A video target region tracking and zooming method, device, equipment and medium

Abstract

The application discloses a video target area tracking and zooming method, which determines a target area containing a target object by recognizing a user's touch gesture track on a client, acquires magnification data of a corresponding position in a video stream through center point coordinate data of the target area, and then performs double-canvas rendering on video stream data for displaying a picture after zooming processing of the target area, so that real-time zooming processing of the target object in the monitoring video is realized. In addition, the application also tracks movable objects in the target area through an artificial intelligence algorithm, updates the center point coordinates of the target area in real time, and then synchronously displays a real-time tracking and zooming picture of the target area, so that a user can timely master clear and detailed information of specific targets such as movable objects when viewing real-time monitoring video, and the monitoring efficiency of the security monitoring equipment is effectively improved, and the safety of the user is greatly increased.

Description

TECHNICAL FIELD

[0001] The present application relates to the security monitoring technical field, and particularly relates to a tracking magnification method and device based on a specific target area of a video stream, equipment and a medium. BACKGROUND

[0002] In the existing security video monitoring technology, the target point of the situation occurring in the video monitoring is often limited to a small part of the full monitoring picture, and the details cannot be clearly seen. The user needs to master both the overall information of the monitoring scene and the clear local information of the target point. Therefore, the specific target area needs to be locally magnified. In addition, in the security monitoring field, specific objects in the monitoring scene, such as people, animals, vehicles and other moving objects, are often the most interesting to users. However, the moving objects often occupy a small proportion in the picture, so that the details are often not clear in the entire monitoring video. Therefore, the moving objects in the monitoring scene need to be locally magnified and the moving track needs to be tracked in real time, so that the user can timely master the clear detail information of the specific target such as the moving object when viewing the real-time monitoring video.

[0003] At present, in the existing technology in the video monitoring field, if the video needs to be magnified and displayed, the monitoring video often needs to be played back, and the specific target is locally magnified through the monitoring client platform software. It is impossible to realize real-time tracking and magnification processing of the specific target area or object in the monitoring video.

[0004] In order to solve the above problems, the present application provides a video target area tracking magnification method. SUMMARY

[0005] In order to overcome the shortcomings of the existing technology, the present application provides a video target area tracking magnification method, which comprises the following steps:

[0006] S1: identifying the gesture trajectory drawn by the user on the client touch display interface to obtain the coordinates of the center point and the distance from the mobile phone trajectory edge to the center point, and generating a target area containing a target object for magnification using the center point and the distance from the mobile phone trajectory edge to the center point coordinates;

[0007] S2: obtaining the magnification data of the corresponding position in the video stream through the coordinates of the center point and the distance from the mobile phone trajectory edge to the center point;

[0008] S3: using double canvas rendering for the video stream; wherein the video stream is rendered to the bottom player canvas for displaying the bottom video during live broadcast; and the magnification data is rendered to the upper layer magnification area canvas for displaying the picture of the target area after magnification processing;

[0009] S4: applying an artificial intelligence algorithm to judge the object in the target area, if judging as a movable object, executing step S5; if judging as a static object, displaying the enlarged picture of step S3;

[0010] S5: tracking the movable object, updating the center point coordinate data corresponding to the target area in real time, obtaining the magnification data of the corresponding position in the video stream, and then synchronously displaying the real-time tracking enlarged picture of the target area.

[0011] Preferably, in the step S1, the gesture trajectory recognition adopts a fuzzy algorithm for judgment.

[0012] Preferably, in step S1, the shape of the target area includes but is not limited to a circle or an ellipse.

[0013] Preferably, in step S3, the following steps are further included:

[0014] The user connects to the camera through a mobile client, sends a command to start the video stream, the camera encodes the collected YUV data format into H.264 format, and then sends it to the mobile client through a private encryption format. The mobile client receives the data, decrypts it to obtain H.264 data, decodes the H.264 data to obtain YUV data, and renders the YUV data for the user to watch or stores the obtained video data for the user to view later.

[0015] Preferably, in the step S3, the magnification data is the magnification data of the target area at the corresponding position of the video stream associated with the center point coordinate.

[0016] Preferably, in the step S4, the following steps are included:

[0017] Capturing the object appearing in the scene image, matching the object with a preset instruction set; according to the matching result, when a dynamic object is captured, determining the category to which the dynamic object belongs through the preset instruction set, and tracking and locally enlarging the dynamic object according to the determined category.

[0018] In addition, the application also provides a video target area tracking and enlarging device, comprising:

[0019] A video stream acquisition unit; for the camera to encode the collected YUV data format into H.264 format, and then send it to the mobile client through a private encryption format. The mobile client receives the data, decrypts it to obtain H.264 data, and then decodes the H.264 data to obtain YUV data;

[0020] The video rendering unit is used for identifying a user gesture track and generating a target area, and in response to an enlargement instruction for a picture of the target area, performing an enlargement processing on the picture of the target area through double-canvas rendering;

[0021] The dynamic capturing unit is used for capturing a dynamic object appearing in the target area, and if the dynamic object is captured, triggering a control instruction for tracking and enlarging the dynamic object;

[0022] The tracking and enlarging unit is used for synchronously tracking a real-time enlarged picture of the target area;

[0023] The display unit is used for displaying a live bottom-layer video after being rendered by the video rendering unit and a picture after being enlarged of the target area.

[0024] Preferably, the tracking and enlarging device further comprises a background service unit used for transmitting a video stream acquired by the video stream acquiring unit to the video rendering unit, and transmitting data after being rendered by the video rendering unit to the display unit; and simultaneously starting the dynamic capturing unit and the tracking and enlarging unit, and transmitting a real-time enlarged picture of the tracking and enlarging unit to the display unit.

[0025] The application further provides a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to realize the tracking and enlarging method.

[0026] The application further provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and the computer program is executable on a processor to realize the method.

[0027] Compared with the prior art, the application has the beneficial effects that: the application provides a video target area tracking and enlarging method, wherein a target area containing a target object is determined by identifying a touch gesture track of a user on a client, and a magnification data of a corresponding position in a video stream is acquired through a center point coordinate data of the target area, and then a double-canvas rendering is performed on the video stream data, wherein a bottom-layer player canvas is used for displaying a bottom-layer video during live broadcast, and the magnification data is rendered to an upper-layer enlarged area canvas for displaying a picture after being enlarged of the target area, so that real-time enlargement processing on a target area or an object in a monitoring video is realized. In addition, the application further tracks a movable object in the target area, updates a center point coordinate of the corresponding target area in real time, and synchronously displays a real-time tracking and enlarging picture of the target area, so that a user can timely master clear and detailed information of a specific target such as a movable object when viewing a real-time monitoring video, and the monitoring efficiency of a security monitoring device is effectively improved, and the security of a user's residence is significantly improved, and the application has the advantages of low cost and high convenience in preventing accidents and intrusion and rapid response. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 A step flow chart for an embodiment of the present application;

[0029] Figure 2 A schematic diagram of the principle of step S2 in the embodiment of the present application; Figure 1

[0030] Figure 3 A structural schematic diagram of a video target area tracking and magnifying device provided by an embodiment of the present application; and

[0031] Figure 4 A structural schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the technical problems to be solved by the present application, technical solutions and beneficial effects more clear, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0033] It should be noted that the terms "comprise" and "have" and any variations thereof in the specification and claims of the present application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally further include steps or units not listed, or can optionally further include other steps or units inherent to the process, method, product or device.

[0034] Please refer to Figures 1 to 3 The present application provides a video target area tracking and magnifying method, comprising the following steps:

[0035] S1: identifying a gesture trajectory drawn by a user on a client touch display interface to obtain a center point coordinate and a distance from a mobile trajectory edge to the center point, and generating a target area for magnification containing a target object using the center point and the distance from the mobile trajectory edge to the center point as coordinates;

[0036] S2: obtaining magnification data of a corresponding position in a video stream through the center point coordinate and the distance from the mobile trajectory edge to the center point;

[0037] S3: using double-canvas rendering for the video stream; wherein the video stream is rendered to a bottom-layer player canvas for displaying a bottom-layer video during live streaming; and the magnification data is rendered to an upper-layer magnifying area canvas for displaying a picture after magnifying processing of the target area;

[0038] ​S4: Use artificial intelligence algorithms to judge the objects in the target area. If the object is judged to be a movable object, proceed to step S5; if the object is judged to be a static object, display the magnified view of step S3.

[0039] S5: Tracks moving objects, updates the center coordinates of the corresponding target area in real time, obtains the magnification data of the corresponding position in the video stream, and then synchronously displays the real-time tracking magnified image of the target area.

[0040] In step S1, the gesture trajectory recognition uses a fuzzy algorithm for judgment.

[0041] In step S1, the shape of the target area includes, but is not limited to, a circle or an ellipse.

[0042] like Figure 2 As shown, in step S2, the coordinates of the center point in the preset screen are determined based on the user's click position, such as... Figure 2 As shown, the center point O is the origin coordinate. An enlarged target area is generated based on the origin coordinate. The shape of the target area can be customized by the user, including but not limited to circular frames, rectangular frames, and star-shaped frames. Through the image within the target area, users can view a real-time magnified image of the live stream where details are unclear. For example... Figure 2 As shown, the circular frame represents the target area for local magnification. For the hollow origin A0 within the circular frame, the coordinates of the hollow point A0 are mapped onto the coordinates of the solid point A1. In other words, the original coordinates of all points within the circular frame are mapped onto the offset coordinates, thus completing the local magnification based on a specific target area.

[0043] Step S3 further includes the following steps:

[0044] Users connect to the camera via a mobile client and send a command to start the video stream. The camera encodes the captured YUV data into H.264 format and then sends it to the mobile client using a proprietary encryption format. The mobile client receives the data, decrypts it to obtain H.264 data, decodes the H.264 data to obtain YUV data, renders it for user viewing, or stores the obtained video data for later review. Users can recall and review the stored video file at any time when needed and track and zoom in on objects of interest within the video file.

[0045] In step S3, the magnification data is the magnified data of the target region at the corresponding position in the video stream, which is associated with the center point coordinates.

[0046] In step S4, the present invention uses an artificial intelligence algorithm to determine the target object within the target area. The specific steps are as follows:

[0047] Capture the object appearing in the scene image, match the object with a preset instruction set; wherein, in the embodiment, the preset instruction set can include: people and objects. Including dynamic objects such as human body, face, vehicle, aircraft, unmanned aerial vehicle, animal, etc., and static objects, including road surface, building, mountain, tree, etc.

[0048] According to the matching result, when a dynamic object is captured, the category to which the dynamic object belongs is determined through the preset instruction set, and the dynamic object is tracked and zoomed in according to the determined category. In this way, when zooming in, the system resources can be occupied, and the processing efficiency of zooming in can be optimized.

[0049] In addition, as shown in Figure 4 The application also provides a video target area tracking and zooming device, comprising:

[0050] A video stream acquisition unit 101; for the camera to encode the collected YUV data format into H.264 format, and then send it to the mobile client through a private encryption format. The mobile client receives the data, decrypts it to obtain H.264 data, and then decodes the H.264 data to obtain YUV data;

[0051] A video rendering unit 102; for identifying user gesture tracks and generating a specific target area, and responding to the zoom-in instruction of the specific target area picture, executing zoom-in processing on the specific target area picture through double-canvas rendering;

[0052] A dynamic capture unit 103, for capturing dynamic objects appearing in the target area, and triggering a control instruction for tracking and zooming in on the dynamic object if a dynamic object is captured;

[0053] A tracking and zooming unit 104, for synchronously tracking the real-time zoom-in picture of the specific target area;

[0054] A display unit 105, for displaying the live bottom layer video rendered by the video rendering unit and the picture processed by zooming in on the specific target area.

[0055] A background service unit, for transmitting the video stream acquired by the video stream acquisition unit 101 to the video rendering unit 102, and transmitting the data rendered by the video rendering unit 102 to the display unit 105; at the same time, starting the dynamic capture unit 103 and the tracking and zooming unit 104, and transmitting the real-time zoom-in picture of the tracking and zooming unit 104 to the display unit 105.

[0056] As Figure 4As shown, the present application further provides a computer device 2, comprising a memory 201, a processor 202, and a computer program stored in the memory 201 and executable on the processor 202, the processor 202 executes the computer program to implement the above-mentioned tracking amplification method.

[0057] The present application further provides a computer readable storage medium, which stores a computer program, the program is executed by a processor to implement the above-mentioned method.

[0058] Compared with the prior art, the present application provides a video target area tracking amplification method, which determines a target area containing a target object by recognizing a user's touch gesture track on a client, and obtains magnification data of a corresponding position in a video stream through the center point coordinate data of the target area, and then performs double-canvas rendering on the video stream data, the bottom player canvas is used to display the bottom video during live broadcast; the magnification data is rendered to the upper layer amplification area canvas, which is used to display the picture after the target area is amplified, so that real-time amplification processing of the target area or object in the monitoring video is realized. In addition, the present application also tracks the movable object in the target area, updates the center coordinate of the corresponding target area in real time, and then synchronously displays the real-time tracking amplification picture of the target area, so that the user can grasp the clear and detailed information of the specific target such as the moving object when viewing the real-time monitoring video, effectively improving the monitoring efficiency of the security monitoring device, significantly improving the security of the user's residence, and having the advantages of low cost and high convenience in preventing accidents, preventing intrusion and rapid response.

[0059] Those skilled in the art can understand that each aspect of the present application can be implemented as a system, a method or a program product. Therefore, each aspect of the present application can be embodied in the form of a complete hardware, a complete software (including firmware, microcode, etc.), or a combination of hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system".

[0060] Any one or more of the modules, sub-modules, units, sub-units according to the embodiments can be implemented in one module. Any one or more of the modules, sub-modules, units, sub-units according to the embodiments can be split into multiple modules. Any one or more of the modules, sub-modules, units, sub-units according to the embodiments can be implemented at least in part as a hardware circuit, for example, a field-programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system on package, an application-specific integrated circuit (ASIC), or any other reasonable manner of hardware or firmware by integrating or packaging the circuit, or in any one of software, hardware, and firmware, or in a proper combination of any one or more of them. Alternatively, one or more of the modules, sub-modules, units, sub-units according to the embodiments can be implemented at least in part as computer program modules, which can perform the corresponding functions when the computer program modules are run.

[0061] Furthermore, although the operations of the method according to the present application are described in a particular order, this is not meant to be limiting or insinuate that the operations must be performed in that particular order, or that all of the operations must be performed to achieve desirable results. Additionally or alternatively, certain steps can be omitted, combined, performed in a different order, and / or performed in parallel.

[0062] It should be understood that, for those skilled in the art, modifications or changes can be made according to the above description, and all these modifications and changes shall fall within the protection scope of the appended claims of the present application.

[0063] The above description of the present application is exemplary in conjunction with the accompanying drawings, and it is obvious that the implementation of the present application is not limited by the above manner. Any kind of improvement, or direct application of the concept and technical scheme of the present application to other occasions without modification, all fall within the protection scope of the present application.

Claims

1. A video target region tracking and zooming method, characterized in that, The method comprises the following steps: S1: identifying a gesture trajectory drawn by a user on a client touch display interface to obtain a center point coordinate and a distance from a gesture trajectory edge to the center point, and generating a target area containing a target object for magnification using the center point coordinate and the distance from the gesture trajectory edge to the center point; S2: obtaining magnification data of a corresponding position in a video stream through the center point coordinate and the distance from the gesture trajectory edge to the center point; S3: rendering the video stream using double canvas; wherein the video stream is rendered to a bottom layer player canvas for displaying a bottom layer video during live streaming; and the magnification data is rendered to an upper layer magnification area canvas for displaying a picture after magnification processing of the target area; S4: judging an object in the target area using an artificial intelligence algorithm; if the object is a movable object, executing step S5; if the object is a static object, displaying the magnification picture of step S3; S5: tracking the movable object, updating a center point coordinate data corresponding to the target area in real time, obtaining magnification data of a corresponding position in a video stream, and then synchronously displaying a real-time tracking magnification picture of the target area.

2. The method of claim 1, wherein, In step S1, the gesture trajectory recognition uses a fuzzy algorithm for judgment.

3. The method of claim 1, wherein, In step S1, the shape of the target area includes a circle or an ellipse.

4. The method of claim 1, wherein, In step S3, the following steps are further included: A user connects to a camera through a mobile client, sends a command to start a video stream, the camera encodes YUV data collected in a H.264 format, and then sends the data to the mobile client in a private encryption format; the mobile client receives the data, decrypts the data to obtain H.264 data, decodes the H.264 data to obtain YUV data, and then renders the YUV data for the user to watch or stores the video data for the user to view later.

5. The method of claim 1, wherein, In step S3, the magnification data is magnification data of the target area at a corresponding position in the video stream associated with the center point coordinate.

6. The method of claim 1, wherein, In step S4, the following steps are included: An object appearing in the target area is captured, and the object is matched with a preset instruction set; according to a matching result, when a dynamic object is captured, a category to which the dynamic object belongs is determined through the preset instruction set, and the dynamic object is tracked and locally magnified according to the determined category.

7. A tracking magnification device for implementing the video target region tracking magnification method according to any one of claims 1-6, characterized in that, The method comprises: a video stream acquisition unit; a video rendering unit for identifying a user gesture trajectory and generating a target area, and responding to a magnification instruction of a picture of the target area to perform magnification processing of the picture of the target area through double canvas rendering; a dynamic capture unit for capturing a dynamic object appearing in the target area, and triggering a control instruction for tracking and magnifying the dynamic object if the dynamic object is captured; a tracking magnification unit for synchronously tracking a real-time magnification picture of the target area. ​ A display unit is configured to display the live base video rendered by the video rendering unit and the picture of the target area after zooming.

8. The tracking amplification device of claim 7, wherein, The tracking zooming device further comprises a background service unit configured to transmit the video stream acquired by the video stream acquisition unit to the video rendering unit, and transmit the data rendered by the video rendering unit to the display unit; and start the dynamic capture unit and the tracking zooming unit, and transmit the real-time zooming picture of the tracking zooming unit to the display unit.

9. A computer device, comprising: A computer program product comprising a memory, a processor, and a computer program stored on the memory and loadable on the processor, the processor being configured to execute the computer program to implement the tracking zooming method according to any one of claims 1-6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method according to any one of claims 1-6.

Images