CN115937301A - Dual-camera calibration method and dual-camera positioning method - Google Patents

Abstract

The invention discloses a double camera calibration method and a double camera positioning method. Wherein, the dual-camera calibration method includes the steps of: obtaining a detection event; controlling the tracking camera to capture the target object using AI visual detection technology according to the detection event; determining the key point of positioning of the tracking camera according to the target object captured by the tracking camera; According to the detection event, use AI visual detection technology to capture the target object in the video shot by the panoramic camera; determine the positioning key point of the panoramic camera according to the target object of the panoramic camera; associate the positioning key point of the panoramic camera with the positioning key point of the tracking camera. This method replaces the manual calibration position with AI detection technology, which reduces cumbersome operations and greatly reduces the workload of on-site commissioning personnel. With the help of the stability of the machine, it reduces the measurement error caused by human factors and ensures the accuracy of positioning. accuracy.

Description

Dual-camera calibration method and dual-camera positioning method

technical field

The present invention relates to the technical field of video image processing, and more specifically, to a dual-camera calibration method, a dual-camera positioning method, a device, a device, and a storage medium.

Background technique

In recent years, with the development of video shooting technology, the technology of using a panoramic camera and a tracking camera to track and shoot a target object is more and more widely used. However, due to the uncertain positional relationship between the panoramic camera and the tracking camera, even if there is a relatively definite relationship, the required mapping relationship cannot be precisely defined due to errors in installation and other aspects. Therefore, the associated debugging calibration is a panoramic and a necessary step for tracking camera systems.

In the existing debugging and associated control process of the panoramic camera and the tracking camera, for the calibration management of key points, the more commonly used method is manual calibration, that is, to confirm whether the shooting positions of the two cameras are consistent with the naked eye. When the positions are consistent, Associate the shooting coordinates of these two cameras. In this way, the accuracy cannot be fully guaranteed, and it will take a lot of time for the debugger to confirm the adjustment position, resulting in low work efficiency and poor positioning effect.

Contents of the invention

In order to overcome the defects of low efficiency and poor positioning effect of manual camera adjustment, the present invention provides a dual camera calibration method, device, equipment and storage medium. The technical scheme adopted in the present invention is as follows.

In a first aspect, the present invention provides a dual-camera calibration method, comprising the steps of:

Get detection events;

Control the tracking camera to capture the target object using AI visual detection technology according to the detection event;

Determine the positioning key points of the tracking camera according to the target object captured by the tracking camera;

According to the detection event, utilize AI visual detection technology to capture the target object in the video shot by the panoramic camera;

Determine the positioning key points of the panoramic camera according to the target object of the panoramic camera;

Associate the positioning key of the panorama camera with the positioning key of the tracking camera.

In one embodiment, the process of controlling the tracking camera to capture the target object using AI visual detection technology according to the detection event includes the steps of:

Obtain key point information to be located;

controlling the tracking camera to rotate the shooting initial position corresponding to the key point information to be located according to the key point information to be located;

Start the tracking camera to capture the target object using AI visual detection technology according to the detection event.

In one embodiment, the process of controlling the tracking camera to capture the target object using AI visual detection technology according to the detection event includes the steps of:

Get the preset shooting range;

Control the tracking camera to capture the target object in the preset shooting range by using AI visual detection technology according to the detection event.

In one embodiment, in the process of determining the positioning key point of the tracking camera according to the target object captured by the tracking camera, the coordinates of the positioning key point in the shooting of the tracking camera are determined according to the center position of the target object;

In the process of determining the positioning key point of the panoramic camera according to the target object of the panoramic camera, the coordinates of the positioning key point in the tracking camera shooting are determined according to the center position of the target.

In one implementation manner, the preset detection event is a head detection event.

In a second aspect, the present invention provides a positioning method for dual cameras, comprising the steps of:

Acquire the coordinate transformation relationship between the panoramic camera and the tracking camera, the coordinates of the target object in the panoramic camera, and the detection event of the target object, wherein the positioning key points in the coordinate transformation relationship are obtained through the dual cameras described in any of the preceding embodiments The calibration method is obtained;

Converting the coordinates of the target object in the panoramic camera into the coordinates of the target object in the tracking camera according to the coordinate conversion relationship;

According to the coordinates of the target object in the tracking camera, control the tracking camera to go to the corresponding position;

According to the detection event, the tracking camera is controlled to capture the target object using AI visual detection technology, and the position of the tracking camera is adjusted so that the target object is at the preset position of the shooting picture.

In one embodiment, further comprising the steps of:

The tracking camera is zoomed according to the preset ratio of the target object in the frame.

In a third aspect, the present invention provides a dual-camera calibration device, including:

An acquisition module, configured to acquire detection events;

The capture module is used to control the tracking camera to capture the target object using AI visual detection technology according to the detection event, and use the AI visual detection technology to capture the target object in the video shot by the panoramic camera;

Determining module, for determining the positioning key point of tracking camera according to the target object captured by tracking camera, determining the positioning key point of panoramic camera according to the target object of panoramic camera;

The association module is used for associating the positioning key points of the panoramic camera and the positioning key points of the tracking camera.

In a fourth aspect, the present invention provides a dual-camera positioning device, which is characterized in that it includes:

An acquisition module, configured to acquire the coordinate transformation relationship between the panoramic camera and the tracking camera, the coordinates of the target object in the panoramic camera, and the detection event of the target object, wherein the positioning key points in the coordinate transformation relationship are calibrated by the aforementioned dual cameras The device gets;

A conversion module, configured to convert the coordinates of the target object in the panoramic camera into the coordinates of the target object in the tracking camera according to the coordinate conversion relationship;

A control module, configured to control the tracking camera to go to a corresponding position according to the coordinates of the target object in the tracking camera;

The confirmation module is used to control the tracking camera to capture the target object by using the AI visual detection technology according to the detection event, and adjust the position of the tracking camera so that the target object is at the preset position of the shooting picture.

In a fifth aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, when the processor executes the program, the method of any of the above-mentioned embodiments is implemented .

In a sixth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the method in any one of the above-mentioned implementation modes is implemented.

In the present invention, the AI detection technology is used to capture the target object, and the key positioning points of the two cameras are obtained and associated according to the target object, and the artificial calibration position is replaced by the AI detection technology, which reduces cumbersome operations and greatly reduces the work of on-site debugging personnel. workload, and with the help of the stability of the machine, the measurement error caused by human factors is reduced to ensure the accuracy of positioning. In addition, the positioning process of the present invention is simple, the amount of calculation in the tracking and positioning process is small, the positioning is accurate, and the picture effect is good.

Description of drawings

Fig. 1 is a schematic flow chart of Embodiment 1 of the present invention.

FIG. 2 is a schematic display diagram of Embodiment 1 of the present invention.

Fig. 3 is a schematic flow chart of Embodiment 2 of the present invention.

Fig. 4 is a schematic diagram of the overall structure of Embodiment 3 of the present invention.

Fig. 5 is a schematic diagram of the overall structure of Embodiment 4 of the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

It should be noted that the term "first\second\..." involved in the embodiment of the present invention is only to distinguish similar objects, and does not represent a specific ordering of objects. Understandably, "first\second\ ..." are interchangeable in specific order or sequence where permissible. It should be understood that "first\second\..." distinctions are interchangeable under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein.

Embodiment one

Please refer to FIG. 1 . FIG. 1 is a schematic flowchart of a dual-camera calibration method provided by Embodiment 1 of the present invention. The method includes step S110 , step S120 , step S130 , step S140 , step S150 and step S160 . It should be noted that step S110, step S120, step S130, step S140, step S150 and step S160 are only reference numerals, which are used to clearly explain the corresponding relationship between the embodiment and the accompanying drawing 1, and do not mean that each step in this embodiment The sequence is limited.

Step S110, acquiring detection events;

Step S120, controlling the tracking camera to capture the target object using AI visual detection technology according to the detection event;

Step S130, determine the positioning key point of the tracking camera according to the target object captured by the tracking camera;

Step S140, according to the detection event, using AI visual detection technology to capture the target object in the video shot by the panoramic camera;

Step S150, determining key points for positioning the panoramic camera according to the target object of the panoramic camera;

Step S160, associating the positioning key points of the panoramic camera with the positioning key points of the tracking camera.

Positioning key point refers to the key point to be positioned currently, for example, if a rectangular area is to be positioned, select the four corners of the rectangle as key points. In this method, there is no restriction on the selected orientation of the positioning key point, as long as the selected point can be associated with the panoramic camera and the tracking camera, it can be used as a key point.

This method uses AI detection technology to replace the manual calibration position, so before AI detection, detection events must be obtained. The detection event is an event detected by AI, for example, standing detection, human body detection, human head detection, and the like. After the detection time is obtained, AI can be used to detect the corresponding event. When the corresponding event is detected, the corresponding target can be captured according to the event. For example, in the standing detection, the standing person is used as the target Object, in face detection, the face object is used as the target object. Therefore, in step S120, control the rotation of the tracking camera to detect events and capture the target object, and in step S140, capture the target object in the video shot by the panorama camera.

What needs to be explained here is that if there are two target objects in the current detection event, both target objects will be captured, so when using this method, it should be confirmed as much as possible that only one target object can be captured in the detection event .

Since the target object is in a relatively large range in the video screen, and the positioning key point is a relatively precise point, it is necessary to determine the point that can represent the target object according to the captured target object, and then determine according to the representative point. To locate the key point, for example, the most conventional is to select the center position of the target object as the point representing the target object, and use the point of the target object as the key point for positioning. In addition to the most conventional approach, those skilled in the art may also formulate rules on how to determine representative points through target objects according to actual conditions, and there is no limitation to the established rules in this implementation manner.

By detecting events with AI detection technology, the scope of the target object can be obtained more reliably and uniformly, and then the representative points can be obtained more reliably and uniformly according to the target object, so as to accurately determine the key points of positioning.

Through step S130 and step S150, after obtaining the positioning key points of the tracking camera and the panoramic camera respectively, the two positioning key points can be associated. After all the required positioning key points are associated through this method, the coordinate mapping relationship between the panoramic camera and the tracking camera can be established according to their respective coordinate systems.

In this method, the AI detection technology is used to capture the target object, and the key positioning points of the two cameras are obtained and associated with the target object, and the manual calibration position is replaced by the AI detection technology, which reduces cumbersome operations and greatly reduces the on-site commissioning personnel's time. workload, and with the help of the stability of the machine, the measurement error caused by human factors is reduced to ensure the accuracy of positioning.

In one implementation manner, the process of S120 includes: step S121, step S122, and step S123.

Step S121, obtaining key point information to be located;

Step S122, controlling the tracking camera to rotate the shooting initial position corresponding to the key point information to be located according to the key point information to be located;

Step S123, start the tracking camera to capture the target object by using AI visual detection technology according to the detection event.

As shown in Figure 2, Fig. 2 is carried out with four key points as an example, Fig. 2 is the picture taken by the panoramic camera, in the picture taken by the panoramic camera, four key point search areas are delineated (upper left, lower left, upper right, right Down). Generally speaking, when doing positioning key point association, the target object will be placed within the position range of one of the above four key point search areas every time. Similarly, the initial shooting positions of the tracking camera will be roughly determined for the four key point search areas.

In this embodiment, it is also necessary to obtain key point information to be located. Through this key point information, it can be known in which search area the key point to be located is currently located. If it is the upper left area, then the tracking camera is controlled to rotate the corresponding shooting of the upper left area At the initial position, it is convenient for the tracking camera to capture the target object more quickly.

What needs to be explained here is that this embodiment does not limit the type of information corresponding to the key information to be located, it may be coordinate information or other information. The initial position of the shooting is enough.

In one implementation manner, the process of S120 includes: step S123 and step S124.

Step S123, acquiring a preset shooting range;

Step S124, controlling the tracking camera to capture the target object in the preset shooting range by using AI visual detection technology according to the detection event.

As mentioned in the previous embodiment, each key point actually has an approximate position range, and target objects outside this position range cannot represent this key point and cannot be used. Therefore, in this embodiment, the shooting range is also preset for the tracking camera, so that the tracking camera can only capture the target object within the specified shooting range, reducing the possibility of erroneously capturing the target object.

In one embodiment, in the process of step S130, the coordinates of the positioning key point in the tracking camera shooting are determined according to the central position of the target object;

In the process of step S150, the coordinates of the positioning key point in the tracking camera shooting are determined according to the center position of the target.

This method is as mentioned above. The center point of the target object is selected as the point representing the target object, and then the representative point is used to determine the coordinates of the positioning key points in the shooting of the respective cameras. What needs to be explained here is that after the representative point is obtained, the representative point can be directly used as the positioning key point, or the positioning key point can be obtained based on the representative point through a certain calculation means.

In an implementation manner, the preset detection event is a head detection event.

The shape of the human head is relatively uniform, and the shape of the target object detected by the human head detection technology is relatively uniform, which reduces the measurement error caused by other reasons and ensures the accuracy of positioning.

Embodiment two

This patent also discloses a dual-camera positioning method. The positioning key points of the coordinate transformation relationship between the panoramic camera and the tracking camera used in the method are obtained by the dual-camera calibration method described in the first embodiment. The method includes step S210, step S220, step S230 and step S240. It should be noted that step S210, step S220, step S230 and step S240 are only reference numerals, which are used to clearly explain the corresponding relationship between the embodiment and FIG.

Step S210, obtain the coordinate transformation relationship between the panoramic camera and the tracking camera, the coordinates of the target object in the panoramic camera, and the detection event of the target object, wherein the positioning key points in the coordinate transformation relationship are obtained through the dual The camera calibration method is obtained;

Step S220, converting the coordinates of the target object in the panoramic camera into the coordinates of the target object in the tracking camera according to the coordinate conversion relationship;

Step S230, according to the coordinates of the target object in the tracking camera, control the tracking camera to go to the corresponding position;

Step S240, according to the detection event, control the tracking camera to capture the target object using AI visual detection technology, and adjust the position of the tracking camera so that the target object is at the preset position of the shooting picture.

Taking four-point positioning as an example, the positioning key points obtained in Embodiment 1 are a plane in three-dimensional space. If neither the panoramic camera nor the tracking camera is shooting at the target area, there will be Certain deviation. In actual scenes, it is common for the camera to shoot the target area from the side, so it is necessary to correct the close-up position of the target object.

After step S230, after the tracking camera turns to the corresponding position, in step S240, start the detection according to the detection event, such as standing detection, and move the target object, such as a standing person, to the preset position of the shooting picture, such as middle.

The positioning process of the method is simple, the calculation amount of the tracking and positioning process is small, the positioning is accurate, and the picture effect is good.

In an implementation manner, the dual camera positioning method further includes: Step S250.

Step S250, zooming the tracking camera according to the preset ratio of the target object in the frame.

In order to allow the tracking camera to capture a close-up picture of a suitable size, you can first preset a ratio of the preset target object in the screen. When the ratio of the target object in the screen is consistent with the preset ratio, it is considered a close-up The size of the target object in the picture is appropriate to present a better picture effect.

Embodiment Three

Corresponding to the method in Embodiment 1, as shown in FIG. 4 , the present invention also provides a dual-camera calibration device 4 , including: an acquisition module 410 , a capture module 420 , a determination module 430 and an association module 440 .

An acquisition module 410, configured to acquire a detection event;

The capture module 420 is used to control the tracking camera to capture the target object using AI visual detection technology according to the detection event, and use the AI visual detection technology to capture the target object in the video shot by the panoramic camera;

Determining module 430, is used for determining the positioning key point of tracking camera according to the target object captured by tracking camera, and determining the positioning key point of panoramic camera according to the target object of panoramic camera;

The associating module 440 is used for associating the positioning key points of the panoramic camera with the positioning key points of the tracking camera.

In one embodiment, the capture module is performing the process of controlling the tracking camera to capture the target object using AI visual detection technology according to the detection event, including the steps:

Obtain key point information to be located;

controlling the tracking camera to rotate the shooting initial position corresponding to the key point information to be located according to the key point information to be located;

Start the tracking camera to capture the target object using AI visual detection technology according to the detection event.

In one embodiment, the capture module is performing the process of controlling the tracking camera to capture the target object using AI visual detection technology according to the detection event, including the steps:

Get the preset shooting range;

Control the tracking camera to capture the target object in the preset shooting range by using AI visual detection technology according to the detection event.

In one embodiment, the determination module determines the coordinates of the positioning key point in the tracking camera shooting according to the center position of the target object, and determines the coordinates of the positioning key point in the tracking camera shooting according to the center position of the target.

In one implementation manner, the preset detection event is a head detection event.

In this device, AI detection technology is used to capture the target object, and the key point coordinates of the two cameras are obtained according to the target object. AI detection technology is used to replace the manual calibration position, which reduces cumbersome operations and greatly reduces the work of on-site commissioning personnel. Quantity, and with the help of the stability of the machine, the measurement error caused by human factors is reduced to ensure the accuracy of positioning.

Embodiment four

Corresponding to the method in Embodiment 2, as shown in FIG. 5 , the present invention also provides a dual-camera positioning device, including: an acquisition module 510 , a conversion module 520 , a control module 530 and a confirmation module 540 .

The obtaining module 510 is used to obtain the coordinate transformation relationship between the panoramic camera and the tracking camera, the coordinates of the target object in the panoramic camera and the detection event of the target object, wherein the positioning key points in the coordinate transformation relationship are obtained through the third embodiment Obtained by the dual-camera calibration device described above;

The conversion module 520 is configured to convert the coordinates of the target object in the panoramic camera into the coordinates of the target object in the tracking camera according to the coordinate conversion relationship;

A control module 530, configured to control the tracking camera to turn to a corresponding position according to the coordinates of the target object in the tracking camera;

The confirmation module 540 is configured to control the tracking camera to capture the target object using AI visual detection technology according to the detection event, and adjust the position of the tracking camera so that the target object is at a preset position in the shooting picture.

In an implementation manner, the control module 530 is further configured to zoom the tracking camera according to a preset ratio of the target object in the frame.

The positioning process of the device is simple, the calculation amount of the tracking and positioning process is small, the positioning is accurate, and the picture effect is good.

Embodiment five

An embodiment of the present invention also provides a storage medium on which computer instructions are stored, and when the instructions are executed by a processor, the dual-camera calibration method and/or the dual-camera positioning method in any of the above-mentioned embodiments is implemented.

Those skilled in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the Including the steps of the foregoing method embodiments; and the foregoing storage medium includes: a removable storage device, a random access memory (RAM, Random Access Memory), a read-only memory (ROM, Read-Only Memory), a magnetic disk or an optical disk, etc. A medium on which program code can be stored.

Alternatively, if the above-mentioned integrated units of the present invention are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the embodiment of the present invention or the part that contributes to the related technology can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to make A computer device (which may be a personal computer, a terminal, or a network device, etc.) executes all or part of the methods in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program codes such as removable storage devices, RAM, ROM, magnetic disks or optical disks.

Corresponding to the above-mentioned computer storage medium, in one embodiment, a computer device is also provided, the computer device includes a memory, an encoder, and a computer program stored in the memory and operable on the encoder, wherein the encoder When the program is executed, any one of the dual-camera calibration method and/or the dual-camera positioning method in the foregoing embodiments is implemented.

The above-mentioned computer equipment uses AI detection technology to capture the target object, and obtains the coordinates of the key points of the positioning of the two cameras according to the target object. AI detection technology is used to replace the manual calibration position, which reduces cumbersome operations and greatly reduces the work of on-site commissioning personnel. Quantity, and with the help of the stability of the machine, the measurement error caused by human factors is reduced to ensure the accuracy of positioning. In addition, the positioning process is simple, the calculation amount of the tracking and positioning process is small, the positioning is accurate, and the picture effect is good.

The technical features of the above-mentioned embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, should be considered as within the scope of this specification.

Apparently, the above-mentioned embodiments of the present invention are only examples for clearly illustrating the present invention, rather than limiting the implementation of the present invention. For those of ordinary skill in the art, other changes or changes in different forms can be made on the basis of the above description. It is not necessary and impossible to exhaustively list all the implementation manners here. All modifications, equivalent replacements and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the claims of the present invention.

Claims (11)

1. A double-camera calibration method is characterized by comprising the following steps:

acquiring a detection event;

controlling a tracking camera to capture a target object by utilizing an AI visual detection technology according to the detection event;

determining a positioning key point of a tracking camera according to a target object captured by the tracking camera;

capturing a target object in a video shot by the panoramic camera by utilizing an AI visual detection technology according to the detection event;

determining a positioning key point of the panoramic camera according to a target object of the panoramic camera;

associating the positioning keypoints of the panoramic camera with the positioning keypoints of the tracking camera.

2. The dual-camera calibration method according to claim 1, wherein said process of controlling the tracking camera to capture the target object according to the detection event by using AI visual detection technology comprises the steps of:

acquiring key point information to be positioned;

controlling a tracking camera to rotate a shooting initial position corresponding to the key point information to be positioned according to the key point information to be positioned;

and starting a tracking camera to capture the target object by utilizing an AI visual detection technology according to the detection event.

3. The dual-camera calibration method according to claim 1, wherein said process of controlling the tracking camera to capture the target object according to the detection event by using AI visual detection technology comprises the steps of:

acquiring a preset shooting range;

and controlling a tracking camera to capture the target object in the preset shooting range by utilizing an AI visual detection technology according to the detection event.

4. The dual-camera calibration method according to claim 1, wherein in the process of determining the positioning key points of the tracking camera according to the target object captured by the tracking camera, the coordinates of the positioning key points in the shooting of the tracking camera are determined according to the center position of the target object;

and in the process of determining the positioning key points of the panoramic camera according to the target object of the panoramic camera, determining the coordinates of the positioning key points in the shooting of the tracking camera according to the central position of the target.

5. The dual camera calibration method according to any one of claims 1 to 4, wherein the preset detection event is a human head detection event.

6. A method for positioning a dual camera, comprising the steps of:

acquiring a coordinate conversion relation between a panoramic camera and a tracking camera, coordinates of a target object in the panoramic camera and a detection event of the target object, wherein a positioning key point in the coordinate conversion relation is obtained by the double-camera calibration method according to any one of claims 1 to 5;

converting the coordinates of the target object in the panoramic camera into the coordinates of the target object in the tracking camera according to the coordinate conversion relation;

controlling the tracking camera to rotate to a corresponding position according to the coordinates of the target object in the tracking camera;

and controlling the tracking camera to capture the target object by utilizing an AI visual detection technology according to the detection event, and adjusting the position of the tracking camera to enable the target object to be at a preset position of a shot picture.

7. The method for positioning two cameras according to claim 6, further comprising the steps of:

zooming the tracking camera according to the preset proportion of the target object in the picture.

8. A dual camera calibration apparatus, comprising:

the acquisition module is used for acquiring a detection event;

the capture module is used for controlling the tracking camera to capture a target object by utilizing an AI visual detection technology according to the detection event and capturing the target object in a video shot by the panoramic camera by utilizing the AI visual detection technology;

the determining module is used for determining the positioning key points of the tracking camera according to the target object captured by the tracking camera and determining the positioning key points of the panoramic camera according to the target object of the panoramic camera;

and the association module is used for associating the positioning key points of the panoramic camera with the positioning key points of the tracking camera.

9. A dual-camera positioning apparatus, comprising:

an obtaining module, configured to obtain a coordinate transformation relationship between the panoramic camera and the tracking camera, coordinates of a target object in the panoramic camera, and a detection event of the target object, where a positioning key point in the coordinate transformation relationship is obtained by the dual-camera calibration device according to claim 8;

the conversion module is used for converting the coordinates of the target object in the panoramic camera into the coordinates of the target object in the tracking camera according to the coordinate conversion relation;

the control module is used for controlling the tracking camera to rotate to a corresponding position according to the coordinates of the target object in the tracking camera;

and the confirming module is used for controlling the tracking camera to capture the target object by utilizing an AI visual detection technology according to the detection event and adjusting the position of the tracking camera so that the target object is at the preset position of the shot picture.

10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1-7 when executing the program.

11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.

Images