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

Multi-visual angle gait recognition method and system based on higher-order tensor subspace learning

A gait recognition and multi-view technology, applied in the field of intelligent recognition, can solve problems such as difficult to conceal or camouflage gait characteristics, achieve better recognition accuracy, effective methods, and eliminate interference factors

Active Publication Date: 2017-07-07
CHONGQING UNIV OF POSTS & TELECOMM
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

and it is very difficult for a person to disguise or camouflage his gait characteristics

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
  • Multi-visual angle gait recognition method and system based on higher-order tensor subspace learning
  • Multi-visual angle gait recognition method and system based on higher-order tensor subspace learning
  • Multi-visual angle gait recognition method and system based on higher-order tensor subspace learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] In one embodiment of the present invention, a multi-view gait recognition method based on high-order tensor space learning is provided, see figure 1 , the method process includes:

[0052] S1. Obtain multi-view gait images to form a gait image set.

[0053] Specifically, the initial form of gait data is generally in the form of video. There are two ways to obtain gait data. The first way is to shoot gait video data by yourself, and take an angle according to several special angles or every other constant. The first way is to obtain gait videos from multiple representative angles, and obtain gait sequence images after frame-by-frame interception; the second way is to directly use well-known gait databases, such as the CASIA gait database of the Institute of Automation, Chinese Academy of Sciences, The gait video was acquired every 18°, and the gait sequence images were obtained after frame-by-frame interception.

[0054] S2. Perform image preprocessing to obtain a cont...

Embodiment 2

[0069] In one embodiment of the present invention, a multi-view gait recognition system based on high-order tensor space learning is provided, see Figure 5 , the system includes:

[0070] The angle of view division module 310 is configured to acquire multi-angle gait images, and multiple gait images form a gait image set.

[0071] Specifically, the viewing angle division module 310 includes a gait video acquisition unit 311 and a frame-divided interception unit 312, and the gait video acquisition unit 311 is used to shoot gait video data according to multiple specific angles or every certain angle at intervals, or , acquire gait video data from the target gait database; the frame segmentation and intercepting unit 312 is used to segment the gait video data in units of frames to obtain gait images.

[0072] The pre-processing module 320 is configured to pre-process each gait image to obtain a sequence of contours from corresponding perspectives.

[0073] Specifically, the prep...

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 multi-visual angle gait recognition method and a system based on higher-order tensor subspace learning, which belong to the field of intelligent recognition. A gait video is acquired from multiple representational angles, and a gait sequence image is obtained through framing interception; background extraction, background subtraction and binary processing are carried out on the gait sequence image respectively, black and white visual effects are presented, and a contour sequence under the multiple visual angles is obtained; the contour sequence is converted to tensor data; a higher-order discriminant tensor subspace analysis algorithm based on graph embedding obtained after expanding DTSA on the basis of multilinear discriminant analysis and a graph embedding principle is used for carrying out dimension reduction and feature extraction on the tensor data; and according to the extracted and obtained multi-visual angle gait features, the gait features are subjected to similarity measurement, and a recognition result is obtained. The method is simple, the cost is low, person identity authority detection and disguised person identity authentication can be automatically carried out on a particular place, and safety protection on the monitored place and identity authentication in multiple conditions can be effectively improved.

Description

technical field [0001] The invention relates to the field of intelligent recognition, in particular to a multi-view gait recognition method and system based on high-order tensor quantum space learning. Background technique [0002] With the rapid development of today's computer and network communication technology, information security issues are becoming increasingly prominent. In places that are sensitive to security issues, such as airports, military bases and banks, any illegal use, theft or tampering of information will bring huge losses. Traditional identification methods, such as passwords Cards, smart cards, and ID cards, etc., have been widely used, but there are also many problems related to safety hazards, such as loss, transfer, counterfeiting, etc., and the reliability is getting lower and lower. With the development of modern science and technology With the advancement of society, traditional identification methods can no longer meet certain security requireme...

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): G06K9/00G06K9/60
CPCG06V40/25G06V10/20
Inventor 刘洪涛刘光军蹇洁刘媛媛雷大江
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