Automatic gait recognition using dynamic variance features

Y. Chai, Jinchang Ren, R. Zhao, J. Jia

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

8 Citations (Scopus)

Abstract

Human gait recognition is currently one of the most active research topics in computer vision. Existing recognition methods suffer, in our opinion, from two shortcomings: either much expensive computation or poor identification effect; thus a new method is proposed to overcome these shortcomings. Firstly, we detect the binary silhouette of a walking person in each of the monocular image sequences. Then, we extract the pixel values at the same pixel position over one gait cycle to form a dynamic variation signal (DVS). Next, the variance features of all the DVS are computed respectively and a matrix is constructed to describe the dynamic gait signature of individual. Finally, the correlation coefficient measure based on the gait cycles and two different classification methods (NN and KNN) are used to recognize different subjects. Experimental results show that our method is not only computing efficient, but also very effective of correct recognition rates over 90% on both UCSD and CMU databases

Index Terms

* INSPEC
o Controlled Indexing

computer vision , feature extraction , gait analysis , image classification , image resolution , image sequences , video databases
o Non Controlled Indexing

automatic gait recognition , computer vision , dynamic gait signature , dynamic variation signal , feature extraction , human gait recognition , image classification methods , image resolution , monocular image sequences , walking person binary silhouette

ON THIS PAGE

* Abstract
* Index Terms

Brought to you by
STRATHCLYDE UNIVERSITY LIBRARY

* Your institute subscribes to:
* IEEE-Wiley eBooks Library , IEEE/IET Electronic Library (IEL)
* What can I access?

Terms of Use

LanguageEnglish
Title of host publicationProceedings of 7th International Conference of Automatic Face and Gesture Recognition (FG2006)
Place of PublicationSouthampton, UK
PublisherIEEE
Pages475-480
DOIs
Publication statusPublished - 2006

Fingerprint

Computer vision
Image classification
Image resolution
Feature extraction
Automatic indexing
Pixels
Gait analysis

Keywords

  • face recognition
  • gait recognition

Cite this

Chai, Y., Ren, J., Zhao, R., & Jia, J. (2006). Automatic gait recognition using dynamic variance features. In Proceedings of 7th International Conference of Automatic Face and Gesture Recognition (FG2006) (pp. 475-480). Southampton, UK: IEEE. https://doi.org/10.1109/FGR.2006.24
Chai, Y. ; Ren, Jinchang ; Zhao, R. ; Jia, J. / Automatic gait recognition using dynamic variance features. Proceedings of 7th International Conference of Automatic Face and Gesture Recognition (FG2006). Southampton, UK : IEEE, 2006. pp. 475-480
@inproceedings{e76b8b4a89604085998f54ee90764d17,
title = "Automatic gait recognition using dynamic variance features",
abstract = "Human gait recognition is currently one of the most active research topics in computer vision. Existing recognition methods suffer, in our opinion, from two shortcomings: either much expensive computation or poor identification effect; thus a new method is proposed to overcome these shortcomings. Firstly, we detect the binary silhouette of a walking person in each of the monocular image sequences. Then, we extract the pixel values at the same pixel position over one gait cycle to form a dynamic variation signal (DVS). Next, the variance features of all the DVS are computed respectively and a matrix is constructed to describe the dynamic gait signature of individual. Finally, the correlation coefficient measure based on the gait cycles and two different classification methods (NN and KNN) are used to recognize different subjects. Experimental results show that our method is not only computing efficient, but also very effective of correct recognition rates over 90{\%} on both UCSD and CMU databasesIndex Terms * INSPEC o Controlled Indexing computer vision , feature extraction , gait analysis , image classification , image resolution , image sequences , video databases o Non Controlled Indexing automatic gait recognition , computer vision , dynamic gait signature , dynamic variation signal , feature extraction , human gait recognition , image classification methods , image resolution , monocular image sequences , walking person binary silhouetteON THIS PAGE * Abstract * Index TermsBrought to you bySTRATHCLYDE UNIVERSITY LIBRARY * Your institute subscribes to: * IEEE-Wiley eBooks Library , IEEE/IET Electronic Library (IEL) * What can I access? Terms of Use",
keywords = "face recognition, gait recognition",
author = "Y. Chai and Jinchang Ren and R. Zhao and J. Jia",
year = "2006",
doi = "10.1109/FGR.2006.24",
language = "English",
pages = "475--480",
booktitle = "Proceedings of 7th International Conference of Automatic Face and Gesture Recognition (FG2006)",
publisher = "IEEE",

}

Chai, Y, Ren, J, Zhao, R & Jia, J 2006, Automatic gait recognition using dynamic variance features. in Proceedings of 7th International Conference of Automatic Face and Gesture Recognition (FG2006). IEEE, Southampton, UK, pp. 475-480. https://doi.org/10.1109/FGR.2006.24

Automatic gait recognition using dynamic variance features. / Chai, Y.; Ren, Jinchang; Zhao, R.; Jia, J.

Proceedings of 7th International Conference of Automatic Face and Gesture Recognition (FG2006). Southampton, UK : IEEE, 2006. p. 475-480.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Automatic gait recognition using dynamic variance features

AU - Chai, Y.

AU - Ren, Jinchang

AU - Zhao, R.

AU - Jia, J.

PY - 2006

Y1 - 2006

N2 - Human gait recognition is currently one of the most active research topics in computer vision. Existing recognition methods suffer, in our opinion, from two shortcomings: either much expensive computation or poor identification effect; thus a new method is proposed to overcome these shortcomings. Firstly, we detect the binary silhouette of a walking person in each of the monocular image sequences. Then, we extract the pixel values at the same pixel position over one gait cycle to form a dynamic variation signal (DVS). Next, the variance features of all the DVS are computed respectively and a matrix is constructed to describe the dynamic gait signature of individual. Finally, the correlation coefficient measure based on the gait cycles and two different classification methods (NN and KNN) are used to recognize different subjects. Experimental results show that our method is not only computing efficient, but also very effective of correct recognition rates over 90% on both UCSD and CMU databasesIndex Terms * INSPEC o Controlled Indexing computer vision , feature extraction , gait analysis , image classification , image resolution , image sequences , video databases o Non Controlled Indexing automatic gait recognition , computer vision , dynamic gait signature , dynamic variation signal , feature extraction , human gait recognition , image classification methods , image resolution , monocular image sequences , walking person binary silhouetteON THIS PAGE * Abstract * Index TermsBrought to you bySTRATHCLYDE UNIVERSITY LIBRARY * Your institute subscribes to: * IEEE-Wiley eBooks Library , IEEE/IET Electronic Library (IEL) * What can I access? Terms of Use

AB - Human gait recognition is currently one of the most active research topics in computer vision. Existing recognition methods suffer, in our opinion, from two shortcomings: either much expensive computation or poor identification effect; thus a new method is proposed to overcome these shortcomings. Firstly, we detect the binary silhouette of a walking person in each of the monocular image sequences. Then, we extract the pixel values at the same pixel position over one gait cycle to form a dynamic variation signal (DVS). Next, the variance features of all the DVS are computed respectively and a matrix is constructed to describe the dynamic gait signature of individual. Finally, the correlation coefficient measure based on the gait cycles and two different classification methods (NN and KNN) are used to recognize different subjects. Experimental results show that our method is not only computing efficient, but also very effective of correct recognition rates over 90% on both UCSD and CMU databasesIndex Terms * INSPEC o Controlled Indexing computer vision , feature extraction , gait analysis , image classification , image resolution , image sequences , video databases o Non Controlled Indexing automatic gait recognition , computer vision , dynamic gait signature , dynamic variation signal , feature extraction , human gait recognition , image classification methods , image resolution , monocular image sequences , walking person binary silhouetteON THIS PAGE * Abstract * Index TermsBrought to you bySTRATHCLYDE UNIVERSITY LIBRARY * Your institute subscribes to: * IEEE-Wiley eBooks Library , IEEE/IET Electronic Library (IEL) * What can I access? Terms of Use

KW - face recognition

KW - gait recognition

U2 - 10.1109/FGR.2006.24

DO - 10.1109/FGR.2006.24

M3 - Conference contribution book

SP - 475

EP - 480

BT - Proceedings of 7th International Conference of Automatic Face and Gesture Recognition (FG2006)

PB - IEEE

CY - Southampton, UK

ER -

Chai Y, Ren J, Zhao R, Jia J. Automatic gait recognition using dynamic variance features. In Proceedings of 7th International Conference of Automatic Face and Gesture Recognition (FG2006). Southampton, UK: IEEE. 2006. p. 475-480 https://doi.org/10.1109/FGR.2006.24