Video structuring method based on multi-dimensional segmentation

A video structure and video technology, applied in the field of video structuring, can solve problems such as crossover and incomplete alignment of videos, and achieve the effect of reducing complexity and good segmentation

Active Publication Date: 2019-09-03
BEIJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The videos obtained by splitting in these three dimensions cannot be completely aligned, and there will be intersections

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
  • Video structuring method based on multi-dimensional segmentation
  • Video structuring method based on multi-dimensional segmentation
  • Video structuring method based on multi-dimensional segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] specific implementation plan

[0049] The present invention will be described in further detail below through examples of implementation.

[0050] The implementation steps of the technical solution are as follows:

[0051] Step 1: Video analysis.

[0052] The first step in video parsing is data reception. It is necessary to demultiplex the video and decompose it into image track, audio track, and subtitle track.

[0053] Demultiplex the traffic surveillance video somewhere in Beijing. The video is 1 minute and 50 seconds long, and it is decomposed into image track, audio track and subtitle track. The decomposed audio track and subtitle track are 1 minute and 50 seconds long.

[0054] Step 2: Keyframe extraction in scene segmentation.

[0055] The key frame extraction methods are mainly divided into five categories, the specific methods are as follows: figure 2 shown.

[0056] (1) Extract keyframes based on boundaries. This method directly selects the first frame an...

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 invention mainly provides a video structuring method based on multi-dimensional segmentation. The video structuring method specifically comprises the steps of 1, analyzing a video; 2, extracting akey frame in scene segmentation; 3, segmenting the scene based on the key frame; 4, segmenting the video audio; 5, performing semantic segmentation on the video; and 6, taking the information entropyas a segmentation rule of an objective function. According to the invention, after the same video segment is segmented in three dimensions of scene, sound and text, the segmentation rule is evaluatedin the form of information entropy. Compared with other video structuring methods, the video is well segmented in the image dimension by combining the change of the pixels in the image sequence in the time domain, the correlation between the adjacent frames and the corresponding relation between the previous frame and the current frame, the key information of the video is reserved, and an effective video structuring method can be provided.

Description

technical field [0001] The invention mainly relates to a video structuring method, in particular to a video structuring method based on multi-dimensional segmentation. Background technique [0002] At present, most of the video structuring problems are segmented on the single-dimensional element of the image, and the research on video structuring methods based on multi-dimensional segmentation is less involved. In practice, the audio information and text information contained in the video also play an important role in the video surveillance work. In addition, when segmenting and extracting key frames from moving objects in the video, in order to consider the problem of computational efficiency, only a certain frame in the video is taken as the key frame, and the important information contained in the video is often ignored, or by setting the threshold The above methods do not consider the changes of pixels in the image sequence in the time domain, the correlation between a...

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 Applications(China)
IPC IPC(8): G06K9/00
CPCG06V20/42G06V20/49G06V20/46G06V20/41G06V20/40
Inventor 胡燕祝田雯嘉
Owner BEIJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap