Dual-ellipse fitting approach for robust gait periodicity detection

被引:30
作者
Ben, Xianye [1 ]
Meng, Weixiao [2 ,4 ]
Yan, Rui [3 ]
机构
[1] Shandong Univ, Sch Informat Sci & Engn, Jinan 250100, Shandong, Peoples R China
[2] Harbin Inst Technol, Sch Elect Informat Engn, Harbin 150006, Heilongjiang Pr, Peoples R China
[3] Rensselaer Polytech Inst, Dept Mech Aerosp & Nucl Engn, Troy, NY USA
[4] Harbin Inst Technol, Sch Elect & Commun Engn, Harbin 150006, Heilongjiang Pr, Peoples R China
基金
美国国家科学基金会;
关键词
Gait recognition; Gait period detection; Dual-ellipse fitting; Eccentricity;
D O I
10.1016/j.neucom.2011.10.009
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A new gait period detection algorithm, dual-ellipse fitting (DEF) approach, is proposed. DEF is that two regions of the whole silhouette divided by the centroid are fitted into two ellipses, respectively. We construct the gait fluctuation as a periodic function which depends on the eccentricities of two halves of the silhouette over time. Experimental results show that the proposed method is robust to scale, translation, direction of walking and carrying a bag. (C) 2011 Elsevier B.V. All rights reserved.
引用
收藏
页码:173 / 178
页数:6
相关论文
共 13 条
[1]   Motion-based recognition of people in EigenGait space [J].
BenAbdelkader, C ;
Cutler, R ;
Davis, L .
FIFTH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, PROCEEDINGS, 2002, :267-272
[2]  
Boulgouris NV, 2004, 2004 IEEE 6TH WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING, P263
[3]  
[陈实 Chen Shi], 2009, [电子与信息学报, Journal of Electronics & Information Technology], V31, P116
[4]   Silhouette-based human identification from body shape and gait [J].
Collins, RT ;
Gross, R ;
Shi, JB .
FIFTH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, PROCEEDINGS, 2002, :366-371
[5]  
Gedikli E., 2007, P 15 SIGN PROC COMM, P1
[6]   Identification of humans using gait [J].
Kale, A ;
Sundaresan, A ;
Rajagopalan, AN ;
Cuntoor, NP ;
Roy-Chowdhury, AK ;
Krüger, V ;
Chellappa, R .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (09) :1163-1173
[7]  
Li HG, 2005, PROCEEDINGS OF 2005 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-9, P4516
[8]   Recognizing humans based on gait moment image [J].
Ma, Qinyong ;
Wang, Shenkang ;
Nie, Dongdong ;
Qiu, Jianfeng .
SNPD 2007: EIGHTH ACIS INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, ARTIFICIAL INTELLIGENCE, NETWORKING, AND PARALLEL/DISTRIBUTED COMPUTING, VOL 2, PROCEEDINGS, 2007, :606-+
[9]  
Mori Atsushi, 2010, Proceedings of the 2010 20th International Conference on Pattern Recognition (ICPR 2010), P2194, DOI 10.1109/ICPR.2010.537
[10]   The HumanID gait challenge problem: Data sets, performance, and analysis [J].
Sarkar, S ;
Phillips, PJ ;
Liu, ZY ;
Vega, IR ;
Grother, P ;
Bowyer, KW .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2005, 27 (02) :162-177