A target tracking method, device, equipment and medium

Abstract

The present application discloses a target tracking method, device, equipment and medium for realizing continuous tracking of the target movement process of the entire target road section. The method comprises: obtaining target movement information reported by multiple detection points pre-set on the target road section; the target movement information reported by each detection point is the target movement information obtained by identifying and detecting the tracking target through the detection equipment of the detection point; for each detection point: based on the target movement information reported by the detection point, at least one detection target located in the identification area of ​​the detection point is determined, and the movement information of each detection target is determined; based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the identification blind area of ​​the detection point, the movement information of each simulated target is determined; based on the movement information of the detection targets of multiple detection points and the movement information of the simulated targets, the same target and its movement information are determined.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular to a target tracking method, device, equipment and medium. Background Art

[0002] Frequent traffic jams and traffic accidents in urban areas not only cause trouble to traffic participants, but also become a key concern for traffic management departments. Faced with complex and diverse driving scene changes, how to timely perceive traffic operation status and traffic events, and take control measures in time to ensure the stability of traffic operation has always been a pain point in the transportation industry. Summary of the invention

[0003] The embodiments of the present application provide a target tracking method, apparatus, device and medium for realizing continuous tracking of the target movement process of the entire target section and obtaining full-sample continuous trajectory tracking data of the target.

[0004] An object tracking method provided in an embodiment of the present application includes:

[0005] Obtaining target movement information reported by a plurality of detection points pre-set on the target road section; wherein the target movement information reported by each detection point is the target movement information obtained by identifying and detecting the tracking target through the detection equipment of the detection point;

[0006] For each of the detection points: based on the target movement information reported by the detection point, at least one detection target located in the identification area of ​​the detection point is determined, and the movement information of each of the detection targets is determined; and based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the identification blind area of ​​the detection point, the movement information of each of the simulated targets is further determined;

[0007] Based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulation target, the same target is determined, and the movement information of the same target is determined.

[0008] The target tracking method described in the embodiment of the present application first obtains target movement information reported by multiple detection points pre-set on the target road section; wherein the target movement information reported by each of the detection points is the target movement information obtained by identifying and detecting the tracking target through the detection equipment of the detection point; further, for each of the detection points: based on the target movement information reported by the detection point, at least one detection target located in the identification area of ​​the detection point is determined, and the movement information of each of the detection targets is determined; and based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the identification blind area of ​​the detection point, the movement information of each of the simulated targets is further determined; thereby, the detection targets of the multiple detection points can be used to obtain the target movement information. The target movement information and the simulated target movement information are used to determine the same target and the movement information of the same target. Therefore, the embodiment of the present application can detect the movement information of the target in the identification area of ​​each detection point and simulate the movement information of the target in the identification blind area of ​​the detection point for the target section, thereby realizing the fusion of the target movement trajectory of the entire section of the target section, thereby solving the problem of splicing the target movement trajectory of the entire trunk line of the urban non-closed road, realizing the continuous tracking of the target movement process of the entire trunk line, and obtaining the full-sample continuous trajectory tracking data of the target on the section at the same time, thereby more accurately obtaining the actual position, speed, direction angle, acceleration and other real-time dynamic data of the target at each moment, which greatly facilitates the monitoring of traffic safety and other processing.

[0009] In some embodiments, for each of the detection points: based on the target movement information reported by the detection point, the following method is used to determine whether there is at least one simulated target located in the identification blind spot of the detection point:

[0010] For each of the detection points:

[0011] Based on two consecutive frames of target movement information reported by the detection point, if it is determined that a target exists in the previous frame but does not appear in the next frame, and the speed of the target in the previous frame of target movement information is greater than a preset threshold, then the target is regarded as a simulated target located in the identification blind spot of the detection point.

[0012] In some embodiments, the method further includes: updating the movement information of the simulated target in the following manner, including:

[0013] For each of the simulation targets, the following formula is used to determine the preceding vehicle following conflict determination parameter △x:

[0014] △x= Y1+ V1×t-(Y2+ V2×t)-l2

[0015] in:

[0016] V1 represents the velocity of the simulated target, and Y1 represents the position of the simulated target;

[0017] t represents the preset duration;

[0018] V2 represents the velocity of the previous target of the simulated target, and Y2 represents the position of the previous target;

[0019] l2 represents the vehicle length of the previous target;

[0020] If △x is greater than zero, the speed of the simulated target is updated to the speed V2 of the previous target, and the position of the simulated target is updated to: Y2+ V2×t - l2;

[0021] If △x is less than zero, the speed of the simulated target is updated to: V1' =min(V1+ a1×t, V m ); and, the position of the simulated target is updated to: Y1' = Y1+ V1'×t;

[0022] Wherein, a1 represents the vehicle driving acceleration preset for the target road section, V m Indicates the maximum driving speed preset for the target road section.

[0023] In some embodiments, the updating of the movement information of the simulated target further includes:

[0024] The following formula is used to determine the rear vehicle following conflict judgment parameter △x':

[0025] △x'= Y2'- Y1'

[0026] When △x' is greater than zero, the speed V1' of the simulated target is updated again to the speed V2' of the target after the simulated target; and the position Y1' of the simulated target is updated to Y1' = Y2' + l2'; wherein Y2' represents the position of the target after, and l2' represents the length of the target after.

[0027] In some embodiments, the method further comprises: for each of the detection points, determining a maximum simulated distance of the detection point;

[0028] The updated position of each simulated target does not exceed the maximum simulated distance of the detection point to which the simulated target belongs.

[0029] In some embodiments, the determining of the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target comprises:

[0030] Matching a preset area image of a first target at a first detection point with a preset area image of a second target at a second detection point, and when a similarity is greater than a preset value, determining that the first target and the second target are the same target;

[0031] The first target is a simulated target, and the second target is a detected target.

[0032] In some embodiments, the determining of the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target comprises:

[0033] When one or a combination of the following conditions is met, it is determined that the first target at the first detection point and the second target at the second detection point are the same target:

[0034] Condition 1: the absolute value of the difference between the speed of the first target and the speed of the second target is less than a preset speed difference threshold;

[0035] Condition 2: the absolute value of the difference between the position of the first target and the position of the second target is less than a preset distance threshold;

[0036] Condition three: the absolute value of the difference between the lane number of the first target and the lane number of the second target is less than or equal to a preset lane change threshold;

[0037] The first target is a simulated target, and the second target is a detected target.

[0038] In some embodiments, based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulated targets, the movement information of the same target is determined, including:

[0039] If the difference between the position of the first target at the first detection point and the position of the second target at the second detection point is greater than a preset threshold, the movement information of the second target is deleted, and the movement information of the first target is updated in the following manner:

[0040] If the position of the first target is smaller than the position of the second target, increasing the speed of the first target;

[0041] If the position of the first target is greater than the position of the second target, reducing the speed of the first target;

[0042] Among them, the first detection point is the upstream detection point of the target section, the second detection point is the downstream detection point of the target section, the first target is a simulation target, the second target is a detection target, and the first target and the second target are the same target.

[0043] In some embodiments, the speed of the first target is increased using the following formula:

[0044] V1' = (Y2-Y1) + V2;

[0045] The speed of the first target is reduced using the following formula:

[0046] V1' = V2-(Y1- Y2);

[0047] Wherein, V1' represents the updated speed of the first target, V2 represents the speed of the second target; Y1 represents the position of the first target, and Y2 represents the position of the second target.

[0048] In some embodiments, when increasing the speed of the first target, the method further comprises:

[0049] Determining a maximum speed based on an absolute value of a difference between the position of the first target and the position of the second target; and updating the maximum speed to the maximum speed limit value when the maximum speed is greater than a maximum speed limit value preset for the target road;

[0050] If the updated speed of the first target is greater than the maximum speed, finally updating the speed of the first target to the maximum speed;

[0051] When reducing the speed of the first target, the method further comprises:

[0052] Determine a minimum speed based on an absolute value of a difference between the position of the first target and the position of the second target; and when the minimum speed is less than a minimum speed limit value preset for the target road, update the minimum speed to the minimum speed limit value;

[0053] If the updated speed of the first target is less than the minimum speed, the speed of the first target is finally updated to the minimum speed.

[0054] In some embodiments, based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulated targets, the movement information of the same target is determined, including:

[0055] If the difference between the position of the first target at the first detection point and the position of the second target at the second detection point is less than a preset threshold, the movement information of the first target is deleted, the movement information of the second target is retained, and the movement information of the second target in the previous frame is updated to be the movement information of the first target in the previous frame;

[0056] Among them, the first detection point is the upstream detection point of the target section, the second detection point is the downstream detection point of the target section, the first target is a simulation target, the second target is a detection target, and the first target and the second target are the same target.

[0057] In some embodiments, the method further comprises:

[0058] For any two consecutive frames of motion information of the same target: based on the motion information of the two consecutive frames, determine the interpolation unit between the two consecutive frames of the target; based on the interpolation unit between the two consecutive frames of the target, determine the multi-frame motion information between the two consecutive frames of the target;

[0059] Based on the multiple frames of movement information, the movement trajectory information of the target is determined.

[0060] In some embodiments, determining the interpolation unit between the two consecutive frames of the target based on the movement information of the two consecutive frames includes:

[0061] The interpolation unit between two consecutive frames of the target is determined using the following formula:

[0062] ;

[0063] ;

[0064] ;

[0065] ;

[0066] Among them, unit x 、unit y 、unit v 、unit a Respectively represent the interpolation unit of the horizontal coordinate, the interpolation unit of the vertical coordinate, the interpolation unit of the speed, and the interpolation unit of the direction angle between the two consecutive frames of the target;

[0067] car x1 、car y1 , V1, angle1 represent the horizontal coordinate, vertical coordinate, speed, and direction angle of the target in the previous frame respectively;

[0068] car x2 、car y2 , V2, angle2 represent the horizontal coordinate, vertical coordinate, speed, and direction angle of the target in the next frame respectively;

[0069] N represents the preset interpolation frame rate;

[0070] Wherein, the previous frame and the next frame are two consecutive frames;

[0071] The step of determining the multi-frame movement information between the two consecutive frames of the target based on the interpolation unit between the two consecutive frames of the target includes:

[0072] The following formula is used to determine the i-th frame movement information of the target between the two consecutive frames:

[0073] ;

[0074] ;

[0075] ;

[0076] ;

[0077] Among them, car xi 、car yi 、V i 、angle i Respectively represent the horizontal coordinate, vertical coordinate, speed and direction angle of the target in the i-th frame between two consecutive frames.

[0078] In some embodiments, the method further comprises:

[0079] When it is determined that there is a vehicle queuing event at the road stop line position corresponding to the second detection point, the initial queuing position of the first vehicle is determined as: the sum of the distance between the first detection point and the second detection point and the distance to the blind spot of the field of vision of the detection device of the second detection point;

[0080] The first detection point is an upstream detection point of the target road section, and the second detection point is a downstream detection point of the target road section.

[0081] In some embodiments, when there are more than a preset number of targets whose moving speeds are lower than a preset threshold at the road stop line position corresponding to the second detection point, it is determined that a vehicle queuing event exists.

[0082] In some embodiments, the method further comprises:

[0083] For each simulated target under the first detection point:

[0084] If the position of the simulated target is car y Overtaking the rear car end , then the position of the simulated target car y Update to the last position car end , and update the tail position car end for:

[0085] car end =car end -car len

[0086] Among them, car len Indicates the length of the vehicle;

[0087] Update the speed of the simulated target to zero, and record the simulated target as a queue target;

[0088] When it is determined that there is no vehicle queuing event at the road stop line position corresponding to the second detection point, the speed of the queuing target is increased, and the increased speed does not exceed the maximum speed limit value of the target road section.

[0089] An object tracking device provided in an embodiment of the present application includes:

[0090] The first unit is used to obtain target movement information reported by multiple detection points pre-set on the target road section; wherein the target movement information reported by each detection point is the target movement information obtained by identifying and detecting the tracking target through the detection equipment of the detection point;

[0091] The second unit is configured to: for each of the detection points, determine at least one detection target located in the identification area of ​​the detection point based on the target movement information reported by the detection point, and determine the movement information of each of the detection targets; and, based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the identification blind area of ​​the detection point, further determine the movement information of each of the simulated targets;

[0092] The third unit is used to determine the same target based on the movement information of the detection targets of the multiple detection points and the movement information of the simulated target, and determine the movement information of the same target.

[0093] Another embodiment of the present application provides an electronic device, which includes a memory and a processor, wherein the memory is used to store program instructions, and the processor is used to call the program instructions stored in the memory and execute any of the above methods according to the obtained program.

[0094] Another embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable the computer to execute any of the above methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0096] Figure 1 A schematic diagram of the overall process of a target tracking method provided in an embodiment of the present application;

[0097] Figure 2 A schematic diagram of a specific process of a target tracking method provided in an embodiment of the present application;

[0098] Figure 3 A schematic diagram of each detection point and its identification area and blind area in a rear vehicle mode provided in an embodiment of the present application;

[0099] Figure 4 A schematic diagram of each detection point and its identification area and blind area in a head-on mode provided in an embodiment of the present application;

[0100] Figure 5 Schematic diagram of the visual field blind area, identification area, and detection blind area of ​​the detection point provided in the embodiment of the present application;

[0101] Figure 6 A schematic diagram of a queue simulation position provided in an embodiment of the present application;

[0102] Figure 7 A schematic diagram of a current detection point and a downstream detection point in a queue simulation provided in an embodiment of the present application;

[0103] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0104] Fig. 9 A schematic diagram of the structure of a target tracking device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0105] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0106] The embodiments of the present application provide a target tracking method, apparatus, device and medium for realizing continuous tracking of the target movement process of the entire target section and obtaining full-sample continuous trajectory tracking data of the target.

[0107] Among them, the method and the device, equipment, and medium are based on the same application concept. Since the principles of solving problems by the method and the device, equipment, and medium are similar, the implementation of the device, equipment, medium, and method can refer to each other, and the repeated parts will not be repeated.

[0108] The terms "first", "second", etc. (if any) in the description and claims of the embodiments of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0109] It should be understood that the numbers used in this way are interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "comprises" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0110] The following examples and embodiments are to be understood as illustrative examples only. Although this specification may refer to "one", "an" or "some" examples or embodiments in several places, this does not mean that each such reference relates to the same example or embodiment, nor does it mean that the feature applies only to a single example or embodiment. Individual features of different embodiments may also be combined to provide other embodiments. In addition, terms such as "including" and "comprising" should be understood as not limiting the described embodiments to consist only of those features that have been mentioned; such examples and embodiments may also include features, structures, units, modules, etc. that are not specifically mentioned.

[0111] The following is a detailed description of each embodiment of the present application in conjunction with the accompanying drawings. It should be noted that the display order of the embodiments of the present application only represents the order of the embodiments, and does not represent the advantages and disadvantages of the technical solutions provided by the embodiments.

[0112] Traditional traffic management technology seems relatively backward in the face of growing demand, and the existing traffic management system's discrete application and information islanding approach to traffic problems is no longer applicable.

[0113] As cutting-edge trends in smart transportation, technologies such as digital twins and traffic perception can truly promote the implementation of digital twin traffic management systems that feature global management, synchronous visualization, and virtual-real interaction, and solve industry pain points such as traffic congestion and traffic safety. Therefore, holographic perception is a key research direction in the field of transportation.

[0114] See also Figure 1, a target tracking method provided by an embodiment of the present application includes:

[0115] S101, obtaining target movement information reported by a plurality of detection points pre-set on a target road section; wherein the target movement information reported by each detection point is the target movement information obtained by identifying and detecting the tracking target through the detection equipment of the detection point;

[0116] The target may be, for example, a motor vehicle, a non-motor vehicle, a pedestrian, or the like that needs to be monitored.

[0117] The target movement information may include, for example, vehicle ID, license plate, vehicle model, location (such as longitude and latitude coordinates), speed, direction angle, etc., and may also include the collected vehicle image.

[0118] The detection device is, for example, a camera, a radar, or a radar detection device (i.e., a radar detection and video detection integrated device).

[0119] For example, a detection point may be set at a preset distance on the target road section, or a detection point may be set at each intersection on the road, and detection equipment may be installed at the detection point to collect target movement information.

[0120] S102, for each of the detection points: based on the target movement information reported by the detection point, determine at least one detection target located in the identification area of ​​the detection point, and determine the movement information of each of the detection targets; and based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the identification blind area of ​​the detection point, further determine the movement information of each of the simulated targets;

[0121] Among them, for each of the detection points: based on the target movement information reported by the detection point, at least one detection target located in the identification area of ​​the detection point is determined, and the movement information of each of the detection targets is determined. For example, for each detection point, based on the vehicle data detected by the detection point, if it is determined that the same vehicle appears in two consecutive frames (of course, it can also be more frames), the vehicle can be determined as the detection target, and the movement information of the detection target is recorded, such as vehicle ID, license plate, vehicle model, location (such as longitude and latitude coordinates), speed, direction angle, etc.

[0122] For each of the detection points: based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the recognition blind spot of the detection point, the movement information of each of the simulated targets is further determined. For example, for each detection point, based on the vehicle data detected by the detection point, if in two consecutive frames of data, it is determined that a vehicle exists in the previous frame but does not appear in the next frame, then the vehicle is determined to be a disappeared target in the detection and recognition area, that is, it has entered the detection blind spot;

[0123] Then, for the disappeared target, if the speed of the disappeared target is less than the preset threshold when the disappeared target disappears, no simulation is performed, that is, there is no need to predict the position and speed of the disappeared target;

[0124] Otherwise, the disappeared target is regarded as the target in the simulation area (i.e., the detection blind area). The target in the simulation area is the target whose position and speed are simulated for the target that disappears in the detection and identification area. It can also be called a simulated target or a simulated vehicle, that is, after disappearing from the detection and identification area, in order to keep its track uninterrupted, the target continues to simulate its normal driving.

[0125] Furthermore, based on the position and speed of the simulated target in the previous frame, the current position of the simulated target in the current frame is predicted, and the movement information of the simulated target in the previous frame and the current frame (for example, including vehicle ID, license plate, vehicle model, position, speed, etc.) is recorded.

[0126] That is to say, each detection device has an identifiable area range and a blind spot range for the target road section. Therefore, the embodiment of the present application can realize the fusion of the target movement trajectory for the entire target road section by detecting the movement information of the target in the identification area of ​​each detection point and simulating the target movement information in the identification blind spot of the detection point.

[0127] S103, based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulation targets, determine the same target and the movement information of the same target.

[0128] That is, the embodiment of the present application first performs target fusion based on the movement information of the targets at each detection point (including the actually detected targets and the targets simulated in the blind spot), that is, determines the same target, avoids repeatedly determining the movement trajectory data of the same target, and further determines the movement trajectory data of each target.

[0129] In some embodiments, the method further comprises:

[0130] For each of the simulated targets, the movement information of the simulated target is updated using the car-following model.

[0131] The car-following model includes a leading car-following model and / or a trailing car-following model.

[0132] Regarding the car-following model, that is, for all simulated vehicles, in order to solve the problem of improper vehicle speed simulation and the occurrence of vehicle crushing, a vehicle-following strategy is adopted to simulate the vehicle's driving trajectory.

[0133] For example, a car disappears from the detection and recognition area at a speed of 60km / h. At the same time, another car 10 meters behind the car also disappears at a speed of 80km / h. If the two cars are simulated according to their disappearance speeds, then (80 / 3.6×t = 10 + 60 / 3.6×t) 1.8s later, the two cars collide. Therefore, when simulating a vehicle, it is necessary to consider its own speed, the speed of the vehicle in front, and the distance to the vehicle in front to determine the simulated speed of the vehicle.

[0134] In some embodiments, the method further comprises: for each of the detection points, determining a maximum simulated distance of the detection point;

[0135] The updated position of each simulated target does not exceed the maximum simulated distance of the detection point to which the simulated target belongs.

[0136] The maximum simulated distance of any detection point is the maximum simulated distance after the target disappears from the identification area of ​​the detection point. How to determine the maximum simulated distance can be determined according to actual needs.

[0137] It can be seen that the road section trajectory fusion method based on radar perception data provided in the embodiment of the present application solves the problem of splicing vehicle trajectories on the entire trunk line of non-closed roads in the city, realizes continuous tracking of vehicle driving process on the entire trunk line, and obtains full-sample continuous trajectory tracking data of road section vehicles at the same time, accurately obtaining various real-time dynamic data such as the actual position, speed, direction angle, acceleration, etc. of the vehicle at each moment.

[0138] A more specific example of the method provided in the embodiments of the present application is given below.

[0139] The embodiment of the present application provides a method for fusion of road segment trajectories based on radar perception data, such as Figure 2 As shown, the following steps are included:

[0140] S201, initialization of basic configuration information of detection points.

[0141] This step includes determining the maximum simulated distance of each detection point;

[0142] In some embodiments, this step may also include determining a queue simulation location.

[0143] The detection point is the location where the detection equipment is installed;

[0144] The detection equipment is, for example, a radar video all-in-one device (referred to as radar video equipment).

[0145] The queue simulation position refers to the initial position of the first vehicle queue simulated by the upstream detection point when the downstream detection point detects the existence of a queue.

[0146] Specifically:

[0147] 1. Regarding the determination of the maximum simulation distance of each detection point:

[0148] As Figure 3 Taking the detection point 1 shown in the figure as an example, vehicle information can be detected in the identification area of ​​the detection device of detection point 1 (i.e., the area between the nearest detection point of the radar of detection point 1 and vanishing point 1). The vehicle information includes vehicle ID, license plate, vehicle model, location, speed, etc. When the vehicle leaves the range of this identification area, the detection device of detection point 1 will no longer report any data of the vehicle. In order to keep the trajectory of the vehicle uninterrupted, it is necessary to continue to simulate the trajectory of the vehicle, that is, to predict the vehicle trajectory data of a certain distance. Therefore, it is necessary to define the simulation target, the farthest position to be simulated, that is, the maximum simulation distance starting from the vanishing point (e.g., vanishing point 1, i.e., the boundary point of the identification area of ​​detection point 1).

[0149] Take detection point 1 as an example, see Figure 3 , assuming that the distance between detection point 1 and detection point 2 is d 12 , the distance between detection point 2 and detection point 3 is d 23 , detection point 3 and detection point 4 ( Figure 3 The distance between them is d 34 , and so on. Then, in some embodiments, the maximum simulated distance of the detection point 1 may be determined in the following manner:

[0150] In rear mode:

[0151] like Figure 3 As shown, the maximum simulated distance of detection point 1 is d 12 +d 23 ;

[0152] In some embodiments, if the detection device at detection point 2 is offline or abnormal, the maximum simulated distance of detection point 1 may be determined to be d 12 +d 23 +d 34 Therefore, the embodiment of the present application can simulate the target moving trajectory normally for abnormal points and offline points, and will not cause interruption of the trajectory of the entire road section.

[0153] In head mode:

[0154] like Figure 4 As shown, the maximum simulated distance of detection point 1 can be determined to be d 12 ;

[0155] If the detection device at detection point 2 is offline or abnormal, the maximum simulation distance of detection point 1 can be determined to be d 12 +d 23 .

[0156] The rear / front mode is defined according to the direction in which the radar equipment is installed:

[0157] If the irradiation direction of the radar equipment is consistent with the vehicle's travel direction, it is defined as the rear mode. Figure 3 As shown, the illumination direction of the radar device is from left to right, and the vehicle travels from left to right.

[0158] If the irradiation direction of the radar equipment is opposite to the vehicle's travel direction, it is defined as the vehicle head mode, such as Figure 4 As shown, the radiation direction of the radar device is from left to right, and the vehicle travels from right to left.

[0159] 2. Regarding determining the simulated queue position:

[0160] For example, in rear mode, if Figure 3 As shown in the figure, assuming that detection point 2 is an intersection, the detection equipment at detection point 2 is installed on the electric alarm pole. When the detection point 2 detects that there is a queue of vehicles at the stop line position, the simulated target at detection point 1 starts to queue. When the detection equipment is installed, due to the existence of the installation pitch angle, there will be blind spots, including visual blind spots and detection blind spots, such as Figure 5 Assume that the distance of the blind spot of the bottom edge of the detection device at detection point 2 is d 2b , then we can determine that the initial queue position of the first vehicle simulated at detection point 1 is d 12 +d 2b .

[0161] Generally, vehicles will queue up at intersections due to the influence of red lights. Radar vision equipment will only be installed in two locations at intersections: one is the electric alarm pole at the entrance of the intersection, and the other is the traffic light pole at the exit of the intersection. If it is installed in the reverse direction of the intersection (i.e. the front of the vehicle), the radar vision equipment can detect the queue at the entrance of the intersection, so there is no need to configure the queue. If the radar vision equipment is installed in the forward direction of the intersection (i.e. the rear of the vehicle), the radar vision equipment cannot detect the vehicle target at the entrance of the intersection, and it is necessary to configure whether the simulated vehicles are queued. Figure 6 As shown, assuming that the middle detection point is at an intersection, in the rear vehicle mode, the left side of the radar vision device is a detection blind spot and cannot sense the vehicle queue situation, so a queue simulation is required. In the front vehicle mode, the right side of the radar vision device is within the detection range and can sense the vehicle queue situation, so there is no need for a queue simulation.

[0162] S202: Data processing of each detection point.

[0163] This step includes data processing of the detection identification area and detection blind area for each detection point;

[0164] In some embodiments, this step also includes: queuing data processing, that is, performing simulated queuing and dissipation process processing after simulated queuing for the detection points configured with queuing simulation.

[0165] Specifically, for each detection point:

[0166] 1. Data processing of the detection and identification area:

[0167] Based on the target movement information reported by the detection point, at least one detection target of the detection point is determined, and the movement information of each detection target is recorded.

[0168] 2. Data processing of detection blind areas:

[0169] Step 1: based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the identification blind spot of the detection point, further determine the movement information of each of the simulated targets.

[0170] In some embodiments, it also includes:

[0171] Step 2: For each simulated target, the movement information of the simulated target is updated using the car-following model.

[0172] The embodiment of the present application uses the target following model to make the target's moving trajectory generated finally more realistic, effectively reducing the occurrence of abnormal situations caused by improper simulation and rolling conflicts. Specifically, for example:

[0173] ①Following the front vehicle: Assume that the speed (i.e. simulated speed) of the current simulated vehicle A is V1, the position (i.e. simulated position) is Y1, and the speed of the front vehicle B (which can be a simulated target or an actual detected target) is V2, the position is Y2, and the vehicle length is l2. Then, the following formula can be used to determine the conflict based on the speed-distance relationship:

[0174] △x= Y1+ V1×t-(Y2+ V2×t)-l2

[0175] Among them, △x represents the preceding vehicle following conflict judgment parameter;

[0176] Wherein, t represents the preset driving time.

[0177] If △x is greater than zero, it means that the current simulated vehicle A is too fast and will crush the front vehicle B, resulting in a conflict. Therefore, the speed of the current simulated vehicle A is set to the speed of the front vehicle B V2, and the coordinates are set to:

[0178] Y2+ V2×t - l2

[0179] If △x is less than zero, it means that the current simulated vehicle A is suitable and will not cause a conflict with the front vehicle B. Therefore, the current simulated vehicle A can be accelerated appropriately. Assume that the vehicle acceleration on this road section is a1 and the maximum driving speed is V m , then re-simulate the speed V1' of the current simulated vehicle A as:

[0180] V1' =min(V1+ a1×t, V m )

[0181] Furthermore, the position Y1' of the current simulated vehicle A is recalculated according to V1':

[0182] Y1' = Y1 + V1' × t

[0183] For other simulated targets, the above-mentioned front vehicle conflict judgment is performed similarly. If △x is greater than zero, the front vehicle is followed as above, that is, the speed and position of the simulated target are updated according to the speed and position of the front vehicle; if △x is less than zero, the position and speed of the simulated target are updated according to the vehicle driving acceleration and maximum driving speed on the road section where the simulated target is located.

[0184] ② Following vehicle: Assume that the current simulated vehicle A has a speed of V1 and a position of Y1, and the actual detected speed of the following vehicle B' (detection target) is V2' and the position is Y2', and the vehicle length is l2'. Since the following vehicle B' is the actual detection target, the position and speed of vehicle B' cannot be modified. Therefore, for the simulated target A, if the position and speed of the following vehicle B' are not considered, the simulated target A may be crushed by the following vehicle, causing a conflict.

[0185] According to the above-mentioned front vehicle following model, the position and speed of the simulated target A are updated normally. Assuming that the updated position of the simulated target A is Y1', the updated speed is V1', and the actual detected speed and position of the rear vehicle B' are V2' and Y2', the conflict between the simulated target A and the detected target B' is determined as follows:

[0186] △x'= Y2'- Y1'

[0187] If △x' is greater than zero, it means that the speed of the simulated target A is too low, and the detected target (the rear vehicle B') has crushed the simulated target (the front vehicle A). Therefore, the rear vehicle needs to follow the car, that is, the position and speed of the simulated target A need to be updated as follows according to the speed and position of the rear vehicle B':

[0188] V1' =V2'

[0189] Y1' = Y2' + l2'

[0190] 3. About queue data processing.

[0191] ①Queue detection:

[0192] When it is determined that there is a vehicle queuing event at the road stop line position corresponding to the second detection point, the initial queuing position of the first vehicle is determined as: the sum of the distance between the first detection point and the second detection point and the distance to the blind spot of the field of vision of the detection device of the second detection point;

[0193] The first detection point is an upstream detection point of the target road section, and the second detection point is a downstream detection point of the target road section.

[0194] Regarding how to determine the presence of a vehicle queue event, for example: when there are at least N (N is a preset integer greater than 1) vehicles within the stop line range of the downstream lane whose speed is less than a preset speed threshold (e.g. 5km / h), it is determined that the lane is in a queue state, that is, there is a vehicle queue event at the road stop line position corresponding to the downstream detection point. That is, when there are more than a preset number of targets at the road stop line position corresponding to the second detection point whose moving speed is less than a preset threshold, it is determined that there is a vehicle queue event.

[0195] That is to say, at this time, the road position of the vehicle queue can be determined, that is, the position of the head and the tail of the queue can be determined, which is the blind spot position of the detection equipment at the downstream detection point. That is, the first vehicle in the queue (i.e., the head of the queue) is at the upstream detection point, and the last vehicle (i.e., the tail of the queue) is at the blind spot position of the downstream detection point. The length of the vehicle queue is the distance between the upstream and downstream detection points plus the length of the blind spot of the downstream detection point on the road, for example Figure 3 The d shown 12 +d 2b .

[0196] If there are no N vehicles with speeds less than a preset speed threshold within the stop line range of the downstream lane, it means that the lane is in a non-queuing state.

[0197] ②Determine the queuing target:

[0198] See also Figure 7 , for the current detection point, if the downstream lane of the detection point is currently in a queue state, then for all simulated targets under the detection point, queue simulation is performed in sequence from front to back:

[0199] For each simulated target, if the position of the simulated target in the current frame data is car y Overtaking the rear car end , then the position of the simulated target in the current frame simulation data is car y Update to the last position car end , and update the tail position carend for:

[0200] car end =car end -car len

[0201] Among them, car len Indicates the length of the vehicle. Since the position of the vehicle is defined based on the center point of the vehicle, and since the length of each vehicle type is different, it is necessary to consider the length of the vehicle to determine the actual position of the vehicle.

[0202] Furthermore, in the current frame data, the vehicle speed of the simulated target is updated to 0, and the simulated target is marked as a queuing target.

[0203] ③ Queue dissipation:

[0204] When it is determined that there is no vehicle queuing event at the road stop line position corresponding to the second detection point, the speed of the queuing target is increased, and the increased speed does not exceed the maximum speed limit value of the target road section.

[0205] That is to say, when there is no vehicle queuing event at the road stop line position corresponding to the downstream detection point, the speed of the queuing target can be increased based on the following model of the simulation area in the above step S202, and the maximum speed does not exceed the maximum speed of the road section.

[0206] It can be seen that the embodiment of the present application establishes a queuing theory model for a signal-controlled intersection, so that the generated target movement trajectory at the entrance of the intersection can be more realistic.

[0207] S203: Target fusion is performed on the upstream and downstream detection points.

[0208] Tail Mode Fusion:

[0209] That is, based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulated targets, determining the same target includes:

[0210] Matching a preset area image of a first target at a first detection point with a preset area image of a second target at a second detection point, and when a similarity is greater than a preset value, determining that the first target and the second target are the same target;

[0211] The first target is a simulated target, and the second target is a detected target.

[0212] Specifically, for example, in the rear mode, the vehicle target starts to appear from the nearest detection point of the radar camera. When the vehicle appears, there will be license plate information, but the detection device may have recognition errors for license plate recognition, such as 1 and i, 0 and 0, which may all be recognized incorrectly. Therefore, in the rear mode, fusion matching judgment can be performed based on license plate similarity. For example, if the license plate similarity is greater than 80%, the two detection targets (i.e., the first target and the second target) at the upstream and downstream detection points are considered to be the same vehicle.

[0213] Head mode fusion:

[0214] That is, based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulated targets, determining the same target includes:

[0215] When one or a combination of the following conditions is met, it is determined that the first target at the first detection point and the second target at the second detection point are the same target:

[0216] Condition 1: the absolute value of the difference between the speed of the first target and the speed of the second target is less than a preset speed difference threshold;

[0217] Condition 2: the absolute value of the difference between the position of the first target and the position of the second target is less than a preset distance threshold;

[0218] Condition three: the absolute value of the difference between the lane number of the first target and the lane number of the second target is less than or equal to a preset lane change threshold;

[0219] The first target is a simulated target, and the second target is a detected target.

[0220] Specifically, for example:

[0221] In the front mode, the vehicle target starts to appear from the far end of the radar camera. When the vehicle appears, only the position, speed and lane information exist, without relevant information such as license plate and model, and it is impossible to match it with the inherent attributes of the vehicle. Therefore, for the front mode, the vehicle's spatial position characteristics can be used for matching.

[0222] Assume that the speed, position, and lane number of vehicle target A (the first target) at detection point 1 are V1, Y1, and l1 respectively, and the speed, position, and lane number of vehicle target B (the second target) at detection point 2 are V2, Y2, and l2 respectively. Then, if the following three conditions are met, the two detection targets (i.e., vehicle target A and vehicle target B) at the upstream and downstream detection points (i.e., detection point 1 and detection point 2) are considered to be the same vehicle:

[0223] Condition 1: The absolute value of the difference between V1 and V2 is less than the preset speed difference threshold V t(e.g. 20km / h);

[0224] Condition 2: The absolute value of the difference between Y1 and Y2 is less than the preset distance threshold Y t (e.g. 80m);

[0225] Condition 3: The absolute value of the difference between l1 and l2 is less than or equal to the preset lane change threshold l t (For example, 1 means changing lane at most 1).

[0226] S204: Target matching and connection processing.

[0227] For the upstream and downstream targets matched in step S203, that is, the same target, the following data processing is performed taking the rear vehicle mode as an example:

[0228] Assume that the speed and position of vehicle target A (i.e., simulated target, or first target) at detection point 1 are V1 and Y1 respectively, and the speed and position of vehicle target B (i.e., real target, or second target) at detection point 2 are V2 and Y2 respectively; these two targets, target A and target B, are determined to be the same target in the previous step. Then:

[0229] 1. If the difference between Y1 and Y2 is greater than a preset threshold (e.g. 5 meters, i.e. the length of a vehicle body), it is considered that there is a distance difference between targets A and B, and a vehicle connection strategy is adopted for processing. At this time, the information of target A at detection point 1 is retained, and the information of target B at detection point 2 is deleted. Subsequently, the driving trajectory data of target A at detection point 1 is corrected and finally rendered and output;

[0230] Among them, the vehicle connection strategy, that is, when the vehicle simulated at the previous detection point (for example, detection point 1) is actually detected at the next detection point (for example, detection point 2), due to the position deviation between the simulated target and the real detected target, it is necessary to adjust the speed of the simulated target to correct its position so that its position is consistent with the position of the real vehicle. When the position of the simulated target is not much different from the position of the real target (for example, Y1 and Y2

[0231] When the difference between the two is less than the preset threshold, it is considered that the vehicle connection is successful and the trajectory will not be interrupted.

[0232] Therefore, if Y1 is less than Y2, target A needs to accelerate to catch up with target B, and the position displayed by the real-time output of the vehicle trajectory will be closer to the actual position; otherwise, if Y1 is greater than Y2, target A needs to slow down and wait for target B, and the position displayed by the real-time output of the vehicle trajectory of target A will be closer to the actual position.

[0233] In order to make the simulation trajectory more consistent with the real scene trajectory, the acceleration or deceleration change range cannot be too large, otherwise it will produce a state of rapid acceleration or rapid deceleration. Therefore, the speed control adopts the following strategy:

[0234] Case 1: No restriction on speed increment:

[0235] In the acceleration scenario, if you need to control target A to catch up with target B in the next second, the speed of target A is updated as:

[0236] V1' = (Y2-Y1) + V2

[0237] In the deceleration scenario, if you need to control target A to catch up with target B in the next second, the speed of target A is updated as:

[0238] V1' = V2 - (Y1 - Y2)

[0239] Case 2: Based on the above update of the speed of target A, further update the speed of target A according to the distance difference. , limit the speed increment:

[0240] In the acceleration scenario, the maximum speed Vmax of target A is determined based on the distance difference:

[0241]

[0242] If Vmax is greater than the preset speed limit value Vmaxt, that is, the maximum speed is greater than the road speed limit, the maximum speed is updated to Vmax=Vmaxt;

[0243] If the updated speed V1' of the target A is less than Vmax, the speed of the target A is set to V1'; otherwise, the speed of the target A is set to Vmax.

[0244] In the deceleration scenario, the minimum speed Vmin of target A is determined based on the distance difference as follows:

[0245]

[0246] If Vmin is greater than the preset minimum speed limit Vmint, that is, the minimum speed is greater than the minimum operating speed of the road, then the minimum speed of target A Vmin=Vmint;

[0247] If the updated speed V1' of the target A is greater than Vmin, the speed of the target A is set to V1'; otherwise, the speed of the target A is set to Vmin.

[0248] Second, if the distance difference between Y1 and Y2 is less than the preset threshold (the default value is 5 meters, which is the length of a vehicle body), it is considered that target A and target B are in the same position. At this time, the data of target A at detection point 1 is deleted, the data of target B at detection point 2 is retained, and the position of target B in the previous frame is updated to the position of target A in the previous frame.

[0249] S205: trajectory interpolation and smoothing processing.

[0250] That is, for any two consecutive frames of motion information of the same target (for example, from different seconds): based on the motion information of the two consecutive frames, determine the interpolation unit between the two consecutive frames of the target; based on the interpolation unit between the two consecutive frames of the target, determine the multi-frame motion information between the two consecutive frames of the target;

[0251] Based on the multiple frames of movement information, the movement trajectory information of the target is determined.

[0252] Since the data frequency used for trajectory fusion is in the second level, that is, the target data collected by the radar detection device is obtained once per second, which cannot achieve the purpose of direct visualization, the embodiment of the present application performs interpolation and smoothing processing on the fused target trajectory. Specifically, for example:

[0253] Assume that in two consecutive frames (these two frames are from different seconds, that is, assuming that the target data is obtained from the radar detection device in seconds, hereinafter referred to as the previous frame and the next frame respectively), the horizontal coordinate, vertical coordinate, speed, and direction angle of the target vehicle in the previous frame are car x1 、car y1 , V1, angle1, the horizontal coordinate, vertical coordinate, speed and direction angle of the target vehicle in the next frame are car x2 、car y2 , V2, angle2, the frame rate that needs to be interpolated between these two frames is N (a preset integer greater than or equal to 1). For example, if N=20, 20 frames of data are interpolated between the two frames, that is, there are 20 frames of data per second in the end.

[0254] Then, the interpolation unit size unit needs to be calculated for the horizontal coordinate, vertical coordinate, speed, and direction angle respectively. x 、unit y 、unit v 、unit a as follows:

[0255] ;

[0256] ;

[0257] ;

[0258] .

[0259] Then, the horizontal coordinate car of the target vehicle in the i-th frame between these two seconds can be determined xi , vertical coordinate car yi , speed V i 、Direction angle i They are:

[0260] ;

[0261] ;

[0262] ;

[0263] ;

[0264] In summary, the method provided in the embodiment of the present application is for fusing the trajectory of the entire road section under non-closed roads, and can be applied to various scenarios such as non-signal-controlled intersections (intersections without traffic lights) and signal-controlled intersections (intersections with traffic lights). In addition, the embodiment of the present application does not rely heavily on the deployment of detection equipment (including radars, camera lights), does not require full coverage of the detection area, and the frequency of obtaining target movement data from each detection point is in seconds, effectively reducing the access cost of detection equipment.

[0265] The following is an introduction to the equipment or device provided in the embodiments of the present application, in which the explanations or examples of technical features that are the same or corresponding to those described in the above method will not be repeated later.

[0266] An electronic device (for example, any terminal or network device) provided in an embodiment of the present application is Figure 8 , for example:

[0267] The processor 600 is used to read the program in the memory 620 and execute the following process:

[0268] Obtaining target movement information reported by a plurality of detection points pre-set on the target road section; wherein the target movement information reported by each detection point is the target movement information obtained by identifying and detecting the tracking target through the detection equipment of the detection point;

[0269] For each of the detection points: based on the target movement information reported by the detection point, at least one detection target located in the identification area of ​​the detection point is determined, and the movement information of each of the detection targets is determined; and based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the identification blind area of ​​the detection point, the movement information of each of the simulated targets is further determined;

[0270] Based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulation target, the same target is determined, and the movement information of the same target is determined.

[0271] In some embodiments, for each of the detection points: based on the target movement information reported by the detection point, the processor 600 determines that there is at least one simulated target located in the recognition blind spot of the detection point in the following manner:

[0272] For each of the detection points:

[0273] Based on two consecutive frames of target movement information reported by the detection point, if it is determined that a target exists in the previous frame but does not appear in the next frame, and the speed of the target in the previous frame of target movement information is greater than a preset threshold, then the target is regarded as a simulated target located in the identification blind spot of the detection point.

[0274] In some embodiments, the processor 600 is further configured to read a program in the memory 620 and execute the following process:

[0275] The movement information of the simulated target is updated in the following manner, including:

[0276] For each of the simulation targets, the following formula is used to determine the preceding vehicle following conflict determination parameter △x:

[0277] △x= Y1+ V1×t-(Y2+ V2×t)-l2

[0278] in:

[0279] V1 represents the velocity of the simulated target, and Y1 represents the position of the simulated target;

[0280] t represents the preset duration;

[0281] V2 represents the velocity of the previous target of the simulated target, and Y2 represents the position of the previous target;

[0282] l2 represents the vehicle length of the previous target;

[0283] If △x is greater than zero, the speed of the simulated target is updated to the speed V2 of the previous target, and the position of the simulated target is updated to: Y2+ V2×t - l2;

[0284] If △x is less than zero, the speed of the simulated target is updated to: V1' =min(V1+ a1×t, V m ); and, the position of the simulated target is updated to: Y1' = Y1+ V1'×t;

[0285] Wherein, a1 represents the vehicle driving acceleration preset for the target road section, V m Indicates the maximum driving speed preset for the target road section.

[0286] In some embodiments, the updating of the movement information of the simulated target further includes:

[0287] The following formula is used to determine the rear vehicle following conflict judgment parameter △x':

[0288] △x'= Y2'- Y1'

[0289] When △x' is greater than zero, the speed V1' of the simulated target is updated again to the speed V2' of the target after the simulated target; and the position Y1' of the simulated target is updated to Y1' = Y2' + l2'; wherein Y2' represents the position of the target after, and l2' represents the length of the target after.

[0290] In some embodiments, in some embodiments, the processor 600 is further configured to read a program in the memory 620 and execute the following process: for each of the detection points, determine the maximum simulation distance of the detection point;

[0291] The updated position of each simulated target does not exceed the maximum simulated distance of the detection point to which the simulated target belongs.

[0292] In some embodiments, the determining of the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target comprises:

[0293] Matching a preset area image of a first target at a first detection point with a preset area image of a second target at a second detection point, and when a similarity is greater than a preset value, determining that the first target and the second target are the same target;

[0294] The first target is a simulated target, and the second target is a detected target.

[0295] In some embodiments, the determining of the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target comprises:

[0296] When one or a combination of the following conditions is met, it is determined that the first target at the first detection point and the second target at the second detection point are the same target:

[0297] Condition 1: the absolute value of the difference between the speed of the first target and the speed of the second target is less than a preset speed difference threshold;

[0298] Condition 2: the absolute value of the difference between the position of the first target and the position of the second target is less than a preset distance threshold;

[0299] Condition three: the absolute value of the difference between the lane number of the first target and the lane number of the second target is less than or equal to a preset lane change threshold;

[0300] The first target is a simulated target, and the second target is a detected target.

[0301] In some embodiments, based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulated targets, the movement information of the same target is determined, including:

[0302] If the difference between the position of the first target at the first detection point and the position of the second target at the second detection point is greater than a preset threshold, the movement information of the second target is deleted, and the movement information of the first target is updated in the following manner:

[0303] If the position of the first target is smaller than the position of the second target, increasing the speed of the first target;

[0304] If the position of the first target is greater than the position of the second target, reducing the speed of the first target;

[0305] Among them, the first detection point is the upstream detection point of the target section, the second detection point is the downstream detection point of the target section, the first target is a simulation target, the second target is a detection target, and the first target and the second target are the same target.

[0306] In some embodiments, the speed of the first target is increased using the following formula:

[0307] V1' = (Y2-Y1) + V2;

[0308] The speed of the first target is reduced using the following formula:

[0309] V1' = V2-(Y1- Y2);

[0310] Wherein, V1' represents the updated speed of the first target, V2 represents the speed of the second target; Y1 represents the position of the first target, and Y2 represents the position of the second target.

[0311] In some embodiments, when the speed of the first target is increased, in some embodiments, the processor 600 is further configured to read a program in the memory 620 and perform the following process:

[0312] Determining a maximum speed based on an absolute value of a difference between the position of the first target and the position of the second target; and updating the maximum speed to the maximum speed limit value when the maximum speed is greater than a maximum speed limit value preset for the target road;

[0313] If the updated speed of the first target is greater than the maximum speed, finally updating the speed of the first target to the maximum speed;

[0314] When the speed of the first target is reduced, in some embodiments, the processor 600 is further configured to read a program in the memory 620 and execute the following process:

[0315] Determine a minimum speed based on an absolute value of a difference between the position of the first target and the position of the second target; and when the minimum speed is less than a minimum speed limit value preset for the target road, update the minimum speed to the minimum speed limit value;

[0316] If the updated speed of the first target is less than the minimum speed, the speed of the first target is finally updated to the minimum speed.

[0317] In some embodiments, based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulated targets, the movement information of the same target is determined, including:

[0318] If the difference between the position of the first target at the first detection point and the position of the second target at the second detection point is less than a preset threshold, the movement information of the first target is deleted, the movement information of the second target is retained, and the movement information of the second target in the previous frame is updated to be the movement information of the first target in the previous frame;

[0319] Among them, the first detection point is the upstream detection point of the target section, the second detection point is the downstream detection point of the target section, the first target is a simulation target, the second target is a detection target, and the first target and the second target are the same target.

[0320] In some embodiments, the processor 600 is further configured to read a program in the memory 620 and execute the following process:

[0321] For any two consecutive frames of motion information of the same target: based on the motion information of the two consecutive frames, determine the interpolation unit between the two consecutive frames of the target; based on the interpolation unit between the two consecutive frames of the target, determine the multi-frame motion information between the two consecutive frames of the target;

[0322] Based on the multiple frames of movement information, the movement trajectory information of the target is determined.

[0323] In some embodiments, determining the interpolation unit between the two consecutive frames of the target based on the movement information of the two consecutive frames includes:

[0324] The interpolation unit between two consecutive frames of the target is determined using the following formula:

[0325] ;

[0326] ;

[0327] ;

[0328] ;

[0329] Among them, unit x 、unit y 、unit v 、unit a Respectively represent the interpolation unit of the horizontal coordinate, the interpolation unit of the vertical coordinate, the interpolation unit of the speed, and the interpolation unit of the direction angle between the two consecutive frames of the target;

[0330] car x1 、car y1 , V1, angle1 represent the horizontal coordinate, vertical coordinate, speed, and direction angle of the target in the previous frame respectively;

[0331] car x2 、car y2 , V2, angle2 represent the horizontal coordinate, vertical coordinate, speed, and direction angle of the target in the next frame respectively;

[0332] N represents the preset interpolation frame rate;

[0333] Wherein, the previous frame and the next frame are two consecutive frames;

[0334] The step of determining the multi-frame movement information between the two consecutive frames of the target based on the interpolation unit between the two consecutive frames of the target includes:

[0335] The following formula is used to determine the i-th frame movement information of the target between the two consecutive frames:

[0336] ;

[0337] ;

[0338] ;

[0339] ;

[0340] Among them, car xi 、car yi 、V i 、angle i Respectively represent the horizontal coordinate, vertical coordinate, speed and direction angle of the target in the i-th frame between two consecutive frames.

[0341] In some embodiments, the processor 600 is further configured to read a program in the memory 620 and execute the following process:

[0342] When it is determined that there is a vehicle queuing event at the road stop line position corresponding to the second detection point, the initial queuing position of the first vehicle is determined as: the sum of the distance between the first detection point and the second detection point and the distance to the blind spot of the field of vision of the detection device of the second detection point;

[0343] The first detection point is an upstream detection point of the target road section, and the second detection point is a downstream detection point of the target road section.

[0344] In some embodiments, when there are more than a preset number of targets whose moving speeds are lower than a preset threshold at the road stop line position corresponding to the second detection point, it is determined that a vehicle queuing event exists.

[0345] In some embodiments, the processor 600 is further configured to read a program in the memory 620 and execute the following process:

[0346] For each simulated target under the first detection point:

[0347] If the position of the simulated target is car y Overtaking the rear car end , then the position of the simulated target car y Update to the last position car end , and update the tail position car end for:

[0348] car end =car end -car len

[0349] Among them, car len Indicates the length of the vehicle;

[0350] Update the speed of the simulated target to zero, and record the simulated target as a queue target;

[0351] When it is determined that there is no vehicle queuing event at the road stop line position corresponding to the second detection point, the speed of the queuing target is increased, and the increased speed does not exceed the maximum speed limit value of the target road section.

[0352] The transceiver 610 is configured to receive and send data under the control of the processor 600 .

[0353] Among them, Figure 8 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 600 and various circuits of memory represented by memory 620 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 610 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, including wireless channels, wired channels, optical cables, and other transmission media. For different user devices, the user interface 630 may also be an interface capable of externally and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0354] The processor 600 is responsible for managing the bus architecture and general processing, and the memory 620 can store data used by the processor 600 when performing operations.

[0355] In some embodiments, the processor 600 may be a CPU (central processing unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or a CPLD (Complex Programmable Logic Device), and the processor may also adopt a multi-core architecture.

[0356] The processor calls the computer program stored in the memory to execute any of the methods provided in the embodiments of the present application according to the obtained executable instructions. The processor and the memory can also be arranged physically separately.

[0357] It should be noted here that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0358] See also Fig. 9The target tracking device (or target tracking system) provided in the embodiment of the present application includes:

[0359] The first unit 11 is used to obtain target movement information reported by multiple detection points pre-set on the target road section; wherein the target movement information reported by each detection point is the target movement information obtained by identifying and detecting the tracking target through the detection equipment of the detection point;

[0360] The second unit 12 is used for: for each of the detection points, based on the target movement information reported by the detection point, determining at least one detection target located in the identification area of ​​the detection point, and determining the movement information of each of the detection targets; and, based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the identification blind area of ​​the detection point, further determining the movement information of each of the simulated targets;

[0361] The third unit 13 is used to determine the same target based on the movement information of the detection targets of the multiple detection points and the movement information of the simulated target, and determine the movement information of the same target.

[0362] In some embodiments, for each of the detection points: based on the target movement information reported by the detection point, the second unit 12 determines that there is at least one simulated target located in the identification blind spot of the detection point in the following manner:

[0363] For each of the detection points:

[0364] Based on two consecutive frames of target movement information reported by the detection point, if it is determined that a target exists in the previous frame but does not appear in the next frame, and the speed of the target in the previous frame of target movement information is greater than a preset threshold, then the target is regarded as a simulated target located in the identification blind spot of the detection point.

[0365] In some embodiments, the second unit 12 is further configured to:

[0366] The movement information of the simulated target is updated in the following manner, including:

[0367] For each of the simulation targets, the following formula is used to determine the preceding vehicle following conflict determination parameter △x:

[0368] △x= Y1+ V1×t-(Y2+ V2×t)-l2

[0369] in:

[0370] V1 represents the velocity of the simulated target, and Y1 represents the position of the simulated target;

[0371] t represents the preset duration;

[0372] V2 represents the velocity of the previous target of the simulated target, and Y2 represents the position of the previous target;

[0373] l2 represents the vehicle length of the previous target;

[0374] If △x is greater than zero, the speed of the simulated target is updated to the speed V2 of the previous target, and the position of the simulated target is updated to: Y2+ V2×t - l2;

[0375] If △x is less than zero, the speed of the simulated target is updated to: V1' =min(V1+ a1×t, V m ); and, the position of the simulated target is updated to: Y1' = Y1+ V1'×t;

[0376] Wherein, a1 represents the vehicle driving acceleration preset for the target road section, V m Indicates the maximum driving speed preset for the target road section.

[0377] In some embodiments, the updating of the movement information of the simulated target further includes:

[0378] The following formula is used to determine the rear vehicle following conflict judgment parameter △x':

[0379] △x'= Y2'- Y1'

[0380] When △x' is greater than zero, the speed V1' of the simulated target is updated again to the speed V2' of the target after the simulated target; and the position Y1' of the simulated target is updated to Y1' = Y2' + l2'; wherein Y2' represents the position of the target after, and l2' represents the length of the target after.

[0381] In some embodiments, the second unit 12 is further used to: determine, for each of the detection points, a maximum simulated distance of the detection point;

[0382] The updated position of each simulated target does not exceed the maximum simulated distance of the detection point to which the simulated target belongs.

[0383] In some embodiments, the determining of the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target comprises:

[0384] Matching a preset area image of a first target at a first detection point with a preset area image of a second target at a second detection point, and when a similarity is greater than a preset value, determining that the first target and the second target are the same target;

[0385] The first target is a simulated target, and the second target is a detected target.

[0386] In some embodiments, the determining of the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target comprises:

[0387] When one or a combination of the following conditions is met, it is determined that the first target at the first detection point and the second target at the second detection point are the same target:

[0388] Condition 1: the absolute value of the difference between the speed of the first target and the speed of the second target is less than a preset speed difference threshold;

[0389] Condition 2: the absolute value of the difference between the position of the first target and the position of the second target is less than a preset distance threshold;

[0390] Condition three: the absolute value of the difference between the lane number of the first target and the lane number of the second target is less than or equal to a preset lane change threshold;

[0391] The first target is a simulated target, and the second target is a detected target.

[0392] In some embodiments, based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulated targets, the movement information of the same target is determined, including:

[0393] If the difference between the position of the first target at the first detection point and the position of the second target at the second detection point is greater than a preset threshold, the movement information of the second target is deleted, and the movement information of the first target is updated in the following manner:

[0394] If the position of the first target is smaller than the position of the second target, increasing the speed of the first target;

[0395] If the position of the first target is greater than the position of the second target, reducing the speed of the first target;

[0396] Among them, the first detection point is the upstream detection point of the target section, the second detection point is the downstream detection point of the target section, the first target is a simulation target, the second target is a detection target, and the first target and the second target are the same target.

[0397] In some embodiments, the speed of the first target is increased using the following formula:

[0398] V1' = (Y2-Y1) + V2;

[0399] The speed of the first target is reduced using the following formula:

[0400] V1' = V2-(Y1- Y2);

[0401] Wherein, V1' represents the updated speed of the first target, V2 represents the speed of the second target; Y1 represents the position of the first target, and Y2 represents the position of the second target.

[0402] In some embodiments, when the speed of the first target is increased, the second unit 12 is further configured to:

[0403] Determining a maximum speed based on an absolute value of a difference between the position of the first target and the position of the second target; and updating the maximum speed to the maximum speed limit value when the maximum speed is greater than a maximum speed limit value preset for the target road;

[0404] If the updated speed of the first target is greater than the maximum speed, finally updating the speed of the first target to the maximum speed;

[0405] When reducing the speed of the first target, the second unit 12 is further configured to:

[0406] Determine a minimum speed based on an absolute value of a difference between the position of the first target and the position of the second target; and when the minimum speed is less than a minimum speed limit value preset for the target road, update the minimum speed to the minimum speed limit value;

[0407] If the updated speed of the first target is less than the minimum speed, the speed of the first target is finally updated to the minimum speed.

[0408] In some embodiments, based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulated targets, the movement information of the same target is determined, including:

[0409] If the difference between the position of the first target at the first detection point and the position of the second target at the second detection point is less than a preset threshold, the movement information of the first target is deleted, the movement information of the second target is retained, and the movement information of the second target in the previous frame is updated to be the movement information of the first target in the previous frame;

[0410] Among them, the first detection point is the upstream detection point of the target section, the second detection point is the downstream detection point of the target section, the first target is a simulation target, the second target is a detection target, and the first target and the second target are the same target.

[0411] In some embodiments, the third unit 13 is further configured to:

[0412] For any two consecutive frames of motion information of the same target: based on the motion information of the two consecutive frames, determine the interpolation unit between the two consecutive frames of the target; based on the interpolation unit between the two consecutive frames of the target, determine the multi-frame motion information between the two consecutive frames of the target;

[0413] Based on the multiple frames of movement information, the movement trajectory information of the target is determined.

[0414] In some embodiments, determining the interpolation unit between the two consecutive frames of the target based on the movement information of the two consecutive frames includes:

[0415] The interpolation unit between two consecutive frames of the target is determined using the following formula:

[0416] ;

[0417] ;

[0418] ;

[0419] ;

[0420] Among them, unit x 、unit y 、unit v 、unit a Respectively represent the interpolation unit of the horizontal coordinate, the interpolation unit of the vertical coordinate, the interpolation unit of the speed, and the interpolation unit of the direction angle between the two consecutive frames of the target;

[0421] car x1 、car y1 , V1, angle1 represent the horizontal coordinate, vertical coordinate, speed, and direction angle of the target in the previous frame respectively;

[0422] car x2 、car y2 , V2, angle2 represent the horizontal coordinate, vertical coordinate, speed, and direction angle of the target in the next frame respectively;

[0423] N represents the preset interpolation frame rate;

[0424] Wherein, the previous frame and the next frame are two consecutive frames;

[0425] The step of determining the multi-frame movement information between the two consecutive frames of the target based on the interpolation unit between the two consecutive frames of the target includes:

[0426] The following formula is used to determine the i-th frame movement information of the target between the two consecutive frames:

[0427] ;

[0428] ;

[0429] ;

[0430] ;

[0431] Among them, car xi 、car yi 、V i 、angle i Respectively represent the horizontal coordinate, vertical coordinate, speed and direction angle of the target in the i-th frame between two consecutive frames.

[0432] In some embodiments, the second unit 12 is further configured to:

[0433] When it is determined that there is a vehicle queuing event at the road stop line position corresponding to the second detection point, the initial queuing position of the first vehicle is determined as: the sum of the distance between the first detection point and the second detection point and the distance to the blind spot of the field of vision of the detection device of the second detection point;

[0434] The first detection point is an upstream detection point of the target road section, and the second detection point is a downstream detection point of the target road section.

[0435] In some embodiments, when there are more than a preset number of targets whose moving speeds are lower than a preset threshold at the road stop line position corresponding to the second detection point, it is determined that a vehicle queuing event exists.

[0436] In some embodiments, the second unit 12 is further configured to:

[0437] For each simulated target under the first detection point:

[0438] If the position of the simulated target is car y Overtaking the rear car end , then the position of the simulated target car y Update to the last position car end , and update the tail position car end for:

[0439] car end =car end -car len

[0440] Among them, carlen Indicates the length of the vehicle;

[0441] Update the speed of the simulated target to zero, and record the simulated target as a queue target;

[0442] When it is determined that there is no vehicle queuing event at the road stop line position corresponding to the second detection point, the speed of the queuing target is increased, and the increased speed does not exceed the maximum speed limit value of the target road section.

[0443] It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0444] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0445] Any of the devices or apparatuses provided in the embodiments of the present application may specifically be a desktop computer, a portable computer, a smart phone, a tablet computer, a personal digital assistant (PDA), etc. It may include a central processing unit (CPU), a memory, an input / output device, etc. The input device may include a keyboard, a mouse, a touch screen, etc. The output device may include a display device, such as a liquid crystal display (LCD), a cathode ray tube (CRT), etc.

[0446] The memory may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor with program instructions and data stored in the memory. In the embodiment of the present application, the memory may be used to store the program of any of the methods provided in the embodiment of the present application.

[0447] The processor calls the program instructions stored in the memory, and the processor is used to execute any of the methods provided in the embodiments of the present application according to the obtained program instructions.

[0448] The present application embodiment also provides a computer program product or computer program, which includes a computer instruction, which is stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction so that the computer device performs any of the methods described in the above embodiments. The program product can use any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0449] The embodiment of the present application provides a computer-readable storage medium for storing computer program instructions used by the apparatus provided in the embodiment of the present application, which includes a program for executing any of the methods provided in the embodiment of the present application. The computer-readable storage medium may be a non-transitory computer-readable medium.

[0450] The computer-readable storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0451] It should be understood that:

[0452] The access technology through which entities in the communication network transmit traffic can be any suitable current or future technology, such as WLAN (Wireless Local Access Network), WiMAX (Worldwide Interoperability for Microwave Access), LTE, LTE-A, 5G, Bluetooth, infrared, etc.; in addition, the embodiments can also apply wired technology, for example, IP-based access technology, such as a wired network or a fixed line.

[0453] Embodiments suitable for being implemented as software code or a portion thereof and running using a processor or processing functionality are independent of the software code and may be specified using any known or future developed programming language, such as a high-level programming language such as objective-C, C, C++, C#, Java, Python, Javascript, other scripting languages, etc., or a low-level programming language such as machine language or assembler.

[0454] The implementation of the embodiments is hardware independent and may be implemented using any known or future developed hardware technology or any mixture thereof, such as a microprocessor or CPU (Central Processing Unit), MOS (Metal Oxide Semiconductor), CMOS (Complementary MOS), BiMOS (Bipolar MOS), BiCMOS (Bipolar CMOS), ECL (Emitter Coupled Logic) and TTL (Transistor-Transistor Logic).

[0455] Embodiments may be implemented as separate devices, apparatuses, units, components, or functions, or in a distributed manner, for example, one or more processors or processing functions may be used or shared in a process, or one or more processing segments or processing portions may be used and shared in a process, wherein one physical processor or more than one physical processor may be used to implement one or more processing portions dedicated to a specific process as described.

[0456] The device may be implemented by a semiconductor chip, a chipset, or a (hardware) module including such a chip or chipset.

[0457] The embodiments may also be implemented as any combination of hardware and software, such as ASIC (Application Specific IC (Integrated Circuit)) components, FPGA (Field Programmable Gate Array) or CPLD (Complex Programmable Logic Device) components or DSP (Digital Signal Processor) components.

[0458] The embodiments may also be implemented as a computer program product including a computer usable medium having computer readable program code embodied therein, the computer readable program code being adapted to perform the processes as described in the embodiments, wherein the computer usable medium may be a non-transitory medium.

[0459] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.

[0460] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0461] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0462] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0463] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A target tracking method, characterized in that: The method comprises: Obtaining target movement information reported by a plurality of detection points pre-set on the target road section; wherein the target movement information reported by each detection point is the target movement information obtained by identifying and detecting the tracking target through the detection equipment of the detection point; For each of the detection points: based on the target movement information reported by the detection point, at least one detection target located in the identification area of ​​the detection point is determined, and the movement information of each of the detection targets is determined; and based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the identification blind area of ​​the detection point, the movement information of each of the simulated targets is further determined; Determine the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target, and determine the movement information of the same target; Wherein, for each of the detection points: based on the target movement information reported by the detection point, at least one simulated target located in the identification blind area of ​​the detection point is determined in the following manner: For each of the detection points: Based on two consecutive frames of target movement information reported by the detection point, if it is determined that a target exists in the previous frame but does not appear in the next frame, and the speed of the target in the previous frame of target movement information is greater than a preset threshold, then the target is regarded as a simulated target located in the identification blind spot of the detection point.

2. The method according to claim 1, characterized in that The method further includes: updating the movement information of the simulated target in the following manner: For each of the simulation targets, the following formula is used to determine the preceding vehicle following conflict determination parameter △x: △x= Y1+ V1×t-(Y2+ V2×t)-l2 in: V1 represents the velocity of the simulated target, and Y1 represents the position of the simulated target; t represents the preset duration; V2 represents the velocity of the previous target of the simulated target, and Y2 represents the position of the previous target; l2 represents the vehicle length of the previous target; If △x is greater than zero, the speed of the simulated target is updated to the speed V2 of the previous target, and the position of the simulated target is updated to: Y2+ V2×t - l2; If △x is less than zero, the speed of the simulated target is updated to: V1'=min(V1+ a1×t, V m ); and, the position of the simulated target is updated to: Y1' = Y1+ V1'×t; Wherein, a1 represents the vehicle driving acceleration preset for the target road section, V m Indicates the maximum driving speed preset for the target road section.

3. The method according to claim 2, characterized in that The movement information of the simulated target is updated, and further includes: The following formula is used to determine the rear vehicle following conflict judgment parameter △x': △x'= Y2'- Y1' When △x' is greater than zero, the speed V1' of the simulated target is updated again to the speed V2' of the target after the simulated target; and the position Y1' of the simulated target is updated to Y1' = Y2' + l2'; wherein Y2' represents the position of the target after, and l2' represents the length of the target after.

4. The method according to claim 2 or 3, characterized in that: The method further comprises: for each of the detection points, determining a maximum simulation distance of the detection point; The updated position of each simulated target does not exceed the maximum simulated distance of the detection point to which the simulated target belongs.

5. The method according to claim 1, characterized in that The determining of the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target comprises: Matching a preset area image of a first target at a first detection point with a preset area image of a second target at a second detection point, and when a similarity is greater than a preset value, determining that the first target and the second target are the same target; The first target is a simulated target, and the second target is a detected target.

6. The method according to claim 1, characterized in that The determining of the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target comprises: When one or a combination of the following conditions is met, it is determined that the first target at the first detection point and the second target at the second detection point are the same target: Condition 1: the absolute value of the difference between the speed of the first target and the speed of the second target is less than a preset speed difference threshold; Condition 2: the absolute value of the difference between the position of the first target and the position of the second target is less than a preset distance threshold; Condition three: the absolute value of the difference between the lane number of the first target and the lane number of the second target is less than or equal to a preset lane change threshold; The first target is a simulated target, and the second target is a detected target.

7. The method according to claim 1, characterized in that Determining the movement information of the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target includes: If the difference between the position of the first target at the first detection point and the position of the second target at the second detection point is greater than a preset threshold, the movement information of the second target is deleted, and the movement information of the first target is updated in the following manner: If the position of the first target is smaller than the position of the second target, increasing the speed of the first target; If the position of the first target is greater than the position of the second target, reducing the speed of the first target; Among them, the first detection point is the upstream detection point of the target section, the second detection point is the downstream detection point of the target section, the first target is a simulation target, the second target is a detection target, and the first target and the second target are the same target.

8. The method according to claim 7, characterized in that The following formula is used to increase the speed of the first target: V1' = (Y2 -Y1) + V2; The speed of the first target is reduced using the following formula: V1' = V2-(Y1 - Y2); Wherein, V1' represents the updated speed of the first target, V2 represents the speed of the second target; Y1 represents the position of the first target, and Y2 represents the position of the second target.

9. The method according to claim 8, characterized in that When increasing the speed of the first target, the method further comprises: Determine a maximum speed based on an absolute value of a difference between the position of the first target and the position of the second target; and when the maximum speed is greater than a maximum speed limit value preset for the target road, update the maximum speed to the maximum speed limit value; If the updated speed of the first target is greater than the maximum speed, finally updating the speed of the first target to the maximum speed; When reducing the speed of the first target, the method further comprises: Determine a minimum speed based on an absolute value of a difference between the position of the first target and the position of the second target; and when the minimum speed is less than a minimum speed limit value preset for the target road, update the minimum speed to the minimum speed limit value; If the updated speed of the first target is less than the minimum speed, the speed of the first target is finally updated to the minimum speed.

10. The method according to claim 1, characterized in that Determining the movement information of the same target based on the movement information of the detection targets at the plurality of detection points and the movement information of the simulated target includes: If the difference between the position of the first target at the first detection point and the position of the second target at the second detection point is less than a preset threshold, the movement information of the first target is deleted, the movement information of the second target is retained, and the movement information of the second target in the previous frame is updated to be the movement information of the first target in the previous frame; Among them, the first detection point is the upstream detection point of the target section, the second detection point is the downstream detection point of the target section, the first target is a simulation target, the second target is a detection target, and the first target and the second target are the same target.

11. The method according to claim 1, characterized in that: The method further comprises: For any two consecutive frames of motion information of the same target: based on the motion information of the two consecutive frames, determine the interpolation unit between the two consecutive frames of the target; based on the interpolation unit between the two consecutive frames of the target, determine the multi-frame motion information between the two consecutive frames of the target; Based on the multiple frames of movement information, the movement trajectory information of the target is determined.

12. The method according to claim 11, characterized in that The step of determining the interpolation unit between the two consecutive frames of the target based on the movement information of the two consecutive frames includes: The interpolation unit between two consecutive frames of the target is determined using the following formula: ； ； ； ； Among them, unit x 、unit y 、unit v 、unit a Respectively represent the interpolation unit of the horizontal coordinate, the interpolation unit of the vertical coordinate, the interpolation unit of the speed, and the interpolation unit of the direction angle between the two consecutive frames of the target; car x1 、car y1 , V1, angle1 represent the horizontal coordinate, vertical coordinate, speed, and direction angle of the target in the previous frame respectively; car x2 、car y2 , V2, angle2 represent the horizontal coordinate, vertical coordinate, speed, and direction angle of the target in the next frame respectively; N represents the preset interpolation frame rate; Wherein, the previous frame and the next frame are two consecutive frames; The step of determining the multi-frame movement information between the two consecutive frames of the target based on the interpolation unit between the two consecutive frames of the target includes: The following formula is used to determine the i-th frame movement information of the target between the two consecutive frames: ； ； ； ； Among them, car xi 、car yi 、V i 、angle i Respectively represent the horizontal coordinate, vertical coordinate, speed and direction angle of the target in the i-th frame between two consecutive frames.

13. The method according to claim 1, characterized in that The method further comprises: When it is determined that there is a vehicle queuing event at the road stop line position corresponding to the second detection point, the initial queuing position of the first vehicle is determined as: the sum of the distance between the first detection point and the second detection point and the distance to the blind spot of the field of vision of the detection device of the second detection point; The first detection point is an upstream detection point of the target road section, and the second detection point is a downstream detection point of the target road section.

14. The method according to claim 13, characterized in that When there are more than a preset number of targets whose moving speeds are lower than a preset threshold value at the road stop line position corresponding to the second detection point, it is determined that a vehicle queuing event exists.

15. The method according to claim 13, characterized in that The method further comprises: For each simulated target under the first detection point: If the position of the simulated target is car y Overtaking the rear car end , then the position of the simulated target car y Update to the last position car end , and update the tail position car end for: car end =car end -car len Among them, car len Indicates the length of the vehicle; Update the speed of the simulated target to zero, and record the simulated target as a queue target; When it is determined that there is no vehicle queuing event at the road stop line position corresponding to the second detection point, the speed of the queuing target is increased, and the increased speed does not exceed the maximum speed limit value of the target road section.

16. A target tracking device, characterized in that: The device comprises: The first unit is used to obtain target movement information reported by multiple detection points pre-set on the target road section; wherein the target movement information reported by each detection point is the target movement information obtained by identifying and detecting the tracking target through the detection equipment of the detection point; The second unit is configured to: for each of the detection points, determine at least one detection target located in the identification area of ​​the detection point based on the target movement information reported by the detection point, and determine the movement information of each of the detection targets; and, based on the target movement information reported by the detection point, when it is determined that there is at least one simulated target located in the identification blind area of ​​the detection point, further determine the movement information of each of the simulated targets; A third unit is used to determine the same target based on the movement information of the detection targets of the plurality of detection points and the movement information of the simulated target, and to determine the movement information of the same target; Wherein, for each of the detection points: based on the target movement information reported by the detection point, at least one simulated target located in the identification blind area of ​​the detection point is determined in the following manner: For each of the detection points: Based on two consecutive frames of target movement information reported by the detection point, if it is determined that a target exists in the previous frame but does not appear in the next frame, and the speed of the target in the previous frame of target movement information is greater than a preset threshold, then the target is regarded as a simulated target located in the identification blind spot of the detection point.

17. An electronic device, characterized in that: include: A memory for storing program instructions; A processor, configured to call the program instructions stored in the memory and execute the method according to any one of claims 1 to 15 according to the obtained program.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable the computer to execute the method according to any one of claims 1 to 15.

Images