Unlock instant, AI-driven research and patent intelligence for your innovation.

A video processing method and device

A video processing and video frame technology, applied in the computer field, can solve problems such as low user experience, and achieve the effect of reducing user burden, improving user experience, and reducing page views

Active Publication Date: 2021-10-12
ZTE CORP
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] A video processing method and device provided by the embodiment of the present invention mainly solves the technical problem: in the existing video processing scheme, video frames with motion information are reserved for users to browse through motion detection technology, resulting in users needing to browse a large number of videos , resulting in poor user experience

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A video processing method and device
  • A video processing method and device
  • A video processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] In order to solve the problem in existing video processing schemes that video frames with motion information are reserved for users to browse through motion detection technology, resulting in users needing to browse a large number of videos and resulting in low user experience, the present invention provides a video processing method, please refer to figure 1 A flow chart of the video processing method shown:

[0030] S102. Perform object recognition on video frames in the basic video, and generate set information for each video frame according to the recognition result.

[0031] The so-called target usually refers to a monitored object that the user is more interested in, such as a person, a pet, and the like. It should be understood that still life, such as household electrical appliances, furniture, etc., will not change in any spatial position all the year round without the action of manpower, so the user installs a surveillance camera in fact not to monitor the sti...

Embodiment 2

[0064] This embodiment will further introduce the video processing method provided by the present invention, especially elaborate the process of aggregating structured semantic information, please refer to figure 2 A flow chart of the video processing method shown:

[0065] S202. Perform motion information detection on each video frame in the original video, and obtain a basic video after screening video frames that do not contain motion information in the original video.

[0066] Since the reasons and methods for screening out video frames that do not contain motion information are explained in detail in Embodiment 1, details will not be repeated here.

[0067] S204. Perform object recognition on the video frames in the basic video, and generate set information for each video frame according to the recognition result.

[0068] Similar to Embodiment 1, the set information of a video frame includes structured semantic information of each object in the video frame. In this em...

Embodiment 3

[0111] This embodiment will further introduce the video processing method in the foregoing embodiments in combination with specific examples, please refer to Figure 6 :

[0112] S602. Obtain the basic video from the original video by using an inter-frame difference method.

[0113] Basic Video A collection of video frames that contain motion information in the original video. For the luminance component Y of the original video, the video frame containing motion information in the original video is detected by using the inter-frame difference method. For example, set the threshold T according to the empirical value diff , for a certain video frame, calculate the average absolute deviation value AvgDiff between the video frame and the adjacent previous video frame or multiple video frames, if AvgDiff exceeds the set threshold T diff , the video frame is considered to be a video frame containing motion information, otherwise the video frame is considered not to contain motion...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the present invention provides a video processing method and device, by identifying the video frames in the basic video and generating the set information containing the structured semantic information of each target, and then according to the time information corresponding to each video frame, each video frame Divide into the corresponding time group, aggregate the structured semantic information corresponding to each video frame in the time group, obtain the structured semantic information in the group, and convert the image information recorded in the basic video frame into a structure containing time information The semantic information of each target is aggregated within a time period by taking advantage of the continuous characteristics of target activities to obtain the structured semantic information within the group within the time period. When users need to understand the video information recorded in the basic video, they can basically understand the information recorded in the basic video based on the structured semantic information in the group corresponding to each time period, which greatly reduces the number of user views and reduces the burden on users , which improves the user experience.

Description

technical field [0001] The invention relates to the field of computers, in particular to a video processing method and device. Background technique [0002] In the field of security, video surveillance is a very important means, and it is also the most widely used solution. For example, in the field of public transportation, commercial and civilian anti-theft fields, etc., surveillance cameras can be seen everywhere. Since surveillance cameras always objectively record the images in the area they monitor, they can provide credible evidence when people conduct retrospective inquiries. But it is precisely because the surveillance cameras will objectively record all the pictures, so the videos captured by many cameras contain more useless information, which is especially prominent in the field of civil security: for example, if users want Recorded video to understand what happened at home on Monday, the user needs to fully browse all the videos recorded by the camera on Monday...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04N7/18H04N21/44H04N21/4545H04N5/232G06K9/00
CPCH04N7/18H04N21/44008H04N21/45457G06V20/41H04N23/80
Inventor 王勃飞
Owner ZTE CORP