WO2019237752A1

WO2019237752A1 - Video tag locating method

Info

Publication number: WO2019237752A1
Application number: PCT/CN2019/073563
Authority: WO
Inventors: 邸磊
Original assignee: 视云融聚（广州）科技有限公司
Priority date: 2018-06-14
Filing date: 2019-01-29
Publication date: 2019-12-19
Also published as: CN108769781A; CN108769781B

Abstract

The present invention provides a video tag locating method, comprising the steps of: determining, at a client, a video object to be tagged; creating corresponding tag information according to the attribute of the video object; creating a display mode of the tag information; configuring the tag information; associatedly storing the video object and the tag information; obtaining a ptz value and a field of view of the video object; computing, according to the ptz value and the field of view of the video object, an xy value of the video object in a video channel; storing the xy value of the video object; when it is required to output the current video, obtaining a ptz value and a field of view recorded by a tag of the current video; computing, according to the ptz value and the field of view of the current video, an xy value of the current video in the video channel; determining, according to the xy value of the current video in the video channel, whether the current video is within a display range of the video channel; if yes, superimposing the corresponding tag information on the current video for display; and if not, not displaying the tag information on the current video.

Description

Video label positioning method

Technical field

The present invention relates to the field of video technology, and in particular, to a video label positioning method.

Background technique

Generally, the camera is installed outdoors in a relatively harsh environment, so after a period of work, the camera may be damaged, which will cause the tag information added by the user to be lost with the damage of the camera. Although the user can back up the data to the system background and restore the virtual label of the camera after replacing the new camera, there is a brand, manufacturer and even version compatibility issue between the new camera and the old camera. The user is free to choose a new one. The camera is very limited. In addition, because the storage space inside the camera is limited, the number of virtual tags for labeling the content in the video is also limited, usually limited to a few hundred. In addition, because the labeling and reading of the virtual tags are in the camera, for the overall processing and analysis of the background video data, there is a communication process between extracting the virtual tag information from the camera to the background processing server, which results in searching for tag information, etc. When processing, the search is often slow.

Summary of the Invention

Based on this, the purpose of the embodiment of the present invention is to provide a video label positioning method, which solves the limitation of label sticking in the camera. No matter what kind of video from the camera, corresponding label labeling can be implemented in the video stream The tags in the background system server are more conducive to the background service system to search, query, and classify tags, etc., and have stronger and wider usability.

To achieve the above object, the embodiments of the present invention adopt the following technical solutions:

A base video label positioning method, comprising the steps:

Identify the video objects that need to be labeled on the client;

Creating corresponding tag information according to the attributes of the video object;

Creating a display style of the label information;

Configuring the label information;

Associatively store the video object and the tag information;

Obtaining a ptz value and a field angle of the video object;

Calculating the xy value of the video object in the video channel according to the ptz value and the field angle of the video object;

Storing the xy value of the video object;

When the current video needs to be output, obtain the ptz value and field of view of the tag record of the current video;

Calculate the xy value of the current video in the video channel according to the ptz value and the angle of view of the current video;

Determine whether the current video is within the display range of the video channel according to the xy value of the current video on the video channel. If it is, the corresponding tag information is displayed superimposed on the current video; if not, the tag information is not displayed on the current video.

The tag information includes: tag name, tag number, tag description, tag link, tag level, tag type, tag annotation, tag creation date, tag modification date, ptz value of the video, and field of view.

When the corresponding tag information is superimposed and displayed on the current video, the corresponding tag information is superimposed and displayed on the current video according to a preset display mode and display style.

Among them, the display style of different label information is different.

Among them, different label information is displayed in different ways.

With the solution of the present invention, the limitation of labeling in the camera is solved. No matter what kind of video from the camera, the corresponding labeling can be realized in the video stream. There is no limitation on labeling. Because the background system is stable, it is not affected by Due to the harsh environment of the outdoor camera, the labeled labels are not easy to lose. At the same time, the labeled labels are in the background system server, which is more conducive to the background service system's processing of label searching, querying, classification, etc., and has stronger and wider usability.

BRIEF DESCRIPTION OF THE DRAWINGS

The drawings are used to provide a further understanding of the present invention, and constitute a part of the description. Together with the following specific embodiments, the drawings are used to explain the present invention, but should not constitute a limitation to the present invention. In the drawing,

FIG. 1 is a schematic flowchart of a video tag positioning method according to 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 do not limit the protection scope of the present invention.

FIG. 1 shows a flowchart of a method for positioning a video tag, including steps:

S1. Determine the video objects that need to be labeled on the client;

S2. Create corresponding tag information according to the attributes of the video object.

S3. Create a display style of the label information;

S4. Configure the label information.

S5. Associate storage of the video object and the tag information;

S6. Obtain a ptz value and a field of view of the video object.

S7. Calculate the xy value of the video object in the video channel according to the ptz value and the field angle of the video object;

S8. Store the xy value of the video object;

S9. When the current video needs to be output, obtain the ptz value and the field of view of the tag record of the current video;

S10. Calculate the xy value of the current video in the video channel according to the ptz value and the field of view of the current video.

S11. Determine whether the current video is within the display range of the video channel according to the xy value of the current video in the video channel. If so, proceed to step S12: superimpose and display the corresponding tag information on the current video; if not, proceed to step S13: not Display tag information on the current video.

Specifically, when a user selects a video that needs to be viewed, the streaming server dispatches a video resource and obtains a PTZ value and a field of view according to the video information;

Retrieve tag-related content from the current database record;

Determine whether a video to be viewed is within the display range of the current video according to the PTZ value and the field of view of the tag;

When the tag is within the display range of the current video, the tag information is displayed superimposed on the current video; when the virtual tag is not within the display range of the current video, the display property of the virtual tag is set to hidden.

Steps s1 to s5 are the process of creating a video tag. In the process of creating a video tag, it includes a tag design module, a tag display control module, a tag management module, and a tag database module. The label design module classifies labels into attributes, and completes the style design and label information configuration management of various labels to meet the various functional requirements of clients and management terminals; including label classification submodules, label style management submodules, and label information configuration Submodule. The label display control module controls the positioning and following display of the virtual label in the monitoring video, the label display mode, the label display status, and the display method of the information in the label; including the label positioning follow display control submodule, the label display mode control submodule, and the label display status control The submodule and label information display control the submodule. The label management module implements classified management of labels to meet client requirements, including six sub-modules including label labeling, label editing, label viewing, label filtering, label search and positioning, and label linkage. The tag database presents the hierarchy and logical relationship between tags in a tree structure. You can edit and manage tags at any level, including four parts: tag storage and backup, tag import and export, tag database update, and tag library operation management.

Further, when the corresponding tag information is superimposed and displayed on the current video, the corresponding tag information is superimposed and displayed on the current video according to a preset display mode and display style.

Further, the display styles of different tag information are different.

Further, different tag information is displayed in different ways.

The method for labeling labels in the present invention is processed after the camera video enters the back end of the system server, which can avoid the limitation of the label labeling information of the camera, and the content of labeling the video can be said to be unlimited. At the same time, the labeling is not limited by the source of the video signal. As long as it is a video input, the labeling can be performed, which eliminates the need for the user to replace the camera capable of labeling. Therefore, the present invention makes the user pay less cost . In addition, the tag label information is implemented in the server in the background, which makes it easier to save the tag label information. It will not cause the tag label information to be lost due to a camera failure like the AR camera with a label; nor will it There are restrictions that can only be purchased on a certain model label that indicates the model or product of the camera.

As long as it does not violate the idea of the present invention, any combination of the various embodiments of the present invention should be regarded as the content disclosed by the present invention; within the scope of the technical concept of the present invention, a variety of simple modifications to the technical solution and Any combination of different embodiments without departing from the idea of the present invention should fall within the protection scope of the present invention.

Claims

A video label positioning method is characterized in that it includes steps:

Identify the video objects that need to be labeled on the client;

Creating corresponding tag information according to the attributes of the video object;

Creating a display style of the label information;

Configuring the label information;

Associatively store the video object and the tag information;

Obtaining a ptz value and a field angle of the video object;

Calculating the xy value of the video object in the video channel according to the ptz value and the field angle of the video object;

Storing the xy value of the video object;

When the current video needs to be output, obtain the ptz value and field of view of the tag record of the current video;

Calculate the xy value of the current video in the video channel according to the ptz value and the angle of view of the current video;

Determine whether the current video is within the display range of the video channel according to the xy value of the current video on the video channel. If it is, the corresponding tag information is displayed superimposed on the current video; if not, the tag information is not displayed on the current video.
The video label positioning method according to claim 1, wherein the label information comprises:

Tag name, tag number, tag description, tag link, tag level, tag type, tag annotation, tag creation date, tag modification date, ptz value of the video, and field of view.
The video tag positioning method according to claim 1, wherein when the corresponding tag information is superimposed and displayed on the current video, the corresponding tag information is superimposed and displayed on the current video according to a preset display mode and display style.
The video tag positioning method according to claim 1, wherein different display styles of the tag information are different.
The video label positioning method according to claim 1, wherein different display methods of the label information are different.