WO2020057353A1 - Object tracking method based on high-speed ball, monitoring server, and video monitoring system - Google Patents

Abstract

The present application relates to the technical field of video monitoring, in particular to an object tracking method based on a high-speed ball, a monitoring server, and a video monitoring system. The method comprises: receiving a positioning instruction, wherein the positioning instruction comprises a target object that needs to be positioned; according to the positioning instruction, traversing video data captured by a target high-speed ball so as to detect the target object; and controlling the target high-speed ball to track the target object, and zooming in or out a video picture comprising the target object. On one hand, the present invention can automatically detect the target object for performing targeted capturing. On the other hand, the present invention can automatically track the target object, and can zoom in or out the video picture comprising the target object, thereby relatively providing a high definition video picture or a larger field of view associated with the target object for a later stage.

Description

High-speed ball-based object tracking method, monitoring server, video monitoring system Technical field

The invention relates to the technical field of video surveillance, in particular to a high-speed ball-based object tracking method, a monitoring server, and a video monitoring system.

Background technique

High-speed dome is a kind of intelligent camera. The full name is high-speed intelligent dome camera. High-speed dome has excellent video surveillance capabilities, so it is widely used in various industries.

The manager manages the video pictures uploaded by each high-speed ball in the monitoring background. When it is necessary to view the specific picture details of a certain character, the manager manually finds the video picture containing the character and zooms in on the character.

In the process of implementing the present invention, the inventor found that the traditional technology has at least the following problems: Because managers often look for the video picture containing the character after the fact, when the video picture is enlarged, although the detailed picture can be viewed, the details The sharpness of the picture is relatively poor and lacks targeted shooting.

Summary of the Invention

An object of the embodiments of the present invention is to provide a high-speed ball-based object tracking method, a monitoring server, and a video monitoring system, which can automatically track a target object in real time for targeted shooting.

To solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

In a first aspect, an embodiment of the present invention provides a high-speed ball-based object tracking method, which is applied to a monitoring server, and the method includes:

Receiving a positioning instruction, the positioning instruction including a target object to be positioned;

Traverse the video data captured by the target high-speed ball according to the positioning instruction to detect the target object;

Controlling the target high-speed ball to track the target object, and reducing or enlarging a video picture containing the target object.

Optionally, the controlling the target high-speed ball to track the target object includes:

Determining whether a target video frame containing the target object matches a preset video detection abnormal model;

If they match, use the target video frame as a tracking start point, and control the target high-speed ball to track the target object;

If there is no match, continue to determine whether the next target video frame containing the target object matches a preset video detection abnormal model.

Optionally, the target object is a person, and the number of the high-speed ball is at least two, and the high-speed ball can shoot the person from different angles;

The controlling the target high-speed ball to track the target object by using the target video frame as a tracking starting point includes:

Using the target video frame as a tracking starting point to obtain a person's image of the person being shot by the target high-speed ball;

Determining whether the person image is a front image of the person, and the front image includes a face image of the person;

If yes, controlling the target high-speed ball to track the person;

If not, an additional high-speed ball set opposite to the target high-speed ball is detected, and the additional high-speed ball is controlled to take a frontal image of the person, and track the person.

Optionally, the method further includes:

Obtaining a training video data set, where the training video data set includes video data of multiple abnormal scenes;

Preprocessing the video data of the multiple abnormal scenes;

The preprocessed video data is processed by a convolution algorithm to establish the video detection abnormal model.

Optionally, the receiving a positioning instruction includes:

Receiving image shape data input by a user, where the image shape data includes a number of image feature points;

Determining a shape of an object corresponding to the image shape data according to a plurality of image feature points in the image shape data;

An object corresponding to the image shape data is used as a target object to be positioned.

In a second aspect, an embodiment of the present invention provides an object tracking device based on a target high-speed ball, which is applied to a monitoring server, and the device includes:

A receiving module, configured to receive a positioning instruction, where the positioning instruction includes a target object to be positioned;

A traversal module, configured to traverse video data shot by the target high-speed ball according to the positioning instruction to detect the target object;

A control module is configured to control the target high-speed ball to track the target object, and to reduce or enlarge a video picture including the target object.

Optionally, the control module includes:

A judging unit, configured to judge whether a target video frame including the target object matches a preset video detection abnormal model;

A control unit, configured to control the target high-speed ball to track the target object by using the target video frame as a tracking starting point if matched;

A continuing judging unit, configured to continue judging whether the target video frame of the next frame containing the target object matches a preset video detection abnormal model if there is no match;

In a third aspect, an embodiment of the present invention provides a monitoring server, including:

At least one processor; and

A memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processing The device can be used to perform the high-speed ball-based object tracking method according to any one of the above.

In a fourth aspect, an embodiment of the present invention provides a video monitoring system, including:

Several high-speed balls;

In the monitoring server, the monitoring server communicates with each of the high-speed domes.

In a fifth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a monitoring server to execute The high-speed ball-based object tracking method according to any one.

In a sixth aspect, an embodiment of the present invention provides a computer program product. The computer program product includes a computer program stored on a non-volatile computer-readable storage medium. The computer program includes program instructions. When the instruction is executed by the monitoring server, the monitoring server is caused to execute the high-speed ball-based object tracking method according to any one of the above.

In the high-speed ball-based object tracking method, monitoring server, and video monitoring system provided by various embodiments of the present invention, first, a positioning instruction is received, and the positioning instruction includes a target object to be positioned; second, according to the positioning instruction, the target high-speed ball is traversed Video data to detect the target object; again, control the target high-speed ball to track the target object, and reduce or enlarge the video frame containing the target object. Therefore, on the one hand, it can automatically detect the target object for targeted shooting. On the other hand, it can track the target object automatically, and can reduce or enlarge the video frame containing the target object, so as to provide a high-definition video frame or a larger field of view associated with the target object for the later phase.

BRIEF DESCRIPTION OF THE DRAWINGS

One or more embodiments are exemplified by the pictures in the accompanying drawings. These exemplary descriptions do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the drawings in the drawings do not constitute a limitation on scale.

1 is a schematic structural diagram of an object tracking system based on a high-speed ball according to an embodiment of the present invention;

2 is a schematic flowchart of an object tracking method based on a high-speed ball according to an embodiment of the present invention;

3 is a schematic structural diagram of a high-speed ball-based object tracking device according to an embodiment of the present invention;

4 is a schematic structural diagram of a control module in FIG. 3;

FIG. 5 is a schematic structural diagram of a monitoring server according to an embodiment of the present invention.

detailed description

In order to make the objectives, technical solutions, and advantages of the present invention clearer, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

The high-speed ball-based object tracking method according to the embodiment of the present invention can be executed in any suitable type of electronic device with computing capability, such as a monitoring server, a desktop computer, a smart phone, a tablet computer, and other electronic products. The monitoring server here may be a physical server or a logical server virtualized by multiple physical servers. The server may also be a server group composed of multiple servers that can communicate with each other, and each functional module may be separately distributed on each server in the server group.

The high-speed ball-based object tracking device according to the embodiment of the present invention may be used as a software system, independently set in the above-mentioned client, or may be one of the functional modules integrated in the processor to execute the high-speed ball-based object of the embodiment of the present invention. Tracking method.

Please refer to FIG. 1, which is a schematic structural diagram of a video surveillance system according to an embodiment of the present invention. As shown in FIG. 1, the video surveillance system 100 includes a plurality of cameras 11, a surveillance server 12, and a mobile terminal 13.

The camera 11 is installed in a preset area for collecting video data. It can be understood that the camera 11 is fixedly installed in a preset area according to a preset rule, so as to cover the preset area as much as possible. For example, the camera is arranged on a wall surface, a ground, a roof, or an object surface of the preset area in combination with the specific structure and occlusion of the preset area.

Among them, there are multiple cameras. Each camera forms a camera group, which is used to monitor a specific surveillance area. Each camera is installed at a different position in a preset area. Each camera is used to capture images of areas at different angles within a preset area. For example, in some embodiments, the camera group can capture 360-degree objects in the preset area.

Generally, each camera in the camera group uploads the collected video data to the same monitoring server. Different monitoring areas correspond to different monitoring servers. For different managers who manage different surveillance areas, the surveillance servers of the two do not share surveillance video with each other.

In order to increase the shooting angle and shooting range of the camera 11, reduce the deployment of the camera 11, and reduce the system cost, a combination of the camera 11 and a multi-dimensional rotating motor can be used to capture real-time capture of high-definition video frame images in the preset area. Of course, you can choose an integrated camera 11 instead of the combination of the multi-dimensional rotating motor and the camera 11, such as a hemispherical all-in-one machine, a fast dome all-in-one machine, an integrated high-definition camera combined with a gimbal, or an integrated machine with a built-in lens. All-in-one can achieve automatic focusing. Preferably, a high-definition camera with a waterproof function, a small size, a high resolution, a long life, and a universal communication interface is selected.

In some embodiments, the camera 11 is a network camera, and the camera 11 has a built-in network coding module.

The camera includes a lens, an image sensor, a sound sensor, an A / D converter, a controller, a control interface, a network interface, and so on. The camera may be used to collect video data signals, and the video data signals are analog video signals. The camera is mainly composed of a CMOS light-sensitive component and a peripheral circuit, and is used for converting an optical signal input from the lens into an electrical signal.

Specifically, the network coding module has an embedded chip built therein, the embedded chip is used to convert the video data signals collected by the camera into digital signals, the video data signals are analog video signals, and the embedded chip also The digital signal may be compressed. Specifically, the embedded chip may be a Hi3516 high-efficiency compression chip.

The camera 11 sends the compressed digital signal to the monitoring server 12 through the WIFI network. The monitoring server 12 may send the compressed digital signal to the mobile terminal 13. The camera 11 further includes an infrared sensor, so that the camera 11 has a night vision function. Users on the network can directly view the camera image on the web server with a browser or directly access through the mobile terminal APP. The camera 11 can more easily implement monitoring, especially remote monitoring, with simple construction and maintenance, better support for audio, Better support for alarm linkage, more flexible recording storage, richer product selection, higher-definition video effects and more perfect monitoring and management functions, and the camera can be directly connected to the local area network, which is the data collection and photoelectric signal The conversion end is the data supply end of the entire network.

The monitoring server 12 is a device that provides computing services. The composition of the monitoring server includes a processor, a hard disk, a memory, a system bus, and the like. Similar to a general computer architecture, the monitoring server is responsible for providing functions such as mobile terminal APP registration, user management, and device management. At the same time, it is responsible for the video data storage function of the camera, and remembers the IP and port of the mobile terminal and camera through the monitoring server, and transmits the IP and port of the corresponding mobile terminal and camera to each other, so that the camera and mobile end can know The other party's IP and port establish a connection and communication through the IP address and port. The monitoring server obtains the video data of the camera and then analyzes the video data according to the artificial intelligence module. When abnormal video data is detected, it sends an alarm message to notify the mobile terminal.

Specifically, the monitoring server 12 includes a processor, and the processor includes an artificial intelligence module. The artificial intelligence module is responsible for real-time analysis of video data, detects abnormal times, and notifies the mobile terminal. The specific implementation of the artificial intelligence module is divided into two parts, the establishment of a video anomaly detection model and the application of a video anomaly detection model. The first is the establishment of the video anomaly detection model. There are three parts. The first part: training the video data set of the video anomaly detection model for the training and learning of the subsequent machines. It includes video data of various abnormal scenes, such as frequent crossing of vehicles, robbery, trailing theft, fights, group fights, screams, crying, smoke, noisy video data, and other abnormal scenes that need to be detected. The training video dataset covers most application scenarios. The second part: the preprocessing of the video data set. The video data is extracted 10 pictures per second, and each picture is converted into a picture of 255 pixels long and 255 pixels wide. The third part: the establishment of training model, using artificial intelligence convolution algorithm, Python code to build the training model. The model includes an input layer, a hidden layer, and an output layer. The input layer is an input pre-processed picture. The hidden layer is used to calculate the features of the input picture. The output layer is based on the calculated features of the hidden layer to output whether the video contains abnormal scenes. The training process is. The normal video is marked as 0, and the abnormal video is marked as 1. Then, the abnormal video and the normal video are input into the training system at the same time, and the data set is preprocessed and the training model is calculated to distinguish whether the video is abnormal or normal. Repeat the above steps, stop training when the accuracy of the system's discrimination reaches 90%, and save the model. After the model is established, the model is transferred to the server, the data set is replaced with the video of the camera, and the model is run to detect whether the video of the camera is abnormal.

Please refer to FIG. 2, which is a schematic flowchart of an object tracking method based on a high-speed ball according to an embodiment of the present invention. As shown in FIG. 2, the high-speed ball-based object tracking method S200 includes:

S21. Receive a positioning instruction, where the positioning instruction includes a target object to be positioned;

In this embodiment, the positioning instruction is used to instruct the monitoring server to detect and target objects in the video data. There are various ways to generate a positioning instruction. For example, in some embodiments, a user enters an object name of a target object on a user interaction interface of a monitoring server, thereby triggering the monitoring server to issue a positioning instruction, where the positioning instruction includes an object The target object corresponding to the name. In other embodiments, because there are many types and shapes of objects, and some objects lack an official or common sense uniform name, in order to be able to detect the target object smoothly, the user can pre-build the shape of the specific object on the monitoring server, so The user triggers the monitoring server to issue positioning instructions, and the subsequent monitoring server can generate image shape data according to the shape of the object, where the image shape data includes several image feature points of the object.

Secondly, the monitoring server determines the shape of the object corresponding to the image shape data according to several image feature points in the image shape data.

Again, the monitoring server uses the object corresponding to the image shape data as the target object to be positioned.

For example, a user inputs image shape data of a vehicle at a monitoring server, and the monitoring server parses each image feature point according to the image shape data. Secondly, the monitoring server determines that the image is a vehicle shape image according to each image feature point. Third, the monitoring server regards the vehicle as a target object to be positioned.

S22. According to the positioning instruction, traverse the video data captured by the target high-speed ball to detect the target object;

In this embodiment, the high-speed dome integrates a gimbal system, a communication system, and a camera system, which can implement functions such as target tracking, focus adjustment, position conversion, and the like.

The target high-speed ball is any camera in the camera group. It can be understood that the “target” in the target high-speed ball is used to distinguish other cameras. When the monitoring server selects the video data of a specific camera from the camera group for detection and analysis, This particular camera is the target speed dome. The "target" in the target high-speed ball is not used to limit the protection scope of the present invention, but only used for differentiation.

In this embodiment, according to the positioning instruction, the monitoring server sequentially traverses the video data captured by the target high-speed ball according to the monitoring time, and detects the target object therefrom.

S23. Control the target high-speed ball to track the target object, and reduce or enlarge the video image containing the target object.

In this embodiment, the monitoring server controls the PTZ of the target high-speed ball to adjust the camera lens to follow the movement of the target object according to the movement of the target object. In some embodiments, when the target high-speed ball tracks the target object, the monitoring server may draw and save the walking path of the target object, so as to provide convenience when the target object is subsequently analyzed.

Since the target object is the focus of the monitoring server, in order to analyze the target object with the help of high-definition images later, the monitoring server can enlarge the video image containing the target object in order to obtain a more detailed picture of the target object. Or, in order to fully restore the surrounding environment of the target object at a later stage, the monitoring server may also reduce the video image containing the target object to obtain a larger field of view including the target object as much as possible.

In summary, on the one hand, it can automatically detect a target object for targeted shooting. On the other hand, it can track the target object automatically, and can reduce or enlarge the video frame containing the target object, so as to provide a high-definition video frame or a larger field of view associated with the target object for the later phase.

Generally, when there are some abnormal situations in a video scene, the objects in the video scene are more worthy of attention, such as anomalies such as robbery, trailing theft, fights, group fights, screams, crying, smoke or noisy. The objects in the scene are worth paying attention to. Therefore, in some embodiments, when the monitoring server controls the target high-speed ball to track the target object, first, the monitoring server determines whether the target video frame containing the target object matches the preset video detection abnormal model; if it matches, the target video frame is used as the tracking starting point. Starting point, control the target high-speed ball to track the target object. If they do not match, continue to determine whether the next target video frame containing the target object matches the preset video detection abnormal model.

In some embodiments, the target object is a person, and the number of high-speed balls is at least two. Different high-speed balls can photograph people from different angles. The monitoring server uses the target video frame as the tracking start point. When controlling the target high-speed ball to track the target object, the monitoring server first uses the target video frame as the tracking start point to obtain the target high-speed ball to shoot the person's image.

Second, the monitoring server determines whether the person image is a front image of the person, and the front image includes a face image of the person. For example, A's Trailer B, Opportunity Pickpocket B's handbag, the camera monitors A's Trailing action behavior, and sends video data containing A's Trailing action behavior to the monitoring server. The monitoring server detects A's Trailing action behavior and determines A is the target person. The monitoring server then analyzes the person's image according to the image analysis algorithm to determine whether there are facial feature points associated with the target person in the video data. If it exists, it considers that the video data contains a frontal image of the target person; if it does not exist, it considers the video data The front image of the target person is not included, and the video data includes only the back image of the target person. For example, following the above example, if the monitoring server detects the face image of A in the video data, it is considered that the target high-speed ball has captured the front image of A. If the monitoring server does not detect the face image of nail A in the video data, it considers that the target high-speed ball captured the back image of nail A.

Again, if it is a frontal image of a person, the monitoring server controls the target high-speed ball to track the person; if not, the monitoring server detects an additional high-speed ball set opposite the target high-speed ball, controls the additional high-speed ball to take a frontal image of the person, and tracks the person. For example, when the monitoring server detects that the video data does not include a frontal image of the target person, the monitoring server determines the current geographic location of the target person.

Secondly, the monitoring server detects and covers all additional high-speed domes of the target person's current geographical position and determines the installation geographic positions of all the additional high-speed domes according to the current geographic position of the target person, and determines the installation locations from all of the additional high-speed domes. The target high-speed dome is an additional high-speed dome that is relatively geographically installed.

Again, the monitoring server controls the extra high-speed ball relative to the installed geographical position of the target high-speed ball to track the person and take a frontal image of the person.

In fact, some vicious events occur mostly in dark places such as low light. In order to prevent illegal elements and strive to obtain high-definition face images of illegal elements, in some embodiments, the monitoring server detects additional high speeds that are set opposite the target high-speed ball. When the ball is used, first, the monitoring server obtains the light intensity in the preset area. For example, a light sensor set in the preset area collects the light intensity and transmits the light intensity to the monitoring server.

Secondly, the monitoring server judges whether the light intensity is greater than a preset intensity threshold. If it is greater than that, it obtains the minimum illumination values of all the additional high-speed balls set opposite to the target high-speed ball, and traverses the lowest illumination value from the lowest illumination values of all the additional high-speed balls. The extra high-speed ball is used as a high-speed ball that tracks and captures the front image of the character. Therefore, the surveillance server obtains the front image of the character as high-definition as possible. If it is less than that, an additional high-speed ball set opposite to the target high-speed ball is detected.

In this way, it can obtain high-definition frontal images of people as much as possible, thereby achieving effective video surveillance.

It should be noted that, in the above embodiments, there is not necessarily a certain sequence between the above steps. Those skilled in the art can understand from the description of the embodiments of the present invention that the above steps in different embodiments There can be different execution orders, that is, execution can be performed in parallel, execution can be exchanged, and so on.

As another aspect of the embodiments of the present invention, an embodiment of the present invention provides a high-speed ball-based object tracking device applied to a monitoring server. The high-speed dome-based object tracking device according to the embodiment of the present invention may be used as one of the software functional units. The high-speed dome-based object tracking device includes several instructions. The several instructions are stored in a memory, and the processor may access the memory and call the instructions for execution. To complete the above-mentioned high-speed ball-based object tracking method.

Referring to FIG. 3, the high-speed ball-based object tracking device 300 includes a receiving module 31, a traversal module 32, and a control module 33.

The receiving module 31 is configured to receive a positioning instruction, where the positioning instruction includes a target object to be positioned;

The traversal module 32 is configured to traverse the video data captured by the target high-speed ball according to the positioning instruction to detect the target object;

The control module 33 is used for controlling the target high-speed ball to track the target object, and reducing or enlarging a video picture containing the target object.

In summary, on the one hand, it can automatically detect a target object for targeted shooting. On the other hand, it can track the target object automatically, and can reduce or enlarge the video frame containing the target object, so as to provide a high-definition video frame or a larger field of view associated with the target object for the later phase.

In some embodiments, referring to FIG. 4, the control module 33 includes: a judging unit 331, a control unit 332, and a continuing judging unit 333.

The determining unit 331 is configured to determine whether a target video frame including the target object matches a preset video detection abnormal model;

The control unit 332 is configured to control the target high-speed ball to track the target object by using the target video frame as a tracking starting point if matched;

The continuing determination unit 333 is configured to continue to determine whether the target video frame of the next frame including the target object matches a preset video detection abnormal model if there is no match.

It should be noted that the above-mentioned high-speed ball-based object tracking device can execute the high-speed ball-based object tracking method provided by the embodiment of the present invention, and has corresponding function modules and beneficial effects of the execution method. For technical details not described in detail in the embodiment of the high-speed ball-based object tracking device, refer to the high-speed ball-based object tracking method provided in the embodiment of the present invention.

As yet another aspect of the embodiments of the present invention, an embodiment of the present invention provides a monitoring server. As shown in FIG. 5, the monitoring server 500 includes: one or more processors 51 and a memory 52. Among them, one processor 51 is taken as an example in FIG. 5.

The processor 51 and the memory 52 may be connected through a bus or in other manners. In FIG. 5, the connection through the bus is taken as an example.

The memory 52 is a non-volatile computer-readable storage medium, and can be used to store non-volatile software programs, non-volatile computer executable programs, and modules, such as the high-speed ball-based object tracking method in the embodiment of the present invention. Corresponding program instructions / modules. The processor 51 executes various functional applications and data processing of the high-speed dome-based object tracking device by running non-volatile software programs, instructions, and modules stored in the memory 52, that is, the high-speed dome-based Object tracking method and functions of each module of the above device embodiment.

The memory 52 may include a high-speed random access memory, and may further include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 52 may optionally include a memory remotely disposed with respect to the processor 51, and these remote memories may be connected to the processor 51 through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The program instructions / modules are stored in the memory 52, and when executed by the one or more processors 51, perform the high-speed ball-based object tracking method in any of the above method embodiments, for example, execute the above-described Each step in FIG. 2; the functions of each module described in FIG. 3 and FIG. 4 can also be implemented.

An embodiment of the present invention also provides a non-volatile computer storage medium. The computer storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, such as a process in FIG. 5. The processor 51 may cause the one or more processors to execute the high-speed ball-based object tracking method in any of the foregoing method embodiments, for example, to execute the high-speed ball-based object tracking method in any of the foregoing method embodiments, for example, to execute The above-mentioned execution performs the above-mentioned execution of the steps shown in FIG. 2 described above; the functions of the various modules described in FIG. 3 and FIG. 4 may also be implemented.

The embodiments of the device or device described above are only schematic, and the unit modules described as separate components may or may not be physically separated, and the components displayed as module units may or may not be physical units. , Can be located in one place, or can be distributed to multiple network module units. Some or all of the modules may be selected according to actual needs to achieve the objective of the solution of this embodiment.

Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus a general hardware platform, and of course, also by hardware. Based on such an understanding, the above-mentioned technical solutions that are essentially or contribute to related technologies can be embodied in the form of software products, which can be stored in computer-readable storage media, such as ROM / RAM, magnetic disks , Optical discs, etc., including several instructions until a computer device (which may be a personal computer, a server, or a network device, etc.) executes the methods described in various embodiments or certain parts of the embodiments.

Finally, it should be noted that the above embodiments are only used to describe the technical solution of the present invention, but not limited thereto. Under the idea of the present invention, the technical features in the above embodiments or different embodiments can also be combined. The steps can be implemented in any order and there are many other variations of the different aspects of the invention as described above, for the sake of brevity they are not provided in the details; although the invention has been described in detail with reference to the foregoing embodiments, it is common in the art The skilled person should understand that they can still modify the technical solutions described in the foregoing embodiments, or equivalently replace some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions separate from the implementation of this application. Examples of technical solutions.

Claims (10)

A high-speed ball-based object tracking method applied to a monitoring server is characterized in that the method includes: Receiving a positioning instruction, the positioning instruction including a target object to be positioned; Traverse the video data captured by the target high-speed ball according to the positioning instruction to detect the target object; Controlling the target high-speed ball to track the target object, and reducing or enlarging a video picture containing the target object. The method according to claim 1, wherein the controlling the target high-speed ball to track the target object comprises: Determining whether a target video frame containing the target object matches a preset video detection abnormal model; If they match, use the target video frame as a tracking start point, and control the target high-speed ball to track the target object; If there is no match, continue to determine whether the next target video frame containing the target object matches a preset video detection abnormal model. The method according to claim 2, wherein the target object is a character, and the number of high-speed balls is at least two, and the high-speed ball can shoot the character from different angles; The controlling the target high-speed ball to track the target object by using the target video frame as a tracking starting point includes: Using the target video frame as a tracking starting point to obtain a person's image of the person being shot by the target high-speed ball; Determining whether the person image is a front image of the person, and the front image includes a face image of the person; If yes, controlling the target high-speed ball to track the person; If not, an additional high-speed ball set opposite to the target high-speed ball is detected, and the additional high-speed ball is controlled to take a frontal image of the person, and track the person. The method according to claim 2, wherein: The method further includes: Obtaining a training video data set, where the training video data set includes video data of multiple abnormal scenes; Preprocessing the video data of the multiple abnormal scenes; The preprocessed video data is processed by a convolution algorithm to establish the video detection abnormal model. The method according to any one of claims 1 to 4, wherein the receiving a positioning instruction comprises: Receiving image shape data input by a user, where the image shape data includes a number of image feature points; Determining a shape of an object corresponding to the image shape data according to a plurality of image feature points in the image shape data; An object corresponding to the image shape data is used as a target object to be positioned. A high-speed ball-based object tracking device applied to a monitoring server is characterized in that the device includes: A receiving module, configured to receive a positioning instruction, where the positioning instruction includes a target object to be positioned; A traversal module for traversing video data taken by the target high-speed ball according to the positioning instruction to detect the target object; A control module is configured to control the target high-speed ball to track the target object, and to reduce or enlarge a video picture including the target object. The apparatus according to claim 6, wherein the control module comprises: A judging unit, configured to judge whether a target video frame including the target object matches a preset video detection abnormal model; A control unit, configured to control the target high-speed ball to track the target object by using the target video frame as a tracking starting point if matched; A continuing judging unit, configured to continue judging whether the target video frame of the next frame containing the target object matches a preset video detection abnormal model if there is no match; A monitoring server, comprising: At least one processor; and A memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processing The device can be used to perform the high-speed ball-based object tracking method according to any one of claims 1 to 5. A video surveillance system, comprising: Several high-speed balls; The monitoring server according to claim 8, said monitoring server communicating with each of said high-speed domes. A non-transitory computer-readable storage medium, characterized in that the non-transitory computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a monitoring server to execute the claims 1 to 5 The high-speed ball-based object tracking method according to any one.

Images