Improved Gender Classification Using Nonpathological Gait Kinematics in Full-Motion Video

Author

Flora, Jeffrey B. ; Lochtefeld, Darrell F. ; Bruening, Dustin A. ; Iftekharuddin, Khan M.

Author_Institution

Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA

Volume

45

Issue

3

fYear

2015

fDate

6/1/2015 12:00:00 AM

Firstpage

304

Lastpage

314

Abstract

In this paper, we exploit nonpathological gait kinematics to improve gender classification from motion information using large-scale datasets with subjects moving in a less controlled environment. Dynamic motion features are extracted from motion capture data using principal component analysis. Features are further refined in the time and spatial domain by exploiting gait phase cycles and significant body part indicators obtained from analyzing nonpathological gait kinematics. Classification is performed using support vector machine with a radial basis function. Experimental testing with a dataset of 49 subjects reveals that human gender classification rates are improved from 73% to 93% using leave-one-out cross validation.

Keywords

feature extraction; gait analysis; image classification; image motion analysis; principal component analysis; radial basis function networks; support vector machines; video signal processing; body part indicators; dynamic motion feature extraction; full-motion video; gait phase cycles; improved gender classification; large-scale datasets; leave-one-out cross validation; motion capture data; motion information; nonpathological gait kinematics; principal component analysis; radial basis function; spatial domain; support vector machine; time domain; Feature extraction; Joints; Kinematics; Legged locomotion; Principal component analysis; Support vector machines; Vectors; Gender classification; human factors; principal component analysis (PCA); support vector machine (SVM);

fLanguage

English

Journal_Title

Human-Machine Systems, IEEE Transactions on

Publisher

ieee

ISSN

2168-2291

Type

jour

DOI

10.1109/THMS.2015.2398732

Filename

7050345