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

Cross-angle gait recognition method bases on multi-coupling discrimination local block alignment

A gait recognition and local block technology, applied in the field of pattern recognition and machine learning, can solve problems such as complex post-calculation, complex camera calibration, expensive environment, etc., and achieve the effect of reducing the amount of calculation, improving recognition performance, and improving robustness

Inactive Publication Date: 2016-12-07
SHANDONG UNIV
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods have certain disadvantages. First, they are only suitable for fully controlled multi-camera environments, which are too expensive and complex; second, they require very complicated camera calibration; moreover, they require complex post-processing calculate

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
  • Cross-angle gait recognition method bases on multi-coupling discrimination local block alignment
  • Cross-angle gait recognition method bases on multi-coupling discrimination local block alignment
  • Cross-angle gait recognition method bases on multi-coupling discrimination local block alignment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] A cross-angle gait recognition method based on multi-coupling discriminative local block alignment, including online training and offline testing;

[0063] Described online training comprises the steps:

[0064] First, use principal component analysis to perform feature extraction on gait energy map sample sets under different perspectives, and construct gait energy map features from different perspectives; Analyze and extract the gait energy map features of each viewing angle; among them, viewing angles I, II, and III refer to viewing angles at different angles, and different viewing angle values ​​can be assigned to them;

[0065] Then, look for similar neighbors and heterogeneous neighbors of the gait energy map features of the same person across angles; look for similar neighbors and heterogeneous neighbors of the same person's gait energy map features across angles, so that the k of a certain gait energy map feature 1 The distance between the nearest neighbor samp...

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 provides a cross-angle gait recognition method bases on multi-coupling discrimination local block alignment, including online training and offline testing. Compared with other recognition methods, the method provided by the invention is better in recognition performance, and does not require completely-controlled environments and complicated camera calibration. In addition, the method provided by the invention does not require inverse operation of a matrix, so that the operand is reduced, and the small sample problem is reduced. The method is a cross-domain gait recognition method with high robustness properties.

Description

technical field [0001] The invention relates to a cross-angle gait recognition method based on multi-coupling discrimination and local block alignment, which belongs to the field of pattern recognition and machine learning. Background technique [0002] In recent years, the identification and identification technology using invariant biological characteristics of the human body has developed rapidly, and it has shown good application prospects in the fields of security monitoring, case investigation, network security, military, business and even entertainment. The technology of identity authentication using biometric features such as face, fingerprint, iris, vein, and retina has developed earlier and is relatively mature at present, while the research on gait started relatively late, and there are a lot of problems to be solved. Gait characteristics refer to the characteristics of a person's posture when walking. It is one of the few biological characteristics that can be me...

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): G06K9/00G06K9/62
CPCG06V40/25G06F18/24143
Inventor 贲晛烨贾希彤张鹏庞建华冯云聪赵子君
Owner SHANDONG 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

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