Method and system for tracking vehicles across mirrors in a park

Abstract

The present invention provides a method and system for cross-mirror tracking of vehicles in a park, and the method performs the following steps: Step 1: Use the current camera to detect the surveillance video of the park, and extract the target vehicle feature information of the target tracking vehicle from the surveillance video; Step 2: Use the current camera to perform single-mirror tracking on the target tracking vehicle until it disappears from the lens of the current camera; Step 3: When the target tracking vehicle appears in the new camera, continue to perform single-mirror tracking on the target tracking vehicle, and cycle in this manner until the target tracking vehicle leaves the park. According to the method of the present invention, the current camera is used to perform single-mirror tracking on the target tracking vehicle until it disappears from the lens of the current camera, and then the new camera is used to continue to perform single-mirror tracking on the target tracking vehicle until the target tracking vehicle leaves the park. Therefore, the tracking of vehicles in the park can be achieved through the systematic work between multiple cameras.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle tracking, and in particular to a method and system for cross-mirror vehicle tracking in a park. Background Art

[0002] The current method of cross-camera tracking of vehicles in the park is mainly that the front-end device transmits the identified vehicle structured data to the central server. However, the disadvantage of this method is that each camera works independently and cannot work systematically. Summary of the invention

[0003] The present invention provides a method and system for tracking vehicles across cameras in a park, which are used to solve the problem that each camera cannot work systematically.

[0004] The present invention provides a method for tracking vehicles across mirrors in a park, the method performing the following steps:

[0005] Step 1: Use the current camera to detect the surveillance video of the park, and extract the target vehicle feature information of the target tracking vehicle from the surveillance video;

[0006] Step 2: Using the current camera to perform single-lens tracking on the target tracking vehicle until it disappears from the lens of the current camera;

[0007] Step 3: When the target tracking vehicle appears in the new camera, continue to implement single-lens tracking on the target tracking vehicle, and cycle in this way until the target tracking vehicle leaves the park.

[0008] Furthermore, the method further performs the following steps:

[0009] Step 4: Generate a historical trajectory of the target tracking vehicle based on monitoring videos captured by multiple cameras that perform single-lens tracking on the target tracking vehicle before the target tracking vehicle leaves the park.

[0010] Further, in step 4, the historical trajectory of the target tracking vehicle is generated according to the surveillance videos shot by multiple cameras that perform single-lens tracking on the target tracking vehicle before the target tracking vehicle leaves the park, and the following steps are performed:

[0011] Step A1: using formula (1) to obtain the instantaneous speed of the target tracking vehicle according to the position coordinate point of the target tracking vehicle in each frame image taken by the current camera;

[0012]

[0013] Where V irepresents the instantaneous speed of the target tracking vehicle in the i-th frame image; (X i ,Y i ) represents the position coordinate point of the target tracking vehicle in the i-th frame image; (X i-1 ,Y i-1 ) represents the position coordinate point of the target tracking vehicle in the i-1th frame image; T represents the time taken by the current camera to shoot each frame of image;

[0014] Step A2: using formula (2) to obtain the inclination angle of the line from the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image;

[0015]

[0016] where θ i It represents the inclination angle of the line connecting the target tracking vehicle from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image. When θ i ≥0 means rotating counterclockwise along the positive half axis of the X axis by θ i Angle, when θ i When <0, it means rotating θ clockwise along the positive semi-axis direction of the X axis i angle;

[0017] Step A3: using formula (3) according to the inclination angle of the line connecting the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image and the position coordinate point of the target tracking vehicle in the i frame image, obtain the line equation connecting the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image;

[0018] f(x) = tanθ(xX i )-Y i (3)

[0019] Wherein f(x) represents the ordinate function value of the line equation of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image; x represents the abscissa independent variable of the line equation of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image;

[0020] Step A4: connect the position coordinate point of the target tracking vehicle from the i-1th frame image to the position coordinate point of the i-th frame image according to formula (3), and mark the instantaneous speed of the position coordinate point of the i-th frame image at the position coordinate point of the i-th frame image of the target tracking vehicle;

[0021] Step A5: Repeat steps A1 to A4 for each frame of image captured by all cameras to complete the drawing of the historical trajectory of the target tracking vehicle.

[0022] Further, the step 1: using the current camera to detect the surveillance video of the park, and extracting the target vehicle feature information of the target tracking vehicle from the surveillance video, performs the following steps:

[0023] Step S11: Detecting a target tracking vehicle in a monitoring video shot by a camera among the multiple cameras in the park, and using the camera that detects the target tracking vehicle as the current camera;

[0024] Step S12: extracting target tracking vehicle information from the detected target tracking vehicle.

[0025] Furthermore, the target vehicle characteristic information includes: at least one of vehicle license plate, brand, color, vehicle type, and vehicle speed.

[0026] Furthermore, in step S11, the target tracking vehicle is detected by FasterRCNN, YOLO or SSD deep learning algorithm.

[0027] Furthermore, in step 3, when the target tracking vehicle appears in the new camera, the target tracking vehicle continues to be tracked by a single lens, and the following steps are performed:

[0028] Step S31: When a vehicle reappears in the new camera, the vehicle feature information in the current picture taken by the new camera is compared with the target vehicle feature information to determine whether the vehicle in the new camera matches the target tracking vehicle;

[0029] Step S32: If a match is found, the new camera is used to continue single-lens tracking of the target tracking vehicle;

[0030] Step S33: If there is no match, steps S31 and S32 are repeated until a vehicle matching the target tracking vehicle appears in the new camera, and the new camera is used to continue single-lens tracking of the target tracking vehicle.

[0031] A method for cross-mirror tracking of vehicles in a park provided by an embodiment of the present invention has the following beneficial effects: a current camera is used to perform single-mirror tracking on a target tracking vehicle until it disappears from the lens of the current camera, and then a new camera is used to continue to perform single-mirror tracking on the target tracking vehicle until the target tracking vehicle leaves the park. Therefore, the tracking of vehicles in the park can be achieved through systematic work between multiple cameras.

[0032] The present invention also provides a vehicle cross-mirror tracking system in a park, comprising:

[0033] A target tracking vehicle detection module is used to detect the surveillance video of the park using the current camera and extract the target vehicle feature information of the target tracking vehicle from the surveillance video;

[0034] A first single-lens tracking module, used to perform single-lens tracking on the target tracking vehicle using the current camera until the target tracking vehicle disappears from the lens of the current camera;

[0035] The cyclic single-mirror tracking module is used to continue single-mirror tracking of the target tracking vehicle when the target tracking vehicle appears in a new camera, and to cycle in this way until the target tracking vehicle leaves the park.

[0036] Furthermore, the cross-mirror tracking system for vehicles within the park also includes: a historical trajectory generation module, which is used to generate the historical trajectory of the target tracking vehicle based on the surveillance videos taken by multiple cameras that perform single-mirror tracking on the target tracking vehicle before the target tracking vehicle leaves the park.

[0037] Furthermore, the target tracking vehicle detection module includes:

[0038] A target tracking vehicle detection unit, configured to detect a target tracking vehicle in a surveillance video captured by a camera among the plurality of cameras in the park, and use the camera that detects the target tracking vehicle as a current camera;

[0039] The vehicle information extraction unit is used to extract the target tracking vehicle information from the detected target tracking vehicle.

[0040] A cross-mirror tracking system for vehicles in a park provided by an embodiment of the present invention has the following beneficial effects: a first single-mirror tracking module uses a current camera to perform single-mirror tracking on a target tracking vehicle until the vehicle disappears from the lens of the current camera, and then a cyclic single-mirror tracking module uses a new camera to continue to perform single-mirror tracking on the target tracking vehicle until the target tracking vehicle leaves the park. Therefore, the tracking of vehicles in the park can be achieved through the systematic work between multiple cameras.

[0041] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0042] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0044] Figure 1 A schematic diagram of a flow chart of a method for tracking vehicles across mirrors in a park according to an embodiment of the present invention;

[0045] Figure 2 The block diagram of a cross-mirror tracking system for vehicles in a park according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0047] The embodiment of the present invention provides a method for tracking vehicles across mirrors in a park, such as Figure 1 As shown, the method performs the following steps:

[0048] Step 1: Use the current camera to detect the surveillance video of the park, and extract the target vehicle feature information of the target tracking vehicle from the surveillance video;

[0049] Step 2: Using the current camera to perform single-lens tracking on the target tracking vehicle until it disappears from the lens of the current camera;

[0050] Step 3: When the target tracking vehicle appears in the new camera, continue to implement single-lens tracking on the target tracking vehicle, and cycle in this way until the target tracking vehicle leaves the park.

[0051] The working principle of the above technical solution is: the present invention adopts multiple cameras to work together in a systematic manner to realize the tracking of the target tracking vehicle in the entire park. Specifically, first, the current camera is used to detect the surveillance video of the park, and the target vehicle feature information of the target tracking vehicle is extracted from the surveillance video; then, the current camera is used to perform single-lens tracking on the target tracking vehicle until it disappears from the lens of the current camera; finally, when the target tracking vehicle appears in the new camera, the single-lens tracking of the target tracking vehicle continues, and this cycle is repeated until the target tracking vehicle leaves the park.

[0052] The single-lens tracking means that only the current camera is used to shoot the target tracking vehicle to track the target tracking vehicle until the target tracking vehicle disappears from the lens of the current camera. It should be noted that the park can be a logistics park, a campus, an office area, a residential area, etc.

[0053] The beneficial effect of the above technical solution is: using the current camera to perform single-lens tracking on the target tracking vehicle until it disappears from the lens of the current camera, and then using the new camera to continue single-lens tracking on the target tracking vehicle until the target tracking vehicle leaves the park. Therefore, the tracking of vehicles in the park can be achieved through the systematic work between multiple cameras.

[0054] In one embodiment, the method further performs the following steps:

[0055] Step 4: Generate a historical trajectory of the target tracking vehicle based on monitoring videos captured by multiple cameras that perform single-lens tracking on the target tracking vehicle before the target tracking vehicle leaves the park.

[0056] The working principle of the above technical solution is: based on the monitoring videos shot by multiple cameras that perform single-lens tracking of the target tracking vehicle, a historical trajectory of the target tracking vehicle is generated.

[0057] The beneficial effect of the above technical solution is: generating the historical trajectory of the target tracking vehicle, which is convenient for tracking the target tracking vehicle throughout the whole process.

[0058] In one embodiment, the step 1: using the current camera to detect the surveillance video of the park, and extracting the target vehicle feature information of the target tracking vehicle from the surveillance video, the following steps are performed:

[0059] Step S11: Detecting a target tracking vehicle in a monitoring video shot by a camera among the multiple cameras in the park, and using the camera that detects the target tracking vehicle as the current camera;

[0060] Step S12: extracting target tracking vehicle information from the detected target tracking vehicle.

[0061] The working principle of the above technical solution is: the target vehicle characteristic information includes: at least one of the vehicle license plate, brand, color, vehicle type, and vehicle speed.

[0062] In step S11, the target tracking vehicle is detected by using FasterRCNN, YOLO or SSD deep learning algorithm.

[0063] The beneficial effect of the above technical solution is: providing specific steps for using the current camera to detect the surveillance video of the park and extracting the target vehicle feature information of the target tracking vehicle from the surveillance video.

[0064] In one embodiment, in step 3: when the target tracking vehicle appears in the new camera, continue to perform single-lens tracking on the target tracking vehicle, and perform the following steps:

[0065] Step S31: When a vehicle reappears in the new camera, the vehicle feature information in the current picture taken by the new camera is compared with the target vehicle feature information to determine whether the vehicle in the new camera matches the target tracking vehicle;

[0066] Step S32: If a match is found, the new camera is used to continue single-lens tracking of the target tracking vehicle;

[0067] Step S33: If there is no match, steps S31 and S32 are repeated until a vehicle matching the target tracking vehicle appears in the new camera, and the new camera is used to continue single-lens tracking of the target tracking vehicle.

[0068] The working principle of the above technical solution is: when a vehicle reappears in a new camera, the vehicle feature information in the current picture taken by the new camera is compared with the target vehicle feature information detected previously to determine whether the vehicle appearing in the new camera matches the target tracking vehicle; if they match, the vehicle appearing in the new camera is considered to be the target tracking vehicle, and the new camera is used to continue to implement single-lens tracking of the target tracking vehicle; if they do not match, the vehicle appearing in the new camera is considered not to be the target tracking vehicle, and the search for the vehicle in other cameras continues, and it is determined whether it matches the target tracking vehicle, until a vehicle matching the target tracking vehicle appears in the new camera, and the new camera is used to continue to implement single-lens tracking of the target tracking vehicle.

[0069] The beneficial effect of the above technical solution is: providing specific steps for continuing to implement single-lens tracking on the target tracking vehicle when the target tracking vehicle appears in a new camera.

[0070] In one embodiment, the step 4: generating a historical trajectory of the target tracking vehicle based on the surveillance videos captured by multiple cameras that perform single-lens tracking of the target tracking vehicle before the target tracking vehicle leaves the park, and performing the following steps:

[0071] Step A1: using formula (1) to obtain the instantaneous speed of the target tracking vehicle according to the position coordinate point of the target tracking vehicle in each frame image taken by the current camera;

[0072]

[0073] Where V i represents the instantaneous speed of the target tracking vehicle in the i-th frame image; (X i ,Y i ) represents the position coordinate point of the target tracking vehicle in the i-th frame image; (Xi-1 ,Y i-1 ) represents the position coordinate point of the target tracking vehicle in the i-1th frame image; T represents the time taken by the current camera to shoot each frame of image;

[0074] Step A2: using formula (2) to obtain the inclination angle of the line from the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image;

[0075]

[0076] where θ i It represents the inclination angle of the line connecting the target tracking vehicle from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image. When θ i ≥0 means rotating counterclockwise along the positive half axis of the X axis by θ i Angle, when θ i When <0, it means rotating θ clockwise along the positive semi-axis direction of the X axis i angle;

[0077] Step A3: using formula (3) according to the inclination angle of the line connecting the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image and the position coordinate point of the target tracking vehicle in the i frame image, obtain the line equation connecting the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image;

[0078] f(x) = tanθ(xX i )-Y i (3)

[0079] Wherein f(x) represents the ordinate function value of the line equation of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image; x represents the abscissa independent variable of the line equation of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image;

[0080] Step A4: connect the position coordinate point of the target tracking vehicle from the i-1th frame image to the position coordinate point of the i-th frame image according to formula (3), and mark the instantaneous speed of the position coordinate point of the i-th frame image at the position coordinate point of the i-th frame image of the target tracking vehicle;

[0081] Step A5: Repeat steps A1 to A4 for each frame of image captured by all cameras to complete the drawing of the historical trajectory of the target tracking vehicle.

[0082] The beneficial effect of the above technical solution is: using formula (1) in step A1 to obtain the instantaneous speed of the target tracking vehicle, thereby obtaining the speed of each frame in the historical trajectory of the target tracking vehicle; then using formula (2) in step A2 to obtain the inclination angle of the line connecting the target tracking vehicle from the position coordinate point of the i-1 frame to the position coordinate point of the i-1 frame, the purpose is to obtain the straight line equation for drawing the line connecting the target tracking vehicle from the position coordinate point of the i-1 frame to the position coordinate point of the i-1 frame according to the inclination angle; then using formula (3) in step A3 to obtain the equation of the line connecting the target tracking vehicle from the position coordinate point of the i-1 frame to the position coordinate point of the i-1 frame, thereby completing the drawing of the historical trajectory of the target tracking vehicle according to the equation and the instantaneous speed of the target tracking vehicle; thereby making the drawn trajectory more detailed and specific, and reflecting the historical trajectory more accurate and true.

[0083] like Figure 2 As shown, an embodiment of the present invention provides a vehicle cross-mirror tracking system in a park, comprising:

[0084] The target tracking vehicle detection module 201 is used to detect the monitoring video of the park using the current camera, and extract the target vehicle feature information of the target tracking vehicle from the monitoring video;

[0085] A first single-lens tracking module 202, configured to use a current camera to perform single-lens tracking on the target tracking vehicle until the target tracking vehicle disappears from the lens of the current camera;

[0086] The cyclic single-mirror tracking module 203 is used to continue single-mirror tracking of the target tracking vehicle when the target tracking vehicle appears in a new camera, and to cycle in this way until the target tracking vehicle leaves the park.

[0087] The working principle of the above technical solution is as follows: the present invention adopts multiple cameras to work together in a systematic manner to realize the tracking of the target tracking vehicle in the entire park. Specifically, the target tracking vehicle detection module 201 uses the current camera to detect the surveillance video of the park, and extracts the target vehicle feature information of the target tracking vehicle from the surveillance video; the first single-mirror tracking module 202 uses the current camera to perform single-mirror tracking on the target tracking vehicle until it disappears from the lens of the current camera; the cyclic single-mirror tracking module 203 continues to perform single-mirror tracking on the target tracking vehicle when the target tracking vehicle appears in a new camera, and cycles in this way until the target tracking vehicle leaves the park.

[0088] The beneficial effect of the above technical solution is: the first single-mirror tracking module uses the current camera to perform single-mirror tracking on the target tracking vehicle until it disappears from the lens of the current camera, and the cyclic single-mirror tracking module uses the new camera to continue to perform single-mirror tracking on the target tracking vehicle until the target tracking vehicle leaves the park. Therefore, the tracking of vehicles in the park can be achieved through the systematic work between multiple cameras.

[0089] In one embodiment, the cross-mirror tracking system for vehicles within the park also includes: a historical trajectory generation module 204, which is used to generate the historical trajectory of the target tracking vehicle based on the surveillance videos taken by multiple cameras that perform single-mirror tracking on the target tracking vehicle before the target tracking vehicle leaves the park.

[0090] The working principle of the above technical solution is as follows: the historical trajectory generation module 204 generates the historical trajectory of the target tracking vehicle based on the monitoring videos shot by multiple cameras that perform single-lens tracking on the target tracking vehicle.

[0091] The beneficial effect of the above technical solution is that with the help of the historical trajectory generation module, the historical trajectory of the target tracking vehicle can be generated, which is convenient for tracking the target tracking vehicle throughout the entire process.

[0092] In one embodiment, the target tracking vehicle detection module 201 includes:

[0093] A target tracking vehicle detection unit, configured to detect a target tracking vehicle in a surveillance video captured by a camera among the plurality of cameras in the park, and use the camera that detects the target tracking vehicle as a current camera;

[0094] The vehicle information extraction unit is used to extract the target tracking vehicle information from the detected target tracking vehicle.

[0095] The working principle of the above technical solution is: the target vehicle characteristic information includes: at least one of the vehicle license plate, brand, color, vehicle type, and vehicle speed.

[0096] The target tracking vehicle detection unit detects the target tracking vehicle through FasterRCNN, YOLO or SSD deep learning algorithm.

[0097] The beneficial effect of the above technical solution is that with the help of the target tracking vehicle detection unit and the vehicle information extraction unit, the current camera can be used to detect the target tracking vehicle in the surveillance video of the park and extract the target vehicle feature information.

[0098] In one embodiment, the cyclic single-mirror tracking module 203 includes:

[0099] A vehicle feature information comparison unit is used to compare the vehicle feature information in the current picture taken by the new camera with the target vehicle feature information when the vehicle reappears in the new camera, so as to determine whether the vehicle in the new camera matches the target tracking vehicle;

[0100] A new camera single-lens tracking unit, configured to, when the vehicle in the new camera matches the target tracking vehicle, continue to perform single-lens tracking on the target tracking vehicle using the new camera;

[0101] The matching repetition execution unit is used to repeatedly use the vehicle feature information comparison unit and the second single-mirror tracking unit to find a vehicle matching the target tracking vehicle in the new camera when the vehicle in the new camera does not match the target tracking vehicle, and continue to implement single-mirror tracking on the target tracking vehicle using the new camera.

[0102] The working principle of the above technical solution is: when a vehicle reappears in the new camera, the vehicle feature information comparison unit compares the vehicle feature information in the current picture taken by the new camera with the target vehicle feature information detected previously, so as to determine whether the vehicle appearing in the new camera matches the target tracking vehicle; if they match, it is considered that the vehicle appearing in the new camera is the target tracking vehicle, and the new camera single-lens tracking unit continues to implement single-lens tracking of the target tracking vehicle using the new camera; if they do not match, it is considered that the vehicle appearing in the new camera is not the target tracking vehicle, and the matching repetition execution unit continues to search for vehicles in other cameras and determines whether they match the target tracking vehicle, until a vehicle matching the target tracking vehicle appears in the new camera, and the new camera continues to implement single-lens tracking of the target tracking vehicle.

[0103] The beneficial effect of the above technical solution is: with the help of the vehicle feature information comparison unit, the new camera single-mirror tracking unit and the matching repeated execution unit, the single-mirror tracking of the target tracking vehicle can continue to be implemented when the target tracking vehicle appears in the new camera.

[0104] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for tracking vehicles across cameras in a park, characterized in that: The method performs the following steps: Step 1: Use the current camera to detect the surveillance video of the park, and extract the target vehicle feature information of the target tracking vehicle from the surveillance video; Step 2: Using the current camera to perform single-lens tracking on the target tracking vehicle until it disappears from the lens of the current camera; Step 3: When the target tracking vehicle appears in the new camera, continue to implement single-lens tracking on the target tracking vehicle, and cycle in this way until the target tracking vehicle leaves the park; Step 4: Generate a historical trajectory of the target tracking vehicle based on surveillance videos captured by multiple cameras that perform single-lens tracking on the target tracking vehicle before the target tracking vehicle leaves the park; Wherein, the step 4: before the target tracking vehicle leaves the park, the historical trajectory of the target tracking vehicle is generated according to the monitoring videos shot by multiple cameras that perform single-lens tracking on the target tracking vehicle, and the following steps are performed: Step A1: using formula (1) to obtain the instantaneous speed of the target tracking vehicle according to the position coordinate point of the target tracking vehicle in each frame image taken by the current camera; Where V i represents the instantaneous speed of the target tracking vehicle in the i-th frame image; (X i ,Y i ) represents the position coordinate point of the target tracking vehicle in the i-th frame image; (X i-1 ,Y i-1 ) represents the position coordinate point of the target tracking vehicle in the i-1th frame image; T represents the time taken by the current camera to shoot each frame of image; Step A2: using formula (2) to obtain the inclination angle of the line from the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image; where θ i It represents the inclination angle of the line connecting the target tracking vehicle from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image. When θ i ≥0 means rotating counterclockwise along the positive half axis of the X axis by θ i | angle, when θ i When <0, it means rotating θ clockwise along the positive semi-axis direction of the X axis i | Angle; Step A3: using formula (3) according to the inclination angle of the line connecting the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image and the position coordinate point of the target tracking vehicle in the i frame image, obtain the line equation connecting the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image; f(x)=tanθ(x-X i )-Y i (3) Wherein f(x) represents the ordinate function value of the line equation of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image; x represents the abscissa independent variable of the line equation of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image; Step A4: connect the position coordinate point of the target tracking vehicle from the i-1th frame image to the position coordinate point of the i-th frame image according to formula (3), and mark the instantaneous speed of the position coordinate point of the i-th frame image at the position coordinate point of the i-th frame image of the target tracking vehicle; Step A5: Repeat steps A1 to A4 for each frame of image captured by all cameras to complete the drawing of the historical trajectory of the target tracking vehicle.

2. The method according to claim 1, characterized in that Step 1: Use the current camera to detect the surveillance video of the park, and extract the target vehicle feature information of the target tracking vehicle from the surveillance video, and perform the following steps: Step S11: Detecting a target tracking vehicle in a monitoring video shot by a camera among the multiple cameras in the park, and using the camera that detects the target tracking vehicle as the current camera; Step S12: extracting target tracking vehicle information from the detected target tracking vehicle.

3. The method according to claim 2, characterized in that The target vehicle characteristic information includes: at least one of vehicle license plate, brand, color, vehicle type, and vehicle speed.

4. The method according to claim 2, characterized in that In step S11, the target tracking vehicle is detected by using FasterRCNN, YOLO or SSD deep learning algorithm.

5. The method according to claim 1, characterized in that Step 3: When the target tracking vehicle appears in the new camera, continue to implement single-lens tracking on the target tracking vehicle, and perform the following steps: Step S31: When a vehicle reappears in the new camera, the vehicle feature information in the current picture taken by the new camera is compared with the target vehicle feature information to determine whether the vehicle in the new camera matches the target tracking vehicle; Step S32: If a match is found, the new camera is used to continue single-lens tracking of the target tracking vehicle; Step S33: If there is no match, steps S31 and S32 are repeated until a vehicle matching the target tracking vehicle appears in the new camera, and the new camera is used to continue single-lens tracking of the target tracking vehicle.

6. A vehicle cross-mirror tracking system in a park, characterized in that: include: A target tracking vehicle detection module is used to detect the surveillance video of the park using the current camera and extract the target vehicle feature information of the target tracking vehicle from the surveillance video; A first single-lens tracking module, used to perform single-lens tracking on the target tracking vehicle using the current camera until the target tracking vehicle disappears from the lens of the current camera; A cyclic single-mirror tracking module, used for continuing to implement single-mirror tracking on the target tracking vehicle when the target tracking vehicle appears in a new camera, and cyclically performing the tracking in this manner until the target tracking vehicle leaves the park; The cross-mirror tracking system for vehicles in the park further includes: a historical trajectory generation module, which is used to generate a historical trajectory of the target tracking vehicle based on the monitoring videos captured by multiple cameras that perform single-mirror tracking on the target tracking vehicle before the target tracking vehicle leaves the park; The historical trajectory generation module is specifically used to generate the historical trajectory of the target tracking vehicle according to the surveillance videos shot by multiple cameras that perform single-lens tracking on the target tracking vehicle before the target tracking vehicle leaves the park, and perform the following steps: Step A1: using formula (1) to obtain the instantaneous speed of the target tracking vehicle according to the position coordinate point of the target tracking vehicle in each frame image taken by the current camera; Where V i represents the instantaneous speed of the target tracking vehicle in the i-th frame image; (X i ,Y i ) represents the position coordinate point of the target tracking vehicle in the i-th frame image; (X i-1 ,Y i-1 ) represents the position coordinate point of the target tracking vehicle in the i-1th frame image; T represents the time taken by the current camera to shoot each frame of image; Step A2: using formula (2) to obtain the inclination angle of the line from the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image; where θ i It represents the inclination angle of the line connecting the target tracking vehicle from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image. When θ i ≥0 means rotating counterclockwise along the positive half axis of the X axis by θ i | angle, when θ i When <0, it means rotating θ clockwise along the positive semi-axis direction of the X axis i | Angle; Step A3: using formula (3) according to the inclination angle of the line connecting the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image and the position coordinate point of the target tracking vehicle in the i frame image, obtain the line equation connecting the position coordinate point of the target tracking vehicle moving from the position coordinate point of the i-1 frame image to the position coordinate point of the i frame image; f(x)=tanθ(x-X i )-Y i (3) Wherein f(x) represents the ordinate function value of the line equation of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image; x represents the abscissa independent variable of the line equation of the target tracking vehicle moving from the position coordinate point of the i-1th frame image to the position coordinate point of the i-th frame image; Step A4: connect the position coordinate point of the target tracking vehicle from the i-1th frame image to the position coordinate point of the i-th frame image according to formula (3), and mark the instantaneous speed of the position coordinate point of the i-th frame image at the position coordinate point of the i-th frame image of the target tracking vehicle; Step A5: Repeat steps A1 to A4 for each frame of image captured by all cameras to complete the drawing of the historical trajectory of the target tracking vehicle.

7. The system according to claim 6, characterized in that The target tracking vehicle detection module includes: A target tracking vehicle detection unit, configured to detect a target tracking vehicle in a surveillance video captured by a camera among the plurality of cameras in the park, and use the camera that detects the target tracking vehicle as a current camera; The vehicle information extraction unit is used to extract the target tracking vehicle information from the detected target tracking vehicle.

Images