Browse > Article

Robust Gait Recognition for Directional Variation Using Canonical View Synthesis  

정승도 (한양대학교 전자통신전파공학과)
최병욱 (한양대학교 정보통신대학 정보통신학부)
Publication Information
Journal of the Institute of Electronics Engineers of Korea CI / v.41, no.5, 2004 , pp. 59-67 More about this Journal
Abstract
Gait is defined as a manner or characteristics of walking. Recently, the study on extracting features of the gait to identify the individual has been progressed actively, within the computer vision community. Even if the camera is fixed, gait features extracted from images are varied according to the direction of walking. In this paper, we propose the method which compensates for the drawback of the gait recognition which is dependant on the direction. First, we search a direction of walking and estimate the planar homography with simple operations. Through synthesizing canonical viewed images by using the estimated homography, viewpoint variation by the direction of walking is compensated. In this paper, we segment gait silhouette into sub-regions and use averaged feature and its variation of each region to recognition experiment. Experimental results show that the proposed method is robust for directional variation of the gait.
Keywords
Gait Recognition; View Synthesis; Planar Homography; Canonical View;
Citations & Related Records
연도 인용수 순위
  • Reference
1 A. K. RoyChowdhury, A. Kale, R. Chellappa, Video Synthesis of Arbitrary Views for Approximately Planar Scenes, In Proc. of IEEE Conf. on Acoustics, Speech and Signal Processing, Vol, 3, pp. 497-500, Hong Kong, April 2003   DOI
2 J. J. Little and J. E. Boyd, Recognizing people by their gait: the shape of motion, Videre: Journal of Computer Vision Research, Vol. 1, no. 2, pp. 2-32, MIT Press, 1998
3 L. Lee, W. E. L. Grimson, Gait Appearance for Recognition, Biometric Authentication, Int. ECC V 2002 Workshop, pp. 143-154, Copenhagen, Denmark, June 2002
4 R. Hartley, A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2000
5 A. Winter, The Biomechanics and motor Control of Human Movement, 2nd Eds., John Wiley & Sons, 1990
6 A. W. Fitzgibbon, R. B. Fisher, A Buyer's Guide to Conic Fitting, In Proc. 5th British Machine Vision Conf., pp. 513-522, Birmingham, UK, 1995
7 D. Cunado, M. Nixon, J. Carter, Gait Extraction and Description by Evidence Gathering, In Proc. of 2nd Int. Conf. on Audio- and Video-based Biometric Person Authentication, Washington D. C. USA, March 1999
8 R. Gross, J. Shi, The CMU Motion of Body(MoBo) Database, Tech report CMU-RI-TR-01-08, Robotics Institute, CMU, June 2001
9 C. BenAbdelkader, R. Cutler, View-invariant Estimation of Height and Stride for Gait Recognition, Biometric Authentication, Int. ECCV 2002 Workshop, pp. 155-167, Copenhagen, Denmark, June 2002