Frame difference energy image for gait recognition with incomplete silhouettes

被引：198

作者：

Chen, Changhong ^{[1
]}

Liang, Jimin ^{[1
]}

Zhao, Heng ^{[1
]}

Hu, Haihong ^{[1
]}

Tian, Jie ^{[1
,2
]}

机构：

[1] Xidian Univ, Life Sci Res Ctr, Sch Elect Engn, Xian 710071, Peoples R China

[2] Chinese Acad Sci, Ctr Biometr & Secur Res, Key Lab Complex Syst & Intelligence Sci, Inst Automat, Beijing 100190, Peoples R China

来源：

PATTERN RECOGNITION LETTERS | 2009年 / 30卷 / 11期

关键词：

Gait recognition; Incomplete silhouettes; Frame difference energy image; Hidden Markov model;

D O I：

10.1016/j.patrec.2009.04.012

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The quality of human silhouettes has a direct effect on gait recognition performance. This paper proposes a robust dynamic gait representation scheme, frame difference energy image (FDEI), to suppress the influence of silhouette incompleteness. A gait cycle is first divided into clusters. The average image of each cluster is denoised and becomes the dominant energy image (DEI). FDEI representation of a frame is constructed by adding the corresponding cluster's DEI and the positive portion of the frame difference between the former frame and the current frame. FDEI representation can preserve the kinetic and static information of each frame, even when the silhouettes are incomplete. This proposed representation scheme is tested on the CMU Mobo gait database with synthesized occlusions and the CASIA gait database (dataset B). The frieze and wavelet features are adopted and hidden Markov model (HMM) is employed for recognition. Experimental results show the superiority of FDEI representation over binary silhouettes and some other algorithms when occlusion or body portion lost appears in the gait sequences. (C) 2009 Elsevier B.V. All rights reserved.

引用

页码：977 / 984

页数：8

共 21 条

[1]

[Anonymous], 2001, CMU MOTION BODY MOBO

[2] Gait recognition: A challenging signal processing technology for biometric identification [J].

Boulgouris, NV ;

Hatzinakos, D ;

Plataniotis, KN .

IEEE SIGNAL PROCESSING MAGAZINE, 2005, 22 (06) :78-90

[3]

Chen CH, 2006, LECT NOTES COMPUT SC, V4221, P399

[4] Gait analysis for human identification through manifold learning and HMM [J].

Cheng, Ming-Hsu ;

Ho, Meng-Fen ;

Huang, Chung-Lin .

PATTERN RECOGNITION, 2008, 41 (08) :2541-2553

[5]

Clark A.F., 1999, PERFORMANCE CHARACTE

[6]

Elgammal A., 2000, COMPUTER VISION ECCV, V1843

[7]

Friedman N., 1997, PROC UNCERTAINTY ART, P175

[8] Individual recognition using Gait Energy Image [J].

Han, J ;

Bhanu, B .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (02) :316-322

[9]

Kale A., 2002, INT C AC SPEECH SIGN, P706

[10]

Little J. J., 1998, Videre, V1

← 1 2 3 →