Vehicle tracking method and device based on stake meter number positioning

Abstract

The invention is suitable for the technical field of intelligent transportation, and provides a vehicle tracking method and device based on pile meter number positioning. In the embodiment, for a key area needing to be monitored, basic information of a vehicle is obtained through a first camera at an entrance of the area, and a vehicle model is constructed according to the basic information; after the vehicle enters the area, the driving information of the vehicle is obtained through a second camera in the area; the method comprises the following steps: acquiring driving information of a vehicle in a region, performing frame supplementation and correction on the driving information, generating real-time traffic flow information of the region through the vehicle model, the frame supplementation and correction driving information and a pre-constructed region model of the region, and monitoring the region according to the real-time traffic flow information so as to track key vehicles in the region. Compared with an existing vehicle positioning and tracking method, positioning is more accurate through pile meter number information.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a vehicle tracking method and device based on stake-meter number positioning. Background Art

[0004] For some important sections of roads, such as tunnels, bridges, and some congested sections, the risk control of driving in the area is particularly important due to the importance of their geographical location or the particularity of their building structures. However, in the existing vehicle positioning technology, the dynamic positioning of GPS is affected by factors such as satellite orbit error, clock error, and signal propagation error, and its accuracy is generally 10 to 40 meters; the positioning accuracy of vehicle-mounted GPS can only reach 5 meters in non-surveying and mapping situations, the average best level is about 23 meters, and the average worst level is 30 to 40 meters, which leads to inaccurate positioning of vehicles. Summary of the invention

[0005] In view of this, the present application provides a vehicle tracking method and device based on pole meter number positioning to achieve more accurate positioning and monitoring of vehicles in key monitoring areas, so as to make more accurate corresponding decisions when emergencies occur.

[0006] The first aspect of the present application provides a vehicle tracking method based on stake-meter number positioning, which is applied to an intelligent transportation system, and the method comprises:

[0007] The basic information of the target vehicle is obtained by a first camera at the entrance of the monitoring area, and then the target vehicle is recorded and the speed is measured by a second camera in the monitoring area to obtain the initial driving information of the target vehicle, wherein the initial driving information includes the driving speed and the pole meter number information of the target vehicle, and the pole meter number information is used to characterize the position of the target vehicle in the monitoring area;

[0008] Performing frame interpolation on the initial driving information to obtain frame-interpolated driving information;

[0009] A vehicle model is constructed based on the basic information of the target vehicle, and the real-time traffic flow information of the monitoring area is determined through the vehicle model, the driving information after the frame supplementation, and the pre-constructed regional model of the monitoring area, and the preset key vehicles are tracked based on the real-time traffic flow information.

[0010] Optionally, the step of supplementing the initial driving information includes:

[0011] The initial driving information is stored in a preset buffer pool, and the initial driving information in the buffer pool is updated at a speed of N frames per second using the initial driving information acquired in real time;

[0012] According to the vehicle driving speed and the pile meter number information in the initial driving information in the buffer pool, the frame rate generator performs frame supplementation at a speed of MN frames per second to obtain the driving information after frame supplementation at M frames per second.

[0013] Optionally, after obtaining the frame-filled driving information, the method further includes:

[0014] The driving information after the frame supplement is corrected by the pile meter number information to obtain the corrected driving information. The specific correction method is:

[0015] For the initial driving information T1: [v1, s1], T2: [v2, s2] of two adjacent frames, and the driving information of the supplementary frame between T1 and T2, calculate the distance ds of the target vehicle within the frame time from T1 to T2, and correct the pile meter number information of the driving information of the supplementary frame between T1 and T2 to s2-(s1+ds), where s is the pile meter number information and v is the driving speed;

[0016] The frame-supplemented driving information is updated using the corrected driving information.

[0017] Optionally, the first camera is a bayonet camera, and the second camera is a radar camera.

[0018] Optionally, the method for constructing the regional model of the monitoring area includes:

[0019] Obtaining a design drawing of the monitoring area, and determining the digitized physical properties of the monitoring area according to the design drawing;

[0020] The design drawings and physical properties are input into a predetermined modeling software for three-dimensional static modeling to obtain a regional model of the monitoring area.

[0021] The second aspect of the present application provides a vehicle tracking device based on stake-meter number positioning, which is applied to an intelligent transportation system, and the device includes:

[0022] An initial information acquisition unit is used to acquire basic information of a target vehicle through a first camera at the entrance of a monitoring area, and then to record and measure the speed of the target vehicle in its entirety through a second camera in the monitoring area, so as to obtain initial driving information of the target vehicle, wherein the initial driving information includes the driving speed and the pole meter number information of the target vehicle, and the pole meter number information is used to characterize the position of the target vehicle in the monitoring area;

[0023] An information frame supplementation unit, used for supplementing the initial driving information to obtain the supplemented driving information;

[0024] The vehicle tracking unit is used to construct a vehicle model according to the basic information of the target vehicle, and determine the real-time traffic flow information of the monitoring area through the vehicle model, the final driving information and the pre-constructed regional model of the monitoring area, and track the preset key vehicles according to the real-time traffic flow information.

[0025] Optionally, the step of supplementing the initial driving information in the final information acquisition unit includes:

[0026] The initial driving information is stored in a preset buffer pool, and the initial driving information in the buffer pool is updated at a speed of N frames per second using the initial driving information acquired in real time;

[0027] According to the vehicle driving speed and the pile meter number information in the initial driving information in the buffer pool, the frame rate generator performs frame supplementation at a speed of MN frames per second to obtain the driving information after frame supplementation at M frames per second.

[0028] Optionally, after obtaining the frame-filled driving information, the device further includes:

[0029] The information correction unit is used to correct the driving information after the frame supplementation by using the pile meter number information to obtain the corrected driving information. The specific correction method is:

[0030] For the initial driving information T1: [v1, s1], T2: [v2, s2] of two adjacent frames, and the driving information of the supplementary frame between T1 and T2, calculate the distance ds of the target vehicle within the frame time from T1 to T2, and correct the pile meter number information of the driving information of the supplementary frame between T1 and T2 to s2-(s1+ds), where s is the pile meter number information and v is the driving speed;

[0031] The frame-supplemented driving information is updated using the corrected driving information.

[0032] Optionally, the first camera in the initial information acquisition unit is a bayonet camera, and the second camera is a radar camera.

[0033] Optionally, the method for constructing the regional model of the monitoring area in the vehicle tracking unit includes:

[0034] Obtaining a design drawing of the monitoring area, and determining the digitized physical properties of the monitoring area according to the design drawing;

[0035] The design drawings and physical properties are input into a predetermined modeling software for three-dimensional static modeling to obtain a regional model of the monitoring area.

[0036] In the embodiment provided by the present application, for the key area that needs to be monitored, the basic information of the vehicle is first obtained through the first camera at the entrance of the area, and a vehicle model is constructed based on the basic information; after the vehicle enters the area, the driving information of the vehicle is obtained through the second camera in the area; then after the driving information is supplemented and corrected, the real-time traffic information of the area is generated through the above-mentioned vehicle model, the supplemented and corrected driving information, and the pre-constructed regional model of the area, and the area is monitored based on the real-time traffic information, so as to track the key vehicles in the area. The visual vehicle tracking method provided by the present invention is based on the pile meter number. Compared with the dynamic positioning or vehicle-mounted GPS positioning through the existing GPS, the present application accurately locks the positioning information to the meter level / second level through the pile meter number information. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flow chart of the method provided in the embodiment of the present application;

[0038] Figure 2 A structural diagram of a device provided in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0041] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0042] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0043] The present application provides a vehicle tracking method and device based on pole meter number positioning to achieve more accurate positioning and monitoring of vehicles in key monitoring areas, thereby tracking key vehicles in the area.

[0044] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0045] like Figure 1 As shown, it is a flow chart of a vehicle tracking method based on stake meter number positioning provided by the present application, the method is applied to an intelligent transportation system, and the process may include the following steps:

[0046] Step S101, obtaining basic information of a target vehicle through a first camera at the entrance of a monitoring area, and then recording and measuring the speed of the target vehicle in its entirety through a second camera in the monitoring area to obtain initial driving information of the target vehicle.

[0047] In this embodiment, the basic information of the vehicle may include data such as the license plate number, the shape of the vehicle (length, width and height), etc., so that the vehicle can be modeled according to the basic information of the vehicle later. The initial driving information at least includes the driving speed and the pile meter number information of the target vehicle, which is used to determine the driving condition of the vehicle in the monitoring area. The pile meter number is a meter-level road section marking method, which can provide real-time feedback on where the vehicle is located in the monitoring area.

[0048] In this embodiment, there may be multiple target vehicles in the monitoring area, and the data captured by the camera are actually scattered, that is, the data obtained by the camera has no continuity. It is necessary to aggregate and splice all these scattered and broken data into coherent and valid data through the license plate number in the basic attributes of each target vehicle, so as to determine the basic information and initial driving information of the target vehicle.

[0049] In another embodiment, the first camera is a bayonet camera, and the second camera is a radar camera.

[0050] Bayonet cameras are mainly used for road traffic monitoring and can capture and identify passing vehicles. They are usually installed at the bayonet locations of roads, such as toll booths and major traffic arteries, to record vehicle traffic information, including license plate numbers, vehicle characteristics, etc. Bayonet cameras can identify motor vehicles, non-motor vehicles, and pedestrians, and can detect violations such as speeding, crossing the line, driving in the wrong direction, not wearing seat belts, and making phone calls. Bayonet cameras can also output high-quality full-color images in low-light environments.

[0051] The radar camera is a device that integrates video imaging technology and radar sensing technology, and can realize all-weather, real-time, multi-dimensional and accurate data collection. They can be widely used in scenarios such as highway traffic flow survey and monitoring, road traffic condition monitoring and event perception, traffic target identification and tracking. Through the deep integration of radar and video, the radar camera supports machine, non-machine, and human classification detection and capture, static full-structured feature extraction, and multi-dimensional information collection such as target distance, speed, position, angle, etc. The radar camera has high scene adaptability in complex environments, such as low illumination and abnormal weather, and can provide rich, accurate, and real-time basic data support.

[0052] Bayonet cameras focus on capturing and identifying vehicles, while radar cameras focus on providing more comprehensive and accurate traffic data through the fusion of radar and video technology.

[0053] Step S102, interpolating the initial driving information to obtain interpolated driving information.

[0054] In this embodiment, since the commonly used data transmission method between the application and the server is WebSocket, this transmission method can support our data transmission rate of 12 frames per second, that is to say, when this application obtains the initial driving information, it can obtain it at a rate of up to 12 frames per second. However, the purpose of this application is to display the real-time traffic information of the target vehicle through video. In WEB applications, for a qualified motion visual effect, the average frame rate generally needs to reach about 60 frames. If data at 12 frames per second is used directly, the rendered traffic will have visible freezes, so this application needs to supplement the initial driving information.

[0055] The specific frame filling method is as follows:

[0056] Determine the number of data frames collected per second and the number of data frames required per second to generate the video stream. Use the collected data frames to fill in the frames. For example, if 12 frames are collected per second, and 60 frames are required to generate the video stream, the collected 12 frames of data will be copied to 60 frames, thus achieving the effect of collecting 60 frames per second.

[0057] Furthermore, the pile number information corresponding to the driving information of the supplemented frame can be calculated on average based on the pile number information of two adjacent frames. For example, data frame A and data frame B are adjacent data frames, the pile number information of A is s1, and the pile number information of B is s2. If the number of data frames that need to be supplemented between AB is 10, then the pile number information of the first data frame can be determined as s1+(s2-s1) / 10; and so on, the second data frame is s1+(s2-s1) / 10*2, until the last data frame between A and B is supplemented.

[0058] In another embodiment, the interpolating the initial driving information includes:

[0059] The initial driving information is stored in a preset cache pool, and the push update of WebSocket is monitored in real time. The initial driving information in the cache pool is updated at a speed of N frames per second through the initial driving information obtained in real time.

[0060] According to the vehicle driving speed and the pile meter number information in the initial driving information in the buffer pool, the frame rate generator performs frame supplementation at a speed of MN frames per second to obtain the driving information after frame supplementation at M frames per second.

[0061] In this embodiment, N and M can be set to 12 and 60 respectively. The initial driving information in the buffer pool can be obtained by the frame rate generator, and a new data frame can be obtained by modifying the pile meter number information in the initial driving information during the acquisition, thereby achieving frame supplementation.

[0062] In another embodiment, after obtaining the frame-filled driving information, the method further includes:

[0063] The driving information after the frame supplement is corrected by the pile meter number information to obtain the corrected driving information. The specific correction method is:

[0064] For the initial driving information T1: [v1, s1], T2: [v2, s2] of two adjacent frames, and the driving information of the supplementary frame between T1 and T2, calculate the distance ds of the target vehicle within the frame time from T1 to T2, and correct the pile meter number information of the driving information of the supplementary frame between T1 and T2 to s2-(s1+ds), where s is the pile meter number information and v is the driving speed;

[0065] The frame-supplemented driving information is updated using the corrected driving information.

[0066] After the frame is supplemented, since the speed of the vehicle changes during driving, even in a very small time interval, if the speed changes, the distance we calculate is not accurate. Therefore, in this embodiment, the driving information after the frame supplement can be corrected.

[0067] For example, the initial driving information obtained per second is 12 frames. Assume a car, its speed before and after the 1 / 12 frame is v1, v2 respectively, and this speed, at the data level, is v1 during the 0-1 / 12 frame, and v2 during the 1 / 12-2 / 12 frame. Because the speed is constantly changing, even if the time interval is shortened to 1 / 12 seconds, its speed is constantly changing every 1 / 12 seconds, which leads to inaccurate vehicle driving distance data after we expand the frame. In order to solve this problem, assume that the vehicle speed in the 0-1 / 12 second segment is v1, the captured pile meter number information at 0 seconds is s1, the speed in 1 / 12-2 / 12 seconds is v2, and the captured pile meter number information at 1 / 12 seconds is s2. When the vehicle travels from 0 seconds to 1 / 12 seconds, calculate its distance ds. At this time, the vehicle's travel distance is s1+ds, and the difference between this distance and s2 is calculated as s2-(s1+ds), and then the difference is added to 1 / 12-2 / 12 by increasing or decreasing the speed of 1 / 12-2 / 12. 2 / 12-3 / 12, 3 / 12-4 / 12 and so on.

[0068] After the driving information after frame supplementation is corrected by the above method, the corrected driving information replaces the original driving information after frame supplementation, so that the real-time traffic flow information can be determined later by the corrected driving information.

[0069] Step S103, constructing a vehicle model according to the basic information of the target vehicle, and determining the real-time traffic flow information of the monitoring area through the vehicle model, the driving information after the frame supplementation and the pre-constructed regional model of the monitoring area, and tracking the preset key vehicles according to the real-time traffic flow information.

[0070] In this embodiment, the vehicle model can be a universal unit model, which will be visualized according to the incoming vehicle information. It has basic data and basic methods that can operate normally in the regional model, and different target vehicles need to be instantiated through the incoming vehicle basic information.

[0071] After determining the vehicle model, each vehicle model is placed in the pre-built regional model, and then the traffic engine is used to render the driving information into real-time traffic in the monitoring area and display it on the screen. Finally, the visible real-time dynamic traffic is used to analyze the traffic situation and track key vehicles, such as hazardous chemicals vehicles, incident vehicles, and suspect vehicles in real time.

[0072] For the regional model of the monitoring area, the design drawings of the monitoring area may be obtained first, and the digitized physical properties of the monitoring area, such as length, width, height, curvature, etc., may be determined according to the design drawings;

[0073] The design drawings and physical properties are input into a predetermined modeling software for three-dimensional static modeling to obtain a regional model of the monitoring area.

[0074] Compared with the traditional method of positioning and tracking by switching cameras, this method greatly alleviates the embarrassing situation of people chasing the camera and the camera chasing the car. Just click the mouse to lock the target vehicle, and the picture on the screen will automatically lock to the target vehicle's perspective. Its lane change, steering, acceleration and deceleration, and the conditions of the vehicles around it can all appear clearly on the screen, and when it violates traffic regulations or an accident occurs, it can also automatically provide corresponding warnings.

[0075] So far, completed Figure 1 The process shown.

[0076] In an embodiment of the present application, for key areas that need to be monitored, the basic information of the vehicle is first obtained through the first camera at the entrance of the area, and a vehicle model is constructed based on the basic information; after the vehicle enters the area, the driving information of the vehicle is obtained through the second camera in the area; then, after the driving information is supplemented and corrected, the real-time traffic information of the area is generated through the above-mentioned vehicle model, the supplemented and corrected driving information, and the pre-constructed regional model of the area, and the area is monitored based on the real-time traffic information, so as to track the key vehicles in the area. The tunnel visualization vehicle tracking method provided by the present invention is based on the pile meter number. Compared with the dynamic positioning through the existing GPS or the vehicle-mounted GPS positioning, the present application accurately locks the positioning information to the meter level / second level through the pile meter number information.

[0077] like Figure 2 As shown, the present application also provides a vehicle tracking device based on stake meter number positioning, which is applied to an intelligent transportation system, and the device includes:

[0078] The initial information acquisition unit 201 is used to acquire basic information of the target vehicle through a first camera at the entrance of the monitoring area, and then record and measure the speed of the target vehicle in its entirety through a second camera in the monitoring area to obtain initial driving information of the target vehicle, wherein the initial driving information includes the driving speed and the pile meter number information of the target vehicle, and the pile meter number information is used to characterize the position of the target vehicle in the monitoring area;

[0079] An information frame supplementation unit 202, configured to supplement the initial driving information to obtain supplemented driving information;

[0080] The vehicle tracking unit 203 is used to build a vehicle model based on the basic information of the target vehicle, and determine the real-time traffic information of the monitoring area through the vehicle model, the driving information after the frame supplement and the pre-built regional model of the monitoring area, and track the preset key vehicles according to the real-time traffic information.

[0081] Optionally, the step of supplementing the initial driving information in the final information acquisition unit includes:

[0082] The initial driving information is stored in a preset buffer pool, and the initial driving information in the buffer pool is updated at a speed of N frames per second using the initial driving information acquired in real time;

[0083] According to the vehicle driving speed and the pile meter number information in the initial driving information in the buffer pool, the frame rate generator performs frame supplementation at a speed of MN frames per second to obtain the driving information after frame supplementation at M frames per second.

[0084] Optionally, after obtaining the frame-filled driving information, the device further includes:

[0085] The information correction unit 204 is used to correct the frame-filled driving information by using the pile meter number information to obtain the corrected driving information. The specific correction method is:

[0086] For the initial driving information T1: [v1, s1], T2: [v2, s2] of two adjacent frames, and the driving information of the supplementary frame between T1 and T2, calculate the distance ds of the target vehicle within the frame time from T1 to T2, and correct the pile meter number information of the driving information of the supplementary frame between T1 and T2 to s2-(s1+ds), where s is the pile meter number information and v is the driving speed;

[0087] The frame-supplemented driving information is updated using the corrected driving information.

[0088] Optionally, the first camera in the initial information acquisition unit is a bayonet camera, and the second camera is a radar camera.

[0089] Optionally, the method for constructing the regional model of the monitoring area in the vehicle tracking unit includes:

[0090] Obtaining a design drawing of the monitoring area, and determining the digitized physical properties of the monitoring area according to the design drawing;

[0091] The design drawings and physical properties are input into a predetermined modeling software for three-dimensional static modeling to obtain a regional model of the monitoring area.

[0092] The above embodiment of the present invention provides a vehicle tracking method based on stake and meter number positioning, and based on this method provides a vehicle tracking device based on stake and meter number positioning. Through the above method and device, the vehicle positioning monitoring of key monitoring areas is made more accurate, so that more accurate corresponding decisions can be made when emergencies occur.

[0093] This embodiment also discloses a computer device, such as Figure 3 As shown, the computer device includes a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement any of the above-mentioned vehicle tracking methods based on stake number positioning.

[0094] In addition, in the implementation of the vehicle tracking device based on the stake meter number positioning in the above-mentioned example, the logical division of each program module is only an example. In actual application, the above-mentioned functions can be assigned to different program modules as needed, for example, for the configuration requirements of the corresponding hardware or the convenience of software implementation. That is, the internal structure of the vehicle tracking device based on the stake meter number positioning is divided into different program modules to complete all or part of the functions described above.

[0095] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A vehicle tracking method based on stake number positioning, characterized in that: Applied to an intelligent transportation system, the method comprises: The basic information of the target vehicle is obtained by a first camera at the entrance of the monitoring area, and then the target vehicle is recorded and the speed is measured by a second camera in the monitoring area to obtain the initial driving information of the target vehicle, wherein the initial driving information includes the driving speed and the pole meter number information of the target vehicle, and the pole meter number information is used to characterize the position of the target vehicle in the monitoring area; Performing frame interpolation on the initial driving information to obtain frame-interpolated driving information; A vehicle model is constructed based on the basic information of the target vehicle, and the real-time traffic flow information of the monitoring area is determined through the vehicle model, the driving information after the frame supplementation, and the pre-constructed regional model of the monitoring area, and the preset key vehicles are tracked based on the real-time traffic flow information.

2. The method according to claim 1, characterized in that The interpolating frame of the initial driving information comprises: The initial driving information is stored in a preset buffer pool, and the initial driving information in the buffer pool is updated at a speed of N frames per second using the initial driving information acquired in real time; According to the vehicle driving speed and the pile meter number information in the initial driving information in the buffer pool, the frame rate generator performs frame supplementation at a speed of MN frames per second to obtain the driving information after frame supplementation at M frames per second.

3. The method according to claim 1, characterized in that After obtaining the frame-filled driving information, the method further includes: The driving information after the frame supplement is corrected by the pile meter number information to obtain the corrected driving information. The specific correction method is: For the initial driving information T1: [v1, s1], T2: [v2, s2] of two adjacent frames, and the driving information of the supplementary frame between T1 and T2, calculate the distance ds of the target vehicle within the frame time from T1 to T2, and correct the pile meter number information of the driving information of the supplementary frame between T1 and T2 to s2-(s1+ds), where s is the pile meter number information and v is the driving speed; The frame-supplemented driving information is updated using the corrected driving information.

4. The method according to claim 1, characterized in that: The first camera is a bayonet camera, and the second camera is a radar camera.

5. The method according to claim 1, characterized in that The method for constructing the regional model of the monitoring area includes: Obtaining a design drawing of the monitoring area, and determining the digitized physical properties of the monitoring area according to the design drawing; The design drawings and physical properties are input into a predetermined modeling software for three-dimensional static modeling to obtain a regional model of the monitoring area.

6. A vehicle tracking device based on stake number positioning, characterized in that: Applied to an intelligent transportation system, the device comprises: An initial information acquisition unit is used to acquire basic information of a target vehicle through a first camera at the entrance of a monitoring area, and then to record and measure the speed of the target vehicle in its entirety through a second camera in the monitoring area, so as to obtain initial driving information of the target vehicle, wherein the initial driving information includes the driving speed and the pole meter number information of the target vehicle, and the pole meter number information is used to characterize the position of the target vehicle in the monitoring area; An information frame supplementation unit, used for supplementing the initial driving information to obtain supplemented driving information; The vehicle tracking unit is used to construct a vehicle model based on the basic information of the target vehicle, and determine the real-time traffic information of the monitoring area through the vehicle model, the driving information after the frame supplement and the pre-constructed regional model of the monitoring area, and track the preset key vehicles according to the real-time traffic information.

7. The device according to claim 6, characterized in that The final information acquisition unit supplements the initial driving information with frames, including: The initial driving information is stored in a preset buffer pool, and the initial driving information in the buffer pool is updated at a speed of N frames per second using the initial driving information acquired in real time; According to the vehicle driving speed and the pile meter number information in the initial driving information in the buffer pool, the frame rate generator performs frame supplementation at a speed of MN frames per second to obtain the driving information after frame supplementation at M frames per second.

8. The device according to claim 6, characterized in that After obtaining the frame-filled driving information, the device further includes: The information correction unit is used to correct the driving information after the frame supplementation by using the pile meter number information to obtain the corrected driving information. The specific correction method is: For the initial driving information T1: [v1, s1], T2: [v2, s2] of two adjacent frames, and the driving information of the supplementary frame between T1 and T2, calculate the distance ds of the target vehicle within the frame time from T1 to T2, and correct the pile meter number information of the driving information of the supplementary frame between T1 and T2 to s2-(s1+ds), where s is the pile meter number information and v is the driving speed; The frame-supplemented driving information is updated using the corrected driving information.

9. The device according to claim 6, characterized in that The first camera in the initial information acquisition unit is a bayonet camera, and the second camera is a radar camera.

10. The device according to claim 6, characterized in that The method for constructing the regional model of the monitoring area in the vehicle tracking unit includes: Obtaining a design drawing of the monitoring area, and determining the digitized physical properties of the monitoring area according to the design drawing; The design drawings and physical properties are input into a predetermined modeling software for three-dimensional static modeling to obtain a regional model of the monitoring area.

Images