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

Single sample-based behavior detection and recognition method

A recognition method and a single-sample technology, applied in the field of video recognition, can solve problems such as high complexity and not suitable for real-time application scenarios

Inactive Publication Date: 2018-04-13
CHONGQING UNIV OF POSTS & TELECOMM
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are few existing studies on behavior recognition algorithms based on single samples, and most of them use feature extraction and matching algorithms with high complexity, so they are not suitable for application scenarios with high real-time requirements.

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
  • Single sample-based behavior detection and recognition method
  • Single sample-based behavior detection and recognition method
  • Single sample-based behavior detection and recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] The present invention is used to provide a behavior detection and recognition method based on a single sample. In order to make the purpose, technical solution and effect of the present invention more clear and definite, the present invention will be further described in detail below.

[0013] (1) The important information that can represent the behavior in the video is concentrated on the implementer of the behavior, that is, the moving human body in the video. In order to ensure the correct recognition of the behavior in the video, the interest point detection method we choose must ensure that a sufficient number of effective interest points are extracted from the moving human body. Because the executor has obvious contour information compared with the background, it is a good choice to extract the feature points on the contour of the moving target. Commonly used detection methods include SIFT feature points and Harris corner points, but the complexity of SIFT feature...

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 single sample-based behavior detection and recognition method, and aims at rapidly judging whether behaviors occur in videos. The method comprises the following steps of: matching feature points of a moving target, and voting displacement information corresponding to the feature points to generate a displacement histogram so as to represent the behaviors; and judging thebehaviors by adoption of matrix cosine similarity method. Experiments prove that the method is capable of rapidly and effectively detecting and recognizing behaviors in videos under fixed static scenes of cameras.

Description

technical field [0001] The invention relates to video recognition technology, in particular to a single-sample-based behavior detection and recognition method in video. Background technique [0002] With the development of society and the enhancement of people's safety awareness, video surveillance systems have been widely used in all walks of life. At the same time, the rapid rise of artificial intelligence has made people's demand for intelligent monitoring research and development unprecedentedly expanded. The detection and recognition of behavior in video is the focus and difficulty of research in intelligent video surveillance. When it is difficult to collect behavior samples, it is very meaningful to study the detection and recognition of behavior in video using few or even a single sample. This paper proposes a behavior detection and recognition method based on a single sample, which can quickly judge whether such behavior appears in the video. The method characteri...

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
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06T7/254
CPCG06T7/254G06V20/46G06V10/507G06F18/22
Inventor 黄俊张磊
Owner CHONGQING UNIV OF POSTS & TELECOMM
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com