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

A View-Independent Gait Recognition Method Based on Deterministic Learning Theory

A technology that determines the learning theory and gait recognition. It is applied in the field of gait recognition that has nothing to do with the viewing angle, and can solve the problems of insufficient robustness to viewing angle changes.

Inactive Publication Date: 2017-10-20
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned existing methods that are not robust to changes in viewing angles, and provide a more concise and accurate recognition based on deterministic learning theory for human gaits under different viewing angles, which can adapt to large-scale viewing angle changes. method

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
  • A View-Independent Gait Recognition Method Based on Deterministic Learning Theory
  • A View-Independent Gait Recognition Method Based on Deterministic Learning Theory
  • A View-Independent Gait Recognition Method Based on Deterministic Learning Theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0065] like figure 1 As shown, a view-independent gait recognition method based on deterministic learning theory, including the following steps:

[0066] Step 1: The preprocessing process is as follows:

[0067] The gait database used in the present invention is the CASIA Dataset B database of the Institute of Automation, Chinese Academy of Sciences. The database contains a total of 124 people, each with 11 different viewing angles (0°, 18°, 36°, 54°, 72°, 90°, 108°, 126°, 144°, 162°, 180°) , 6 sequences of normal walking are taken for each viewing angle, a total of 124×11×6=8184 sequences, three of which are selected as training patterns, and the remaining three sequences are used as test patterns. The original video size is 320×240 pixels, and the sampling frequency is 30Hz. The database has been separated from the background, and the work to be done in the present invention is to perform preprocessing on this basis, thereby performing gait cycle detection and extraction ...

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 gait recognition method independent of viewing angle based on deterministic learning theory, which belongs to the technical field of pattern recognition. The method includes the following steps: preprocessing; feature extraction; based on the extracted gait features, neural network modeling and identification of gait system dynamics under different perspectives in the training set; establishment of a constant value neural network; construction of a dynamic estimator, Using the difference in gait system dynamics between gait patterns under different viewing angles, the accurate classification and recognition of test patterns is realized according to the principle of minimum error. The present invention can realize local accurate modeling and identification of the dynamics of the human gait system under different viewing angles, and at the same time, the gait patterns under different viewing angles can be composed into a unified training gait pattern library, which can overcome the limitations of existing methods for different viewing angles. For gait patterns, it is necessary to construct the corresponding training set for recognition, and realize gait recognition independent of viewing angle, which has higher robustness and practicability.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to a gait recognition method based on deterministic learning theory and independent of viewing angle. Background technique [0002] Human gait recognition, as an emerging biometric technology, aims to find and extract the characteristics of individual changes from the same walking behavior, so as to realize automatic identification. The joint angle changes of human walking motion contain rich individual identification information, and human walking motion largely depends on the shape change of body contour over time. This change reflects the unique movement pattern of the individual, which can be effectively identified. Through the analysis of gait, we can get a variety of useful information such as identity, gender, race and so on. In recent years, as the security situation in public places has become more and more serious, a large number of surveillance c...

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): G06K9/66G06K9/46
Inventor 曾玮胡俊敏王聪
Owner SOUTH CHINA UNIV OF TECH
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