Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for recognizing semantics of events in video

A technology in semantic recognition and video, applied in instrumentation, computing, electrical digital data processing, etc.

Inactive Publication Date: 2010-05-19
WUHAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0015] The technical problem to be solved by the present invention is to decompose a complex video event semantics into several unit event semantics, and regard each unit event as a Markov "state"

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
  • Method for recognizing semantics of events in video
  • Method for recognizing semantics of events in video
  • Method for recognizing semantics of events in video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] Below in conjunction with accompanying drawing and take the shooting event in the football match as example the present invention will be described in further detail:

[0062] For the event semantic concept of "shooting in a football game", we identified three semantic objects of interest, people, football, and ball frame, and directly divided them into three categories according to their motion states, and constructed the minimum convex polygon of each category . In the initial video segment, only two semantic object classes, person and football, are included, so we use them as description units in unit events. According to the motion state classification shown in Figure 1, we select the motion relationship classification rules between objects. In the first video segment, the object of interest is a person and a football, and their motion relationship is close, that is, the semantics of the unit event "person approaching the football"; in the second video segment, the...

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

A method for identifying event semanteme in video includes treating normal event semanteme in video as a multi-element event semanteme formed by a numbers of unit event semantemes being used to describe foreground object region identified from video, utilizing Markov chain iteration calculation by multi-element event semanteme to obtain stable distribution of unit event semanteme contained in saidmulti-element event semanteme for realizing automatic identification of video event semanteme in mode of stage by stage.

Description

technical field [0001] The invention relates to the fields of multimedia data mining, artificial intelligence and the like, in particular to a method for realizing event semantic recognition in video by using the principle of Markov chain. Background technique [0002] With the explosive growth of the number and capacity of video files on the Internet and personal computers, how to quickly and accurately retrieve video files consistent with user wishes has become more and more important. At present, keyword-based retrieval technology has been widely adopted by commercial search engines; content-based image and video retrieval systems [1] It has also been born in some research institutions. However, these technologies rely too much on human participation, or the retrieval results are contrary to user needs, and cannot meet the retrieval requirements of a large amount of multimedia data. [0003] Video semantic mining is to mine potential semantic information similar to huma...

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): G06F17/30
Inventor 曾承彭智勇
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products