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

Video Behavior Recognition Method Based on Intelligent High-Level Semantics

A high-level semantic and behavioral technology, applied in the field of video processing, can solve problems such as manpower consumption and increased computational complexity

Active Publication Date: 2021-09-10
XIDIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the learning method of this new attribute needs to traverse all samples, and manually define new attributes according to the confused samples, which will greatly increase the human consumption and computational complexity.

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 Behavior Recognition Method Based on Intelligent High-Level Semantics
  • Video Behavior Recognition Method Based on Intelligent High-Level Semantics
  • Video Behavior Recognition Method Based on Intelligent High-Level Semantics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] refer to figure 1 , the video behavior recognition method based on intelligent high-level semantics of the present invention, the steps are as follows:

[0037] Step 1, obtain the artificially defined high-level semantic set H Set .

[0038] Extract video behavior features and apply them to behavior recognition to obtain the confusion matrix. For the confusion matrix, artificially define the high-level semantics that can distinguish confusing behaviors, and obtain the artificially defined high-level semantic set H Set ;

[0039] Step 2, for the artificially defined high-level semantic set H Set Quantitative assessments of expressivity and discriminability were performed.

[0040] (2.1) For the artificially defined high-level semantic set H obtained in step 1 Set , set the corresponding positive and negative samples:

[0041] If a certain type of video behavior contains a certain high-level semantics, the label of this type of video behavior is set to 1, and it is ...

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 discloses a video behavior recognition method based on intelligent high-level semantics, which mainly solves the problem of low recognition rate caused by incomplete high-level semantics. The implementation plan is: 1) Extract video behavior features, conduct behavior recognition, and obtain confusion matrix; 2) Aiming at confusion matrix, artificially define a high-level semantic set that can distinguish confusing behavior; 3) Expressiveness and Discriminative quantitative evaluation; 4) Use genetic algorithm to obtain a more complete set of high-level semantics, and train and learn more complete high-level semantic features; 5) Input more complete high-level semantic features into the SVM classifier to obtain behavior recognition the result of. The intelligent high-level semantics of the invention has better discrimination, effectively improves the accuracy of video behavior recognition, and can be used for video monitoring.

Description

technical field [0001] The invention belongs to the technical field of video processing, and in particular relates to a video behavior recognition method, which is used for video retrieval, intelligent monitoring, robot navigation, intelligent transportation, human-computer interaction and video monitoring security for game entertainment. Background technique [0002] In recent years, computer vision has developed rapidly as an emerging discipline. Behavior recognition, as a key technology for video analysis and understanding, has important academic value, potential commercial value and huge application prospects, making it quickly become a research area in the field of computer vision. Hotspots and difficulties have been widely used in human-computer interaction fields such as video retrieval, intelligent monitoring, robot navigation, intelligent transportation, and game entertainment. More and more scholars and institutions have carried out a lot of research work in related...

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): G06K9/00G06K9/62
CPCG06V20/40G06V20/52G06F18/2411G06F18/214
Inventor 同鸣郭志强陈逸然闫娜
Owner XIDIAN UNIV