number of traffic conflicts, and the number of traffic conflicts occurring for this heading pair, so as to determine which vehicle headings or lanes at this intersection are more likely to have traffic conflicts. As shown in Table 4. The diverging conflicts mainly come from three parts, namely the straight-right lane at the east approach (vehicles traveling from east to north and vehicles traveling from east to west), the straight-right lane at the west approach (vehicles traveling from west to north and vehicles traveling from west to east), and the straight-left lane at the east approach (vehicles traveling from east to south and vehicles traveling from east to west); the merging conflicts mainly come from the north exit; among them, the number of traffic conflicts between vehicles traveling from west to north and vehicles traveling from east to north is the largest. Figure 9 , Figure 10 , Figure 11 , Figure 12 They are respectively the spatial distributions of all traffic conflicts, merging conflicts, diverging conflicts, and crossing conflicts. The closer to red, the more conflicts occur at that location; the closer to blue, the fewer conflicts occur at that location. As can be seen from Figure 9 , although the frequency of traffic conflicts at this level crossing is relatively high at individual locations, the overall distribution is uniform. As can be seen from Figure 10 , the number of merging conflicts is relatively small, and they are mainly distributed on the east side of the public area. As can be seen from Figure 11 , the number of diverging conflicts is relatively large, and they are mainly evenly distributed on the north and south sides of the public area. As can be seen from Figure 12 , the number of crossing conflicts is also relatively large, and they are mainly concentrated on the north side of the public area.

[0108] In one embodiment, as Figure 13 shown, Figure 13 is a curve graph of traffic conflicts occurring at a level crossing in a target city; among them, the vertical coordinate is the average value of the number of each conflict type occurring within a week, the horizontal coordinate is the time period, and the division unit is hours. In each time period, the diverging conflicts are the most and the crossing conflicts are the least at this level crossing as a whole.

[0109] Table 4

[0110]

[0111] Based on the above embodiment, as Figure 4 shown, in an application embodiment, the above traffic conflict recognition method further includes the following steps:

[0112] Step A: Based on the data fusion of the videos and radars at the intersection, vehicle trajectory data is obtained. By analyzing the vehicle trajectory data, the lane division and public area data of each lane at the intersection are obtained. The lane function data of each lane can also be obtained through on-site investigation of urban road intersections, such as the original data layer shown in Table 1 above. Subsequently, enter Step B.

[0113] Step B: Take the lane division data and lane function data as the basic data of the intersection. The speed, heading angle, and heading of the vehicle are derived from the trajectory data and the basic data of the intersection, such as the derived data layer shown in Table 1 above. Subsequently, enter Step C.

[0114] Step C: Use TTC as a measure of traffic conflict, and take the headings of two vehicles as the basis for judging the type of traffic conflict. Use the conflict recognition model to identify different types of traffic conflicts occurring in the public area of the intersection. Subsequently, enter Step D.

[0115] Step D: Statistically analyze the spatio-temporal laws of different types of traffic conflicts occurring at urban road intersections.

[0116] Furthermore, in Step A, the public area refers to the area enclosed by the stop line at the intersection and its extension line, as Figure 9 shown in the rectangular area.

[0117] The headings of the two vehicles in a traffic conflict are the basis for judging the type of traffic conflict (diverging conflict, merging conflict, crossing conflict), or the cause of the conflict. Due to the influence of the vehicle driving speed, the number of vehicle trajectory points collected varies, and the starting and ending points of the trajectory may not be distributed on the approach lane and the departure lane. Therefore, it is difficult to accurately judge the heading of the vehicle only by using the heading angle of the trajectory points or the position of the starting and ending points of the trajectory.

[0118] In summary, the embodiment of the present invention determines the heading of the vehicle by using the heading angle, position of the trajectory data and the basic data of the intersection, including the following steps:

[0119] Step 1: If both the starting point and the ending point of the trajectory are on the lane, then,

[0120] (1) When the starting point and the ending point are on the same approach lane, it is necessary to judge the heading of the vehicle according to the lane function. For example, if the function of the lane is straight, exclusive right, exclusive left, then its heading is east to west, east to north, east to south, etc.

[0121] (2) When the starting point is on the approach lane and the ending point is on the departure lane, judge its heading according to the heading angles of the starting point and the ending point of the vehicle, as shown in Table 2.

[0122] Step 2: If at least one of the starting point and the ending point of the trajectory is not on the lane, then judge its heading according to the heading angles of the starting point and the ending point of the vehicle's trajectory, as shown in Table 2.

[0123] Further, in the above step C, using TTC as a metric for traffic conflicts specifically includes: assuming that a vertex P0 of vehicle 1 is approaching an edge P1P2 of vehicle 2. The coordinates of P0, P1, and P2 are (x0, y0), (x1, y1), and (x2, y2) respectively, the speed of vehicle 1 is v, and the speed of vehicle 2 is u. Assuming that after time t, P0, P1, and P2 move to P′0, P′1, and P′2 respectively, and their coordinates are (x′0, y′0), (x′1, y′1), and (x′2, y′2) respectively, as shown in formula (1).

[0124]

[0125] Among them, v x , v y are the components of the speed v on the x-axis and y-axis respectively, and u x , u y are the components of the speed u on the x-axis and y-axis respectively.

[0126] In one embodiment, the TTC value is obtained by the following method (Method 1). Assuming that the two vehicles collide after time t, that is, the vertex P0 collides with the edge P1P2. At this time, P′0, P′1, and P′2 are collinear, as Figure 5 shown, and the slope of this line can be expressed as:

[0127]

[0128] Substituting formula (1) into formula (2), formula (3) can be obtained:

[0129]

[0130] By simplifying formula (3), the time t when the two vehicles collide can be calculated, that is, their TTC value:

[0131]

[0132] In another embodiment, the TTC value is obtained by the following method (Method 2). When the two vehicles approach, the area of ΔP0P1P2 enclosed by P0, P1, and P2 gradually decreases. As Figure 6 shown. The area of ΔP′0P′1P′2 can be expressed as the difference between the right trapezoid MNP′2P′0, the right triangle MP′1P′0, and the right triangle NP′1P′2.

[0133]

[0134] The result of formula (5) can be expressed as a determinant as follows:

[0135]

[0136] Since the value of the determinant may be negative, an absolute value is added outside the determinant, as shown in formula (7).

[0137]

[0138] Formula (7) can be transformed into formula (8)

[0139]

[0140] If vehicle 1 and vehicle 2 collide at time t, then the area of ΔP′0P′1P′2 is 0, that is

[0141]

[0142] In practice, there will be situations as Figure 7 shown, that is, when the area of ΔP′0P′1P′2 is 0, the two vehicles do not collide. Therefore, it is necessary to constrain the position of point P′0, and the constraint conditions are shown in formula (10).

[0143]

[0144] In summary, the collision time t of the two vehicles, that is, the TTC value, can be calculated according to formulas (8), (9), and (10), as shown in formula (11). The TTC threshold is taken as 1.5 s, that is, if t is less than or equal to 1.5 s, it is considered that the two vehicles have a traffic conflict.

[0145]

[0146] Furthermore, in step C, traffic conflicts at signalized intersections can be classified according to their causes into: merging conflicts, diverging conflicts, and crossing conflicts. The present invention uses the headings of the two vehicles as the basis for judging the type of traffic conflict, and the judgment basis is shown in Table 3 above.

[0147] Furthermore, in step C, the conflict recognition framework refers to the general process proposed by the present invention for identifying different types of traffic conflicts occurring at signalized intersections, as Figure 8 shown, and the specific steps are as follows:

[0148] Step 1, filtering, select the vehicles in the common area second by second, and filter out the vehicles outside the common area.

[0149] Step 2: Selection. Select all possible headings where traffic conflicts may occur at this moment and the vehicles they contain. All vehicles in two headings where conflicts may occur (such as east to west and south to west) are taken as a calculation unit (the above-mentioned navigation pair).

[0150] Step 3: Calculation. For each calculation unit, directly calculate the TTC values at each collision angle using the above Method 1; or, using Method 2, first determine whether the positions of any two vehicles with different headings satisfy the constraint conditions of the above formula (10). If they do, then calculate the TTC values at each collision angle between them, and select the minimum value as the final TTC value of the two vehicles.

[0151] Step 4: Output Results. According to the TTC threshold, output the time, location, and type of the conflict point.

[0152] Figure 9 、 Figure 10 、 Figure 11 、 Figure 12 They are respectively the spatial distributions of all traffic conflicts, merging conflicts, diverging conflicts, and crossing conflicts. The closer to red, the more conflict times occur at that position; the closer to blue, the fewer conflict times occur at that position. It can be seen from Figure 9 that although the traffic conflicts at this intersection occur more frequently at individual positions, they are overall evenly distributed. It can be seen from Figure 10 that the number of merging conflicts is relatively small, mainly distributed on the east side of the public area. It can be seen from Figure 11 that the number of diverging conflicts is relatively large, mainly evenly distributed on the north and south sides of the public area. It can be seen from Figure 12 that the number of crossing conflicts is also relatively large, mainly concentrated on the north side of the public area.

[0153] According to the headings of the two vehicles where traffic conflicts occur, explore Figure 9 which two headings of vehicles are prone to traffic conflicts, or which two lanes of vehicles are prone to traffic conflicts. The results are shown in Table 4 above. Diverging conflicts mainly come from three parts, namely the straight - right lane at the east entrance (vehicles traveling north from the east and vehicles traveling west from the east), the straight - right lane at the west entrance (vehicles traveling north from the west and vehicles traveling east from the west), and the straight - left lane at the east entrance (vehicles traveling south from the east and vehicles traveling west from the east). Crossing conflicts mainly come from three parts, namely left - turn at the west entrance and straight - through at the east entrance (vehicles traveling north from the west and vehicles traveling west from the east), left - turn at the east entrance and straight - through at the west entrance (vehicles traveling south from the east and vehicles traveling east from the west), and left - turn at the north entrance and straight - through at the east entrance (vehicles traveling east from the north and vehicles traveling west from the east). Merging conflicts mainly come from the north exit. Among them, the number of traffic conflicts between vehicles traveling north from the west and vehicles traveling north from the east is the largest.

[0154] The time pattern of traffic conflicts occurring at this level crossing is as Figure 13 shown. The vertical coordinate in the figure is the average value of the number of each conflict type occurring within a week, and the horizontal coordinate is the time period, with the division unit being hours. In each time period, this level crossing generally shows the most split conflicts and the fewest crossing conflicts.

[0155] The embodiment of the present invention can efficiently identify the location and type of traffic conflicts occurring at a level crossing, thereby determining the operation efficiency and safety of this intersection and providing assistance for managing urban road congestion.

[0156] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0157] According to another aspect of the embodiment of the present invention, there is also provided a traffic conflict recognition device for implementing the above traffic conflict recognition method. As Figure 14 shown, the device includes:

[0158] A first acquisition unit 1402, which acquires the vehicle trajectory data of the level crossing in the target city within a preset time period, as well as the road basic data of the level crossing;

[0159] A first determination unit 1404, which is used to determine the speed, heading angle, and heading of each vehicle according to the vehicle trajectory data and the road basic data; wherein, the heading angle is the included angle between the front direction of the vehicle and a preset direction;

[0160] A second determination unit 1406, which is used to determine whether a traffic conflict occurs between the first vehicle and the second vehicle based on the headings of the first vehicle and the second vehicle by using a preset conflict recognition model; wherein, the conflict recognition model is a recognition model for judging whether two vehicles collide according to the time to collision (TTC) value of the two vehicles;

[0161] A third determination unit 1408, which is used to determine the time, location, and conflict type of the traffic conflict occurring between the first vehicle and the second vehicle.

[0162] In an embodiment of the present invention, vehicle trajectory data of a level crossing in a target city within a preset time period and road basic data of the level crossing are acquired; the speed, heading angle, and heading of each vehicle are determined according to the vehicle trajectory data and the road basic data; wherein, the heading angle is the angle between the front direction of the vehicle and a preset direction; based on the headings of a first vehicle and a second vehicle, a preset conflict recognition model is used to determine whether a traffic conflict occurs between the first vehicle and the second vehicle; wherein, the conflict recognition model is a recognition model for judging whether the two vehicles collide according to the time to collision (TTC) value of the two vehicles; if so, a method for determining the time, location, and conflict type of the traffic conflict between the first vehicle and the second vehicle. In the above method, since it is determined whether a traffic conflict occurs between the first vehicle and the second vehicle based on the headings of the first vehicle and the second vehicle and the time to collision (TTC), and by using a preset conflict recognition model, traffic conflicts at urban traffic intersections can be effectively identified, which helps to manage urban road congestion, and thus solves the technical problem in the related art that traffic conflict recognition between vehicles at lane-level urban intersections cannot be performed.

[0163] In one or more embodiments, the first determination unit 1404 includes:

[0164] A first determination module, configured to determine a first set of target vehicles whose starting points and ending points are both on the lane in the vehicle trajectory data, and determine a second set of target vehicles other than the first set of target vehicles in the vehicle trajectory data;

[0165] A first judgment module, configured to determine the heading of the current vehicle according to the function of the import lane if the starting point and the ending point of the current vehicle are in the same import lane;

[0166] A second judgment module, configured to determine the heading of the current vehicle according to the heading angles corresponding to the starting point and the ending point of the current vehicle if the starting point of the current vehicle is in the import lane and the ending point is in the export lane;

[0167] A third determination module, configured to determine the heading of each vehicle according to the heading angles corresponding to the starting point and the ending point of each vehicle in the second set of target vehicles;

[0168] In one or more embodiments, the second determination unit 1406 includes:

[0169] A fourth determination module, configured to determine a third set of target vehicles in a common area; wherein, the common area is a rectangular area surrounded by the stop line of the level crossing and its extension line;

[0170] The fifth determination module is configured to determine, according to a preset correspondence table between headings and conflict types, a set of heading pairs that meet the preset traffic conflict rules in the third target vehicle set at a preset time interval, and determine the two vehicles corresponding to each heading pair in the set of heading pairs;

[0171] The sixth determination module is configured to determine, based on a preset TTC algorithm, a TTC set corresponding to each heading pair in the set of heading pairs, where the TTC set includes TTC values between the two vehicles at multiple collision angles;

[0172] The seventh determination module is configured to select the minimum value of the TTC values of the current two vehicles at multiple collision angles as the final value of the TTC of the current two vehicles; in the case where the final value of the TTC of the current two vehicles is less than or equal to a preset threshold, determine that the current two vehicles have a traffic conflict.

[0173] In one or more embodiments, the sixth determination module includes:

[0174] The first acquisition subunit is configured to respectively acquire the moving coordinate information of the two vehicles corresponding to the current heading pair in a two-dimensional coordinate system constructed in the horizontal plane; wherein, the moving coordinate information includes the coordinate information from the starting point to the ending point of the vehicle trajectory data;

[0175] The first calculation subunit is configured to, based on the speeds and vertex coordinate information of the two vehicles, sequentially calculate the duration from the starting point to the ending point of the driving trajectories of the two vehicles when the vertex closest to one vehicle from the other vehicle coincides with one side of the other vehicle;

[0176] The first determination subunit is configured to use the duration as the TTC value of the two vehicles corresponding to the current heading pair at this collision angle, and determine the multiple TTC values of the two vehicles obtained as the TTC set of the two vehicles.

[0177] In one or more embodiments, the sixth determination module further includes:

[0178] The second acquisition subunit is configured to acquire the moving coordinate information of one side P1P2 of one of the two vehicles corresponding to the current heading pair, and the coordinate information of a point P0 closest to P1P2 of the other vehicle;

[0179] The first calculation subunit determines the coordinate information after the movement of P0, P1, and P2 when the two vehicles collide after t time according to formula (1):

[0180]

[0181] Among them, the coordinates of P0 are (x0, y0), the coordinates of P1 are (x1, y1), the coordinates of P2 are (x2, y2), the speed of the vehicle where P0 is located is v, the speed of the vehicle where P1P2 is located is u, v x and v y are the components of the speed v on the x and y axes respectively, and u x and u y are the components of the speed u on the x and y axes respectively. After t time, P0, P1, and P2 move to P′0, P′1, and P′2 respectively, and their coordinates are (x′0, y′0), (x′1, y′1), and (x′2, y′2);

[0182] When the three points P′0, P′1, and P′2 are collinear, it is determined that the two vehicles collide, and the slope k of the line segment where the three points P′0, P′1, and P′2 are collinear is determined based on formula (2):

[0183]

[0184] Substitute formula (1) into formula (2) to obtain formula (3), and determine the TTC value of the corresponding two vehicles at the collision angle based on the formula (3);

[0185]

[0186] Among them, the t value in formulas (1) and (2) is the TTC value in formula (3).

[0187] In one or more embodiments, the sixth determination module further includes:

[0188] A second acquisition subunit, configured to respectively acquire the moving coordinate information of the corresponding two vehicles in the two-dimensional coordinate system constructed in the horizontal plane; wherein, the moving coordinate information includes the coordinate information from the starting point to the ending point of the vehicle trajectory data;

[0189] A second calculation subunit, configured to calculate, based on the speeds of the two vehicles and the moving coordinate information of the vertices, the area of the triangle formed by the vertex closest to one vehicle in the driving trajectories of the two vehicles from the starting point to the ending point and one side of the other vehicle in sequence;

[0190] A second determination subunit, configured to determine the duration between the starting moment of the two vehicles and the moment when the area of the triangle becomes zero when the vertex closest to one vehicle in the two vehicles and one side of the other vehicle satisfy a preset coordinate size relationship;

[0191] A third determination subunit, configured to use the duration as the current heading of the corresponding two vehicles at the collision angle for the TTC value, and determine the multiple TTC values of the two vehicles as the TTC set of the two vehicles.

[0192] In one or more embodiments, the third determination unit 1408 includes:

[0193] An eighth determination module, configured to determine a conflict type of a traffic conflict between the first vehicle and the second vehicle based on the headings of the first vehicle and the second vehicle.

[0194] In one or more embodiments, the traffic conflict recognition device further includes:

[0195] A second acquisition unit, configured to acquire traffic conflict data of the intersection during a historical time period;

[0196] A fourth determination unit, configured to determine a frequently-occurring conflict type of the intersection, a corresponding target heading pair, and the number of traffic conflicts occurring for the target heading pair according to the traffic conflict data.

[0197] According to another aspect of the embodiments of the present application, there is also provided an electronic device for implementing the above traffic conflict recognition method. The electronic device may be Figure 1 the terminal device or server shown in the figure. This embodiment takes the electronic device as a server as an example for illustration. As Figure 14 shown in the figure, the electronic device includes a memory 1402 and a processor 1404. A computer program is stored in the memory 1402, and the processor 1404 is configured to execute the steps in any of the above method embodiments through the computer program.

[0198] Optionally, in this embodiment, the above electronic device may be at least one network device among multiple network devices of a computer network.

[0199] Optionally, in this embodiment, the above processor may be configured to execute the following steps through the computer program:

[0200] S1, acquire vehicle trajectory data of an intersection of a target city within a preset time period, and road basic data of the intersection;

[0201] S2, determine the speed, heading angle, and heading of each vehicle according to the vehicle trajectory data and the road basic data; where the heading angle is an angle between the head direction of the vehicle and a preset direction;

[0202] S3. Determine whether a traffic conflict occurs between the first vehicle and the second vehicle by using a preset conflict recognition model based on the headings of the first vehicle and the second vehicle; wherein, the conflict recognition model is a recognition model for judging whether the two vehicles collide according to the time to collision (TTC) value of the two vehicles, and the first vehicle and the second vehicle are different vehicles in the vehicle trajectory data.

[0203] S4. If so, determine the time, location and conflict type of the traffic conflict between the first vehicle and the second vehicle.

[0204] Optionally, those of ordinary skill in the art can understand that Figure 15 the structure shown is only schematic, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, and a mobile Internet device (MID), a PAD and other terminal devices. Figure 15 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device may further include Figure 15 more or fewer components (such as a network interface, etc.) than those shown, or have a different configuration from Figure 15 that shown.

[0205] Among them, the memory 1502 can be used to store software programs and modules, such as the program instructions / modules corresponding to the traffic conflict recognition method and device in the embodiments of the present application. The processor 1504 executes various functional applications and data processing by running the software programs and modules stored in the memory 1502, that is, implements the above-mentioned traffic conflict recognition method. The memory 1502 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, a flash memory, or other non-volatile solid-state memories. In some instances, the memory 1502 may further include a memory remotely provided with respect to the processor 1504, and these remote memories can be connected to the terminal through a network. Examples of the above network include but are not limited to the Internet, an enterprise internal network, a local area network, a mobile communication network and their combinations. Among them, the memory 1502 may specifically but not limitedly include information such as the time, location and conflict type of the traffic conflict. As an example, as Figure 15 shown, the above-mentioned memory 1502 may but not limitedly include the first acquisition unit 1402, the first determination unit 1404, the second determination unit 1406 and the third determination unit 1410 in the above-mentioned traffic conflict recognition device. In addition, it may also include but not limited to other module units in the above-mentioned traffic conflict recognition device, which will not be elaborated in this example.

[0206] Optionally, the above-mentioned transmission device 1506 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 1506 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers through a network cable, so as to communicate with the Internet or a local area network. In one example, the transmission device 1506 is a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0207] In addition, the above-mentioned electronic device further includes: a display 1508, which is used to display the time, location, and conflict type of traffic conflicts; and a connection bus 1510, which is used to connect each module component in the above-mentioned electronic device.

[0208] In other embodiments, the above-mentioned terminal device or server can be a node in a distributed system. Among them, the distributed system can be a blockchain system, and the blockchain system can be a distributed system formed by connecting the multiple nodes in the form of network communication. Among them, the nodes can form a Peer-to-Peer (P2P) network, and any form of computing device, such as electronic devices like servers and terminals, can become a node in the blockchain system by joining the peer-to-peer network.

[0209] In one or more embodiments, the present application further provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-mentioned traffic conflict recognition method. Among them, the computer program is set to execute the steps in any one of the above-mentioned method embodiments when running.

[0210] Optionally, in this embodiment, the above-mentioned computer-readable storage medium can be set to store a computer program for executing the following steps:

[0211] S1. Obtain the vehicle trajectory data of the level crossings in the target city within a preset time period, and the road basic data of the level crossings;

[0212] S2. Determine the speed, heading angle, and heading of each vehicle according to the vehicle trajectory data and the road basic data; where the heading angle is the included angle between the head direction of the vehicle and a preset direction;

[0213] S3. Determine whether a traffic conflict occurs between the first vehicle and the second vehicle by using a preset conflict recognition model based on the headings of the first vehicle and the second vehicle; wherein, the conflict recognition model is a recognition model for judging whether the two vehicles collide according to the time to collision (TTC) value of the two vehicles, and the first vehicle and the second vehicle are different vehicles in the vehicle trajectory data.

[0214] S4. If so, determine the time, location and conflict type of the traffic conflict that occurs between the first vehicle and the second vehicle.

[0215] Optionally, in this embodiment, those of ordinary skill in the art can understand that all or part of the steps in the above-mentioned various methods of the embodiment can be completed by instructing the relevant hardware of the terminal device through a program, and this program can be stored in a computer-readable storage medium. The storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disc, etc.

[0216] The serial numbers of the above-mentioned embodiments of the present invention are only for description and do not represent the superiority or inferiority of the embodiments.

[0217] If the integrated unit in the above-mentioned embodiment is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in the above-mentioned computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing one or more computer devices (which may be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention.

[0218] In the above-mentioned embodiments of the present invention, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0219] In several embodiments provided by the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, and the indirect coupling or communication connection of units or modules may be in an electrical or other form.

[0220] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0221] In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0222] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A traffic conflict recognition method, characterized in that, Including: Obtaining the vehicle trajectory data of the level crossings in the target city within a preset time period, and the road basic data of the level crossings; Determining the speed, heading angle and heading of each vehicle according to the vehicle trajectory data and the road basic data; wherein, the heading angle is the angle between the front direction of the vehicle and a preset direction; Based on the headings of the first vehicle and the second vehicle, using a preset conflict recognition model to determine whether the first vehicle and the second vehicle have a traffic conflict; wherein, the conflict recognition model is a recognition model for judging whether the two vehicles collide according to the time to collision (TTC) value of the two vehicles, and the first vehicle and the second vehicle are two vehicles corresponding to a heading pair that satisfies the preset traffic conflict rule determined according to a preset correspondence table between heading and conflict type, and the vehicle trajectories of which are in a common area; wherein, the common area is a rectangular area enclosed by the stop line of the level crossing and its extension line; If so, determining the time, location and conflict type of the traffic conflict between the first vehicle and the second vehicle; Determining the conflict type of the traffic conflict between the first vehicle and the second vehicle includes: Based on the headings of the first vehicle and the second vehicle, determining the conflict type of the traffic conflict between the first vehicle and the second vehicle; Obtaining the traffic conflict data of the level crossing within a historical time period; According to the traffic conflict data, determining the frequently occurring conflict types at the level crossing, the corresponding target heading pairs thereof, and the number of traffic conflicts occurring for the target heading pairs.

2. The method according to claim 1, characterized in that, Determining the heading of each vehicle according to the vehicle trajectory data and the road basic data includes: Determining a first set of target vehicles in the vehicle trajectory data whose starting point and ending point are both on the lane, and determining a second set of target vehicles in the vehicle trajectory data other than the first set of target vehicles; If the starting point and the ending point of the current vehicle in the first set of target vehicles are on the same import lane, determining the heading of the current vehicle according to the function of the import lane; If the starting point of the current vehicle is on the import lane and the ending point is on the export lane, determining the heading of the current vehicle according to the heading angles corresponding to the starting point and the ending point of the current vehicle; According to the heading angles corresponding to the starting point and the ending point of each vehicle in the second set of target vehicles, determining the headings of the vehicles in the second set of target vehicles.

3. The method according to claim 1, characterized in that, The using a preset conflict recognition model to determine whether the first vehicle and the second vehicle have a traffic conflict includes: Determining a third set of target vehicles whose vehicle trajectories are in the common area; According to a preset correspondence table between heading and conflict type, determining a set of heading pairs that satisfy the preset traffic conflict rule in the third set of target vehicles at preset time intervals, and determining the two vehicles corresponding to each heading pair in the set of heading pairs; Based on a preset TTC algorithm, determining a TTC set of the two vehicles corresponding to each heading pair in the set of heading pairs, and the TTC set includes the TTC values of the two vehicles at multiple collision angles; Select the minimum value of the TTC values of the current two vehicles at multiple collision angles as the final value of the TTC of the current two vehicles; when the final value of the TTC of the current two vehicles is less than or equal to a preset threshold, determine that a traffic conflict occurs between the current two vehicles.

4. The method according to claim 3, wherein Based on the preset TTC algorithm, determining the TTC set of the two vehicles corresponding to each heading pair includes: Respectively obtain the moving coordinate information of the two vehicles corresponding to the current heading pair in the two-dimensional coordinate system constructed in the horizontal plane; wherein, the moving coordinate information includes the coordinate information from the starting point to the ending point of the vehicle trajectory data. Based on the speeds and vertex coordinate information of the two vehicles, sequentially calculate the duration when the vertex of one vehicle closest to the other vehicle in the driving trajectories of the two vehicles from the starting point to the ending point coincides with one side of the other vehicle. Take the duration as the TTC value of the two vehicles corresponding to the current heading pair at this collision angle, and determine the multiple TTC values of the two vehicles obtained as the TTC set of the two vehicles.

5. The method according to claim 4, characterized in that, The step of respectively obtaining the moving coordinate information of the two vehicles corresponding to the current heading pair in the two-dimensional coordinate system constructed in the horizontal plane, calculating the duration when the vertex of one vehicle closest to the other vehicle in the driving trajectories of the two vehicles from the starting point to the ending point coincides with one side of the other vehicle, and taking the duration as the TTC value of the two vehicles corresponding to the current heading pair at this collision angle includes: Obtain the moving coordinate information of one side P1P2 of one of the two vehicles corresponding to the current heading pair, and the coordinate information of a point P0 closest to P1P2 of the other vehicle. Determine the coordinates of P0, P1, and P2 after moving when the two vehicles collide after t time according to formula (1): Among them, the coordinates of P0 are (x0, y0), the coordinates of P1 are (x1, y1), the coordinates of P2 are (x2, y2), the speed of the vehicle where P0 is located is v, the speed of the vehicle where P1P2 is located is u, v x and v y are the components of the speed v on the x and y axes respectively, and u x and u y are the components of the speed u on the x and y axes respectively. After time t, P0, P1, and P2 move to P0′, P1′, and P2′ respectively, and their coordinates are (x′0, y′0), (x1′, y1′), and (x′2, y′2); When the three points P0′, P1′, and P2′ are collinear, determine that the two vehicles collide, and determine the slope k of the line segment where the three points P0′, P1′, and P2′ are collinear based on formula (2): Substitute formula (1) into formula (2) to obtain formula (3), and determine the TTC value of the two vehicles corresponding to the current heading pair at this collision angle based on formula (3); Wherein, the t value in formulas (1) and (2) is the TTC value in formula (3).

6. The method according to claim 3, wherein Based on the preset TTC algorithm, determining the TTC set of the two vehicles corresponding to each heading pair further includes: Respectively obtain the moving coordinate information of the two vehicles corresponding to the current heading pair in the two-dimensional coordinate system constructed in the horizontal plane; wherein, the moving coordinate information includes the coordinate information from the starting point to the ending point of the vehicle trajectory data. Based on the speeds of the two vehicles and the moving coordinate information of the vertices, sequentially calculate the area of the triangle formed by the vertex of one vehicle closest to the other vehicle and one side of the other vehicle in the driving trajectories of the two vehicles from the starting point to the ending point. When the vertex of one vehicle closest to the other vehicle and one side of the other vehicle satisfy a preset coordinate size relationship, determine the duration between the starting moment of the two vehicles and the moment when the area of the triangle becomes zero. Take the duration as the current heading to obtain the TTC values of the corresponding two vehicles at this collision angle, and determine the multiple TTC values of the two vehicles obtained as the TTC set of the two vehicles.

7. A traffic conflict recognition device, characterized in that Including: A first acquisition unit that acquires vehicle trajectory data of a signalized intersection in a target city within a preset time period, and road basic data of the signalized intersection; A first determination unit configured to determine the speed, heading angle, and heading of each vehicle according to the vehicle trajectory data and the road basic data; wherein, the heading angle is the angle between the front direction of the vehicle and a preset direction; A second determination unit configured to determine whether a traffic conflict occurs between the first vehicle and the second vehicle by using a preset conflict recognition model based on the headings of the first vehicle and the second vehicle; wherein, the conflict recognition model is a recognition model for judging whether two vehicles collide according to the time to collision (TTC) values of the two vehicles, and the first vehicle and the second vehicle are two vehicles corresponding to a heading pair that satisfies a preset traffic conflict rule determined according to a preset correspondence table between heading and conflict type, and the vehicle trajectories of which are located in a common area; wherein, the common area is a rectangular area enclosed by the stop line of the signalized intersection and its extension line; A third determination unit configured to determine the time, location, and conflict type of the traffic conflict that occurs between the first vehicle and the second vehicle; The third determination unit includes an eighth determination module; the eighth determination module is configured to determine the conflict type of the traffic conflict that occurs between the first vehicle and the second vehicle based on the headings of the first vehicle and the second vehicle; A second acquisition unit configured to acquire traffic conflict data of the signalized intersection within a historical time period; A fourth determination unit configured to determine the frequently occurring conflict types at the signalized intersection, the corresponding target heading pairs, and the number of traffic conflicts that occur for the target heading pairs according to the traffic conflict data.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when running, executes the method according to any one of claims 1 to 6.

9. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

Images