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

来源：

NEUROCOMPUTING | 2012年 / 79卷

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

页码：173 / 178

页数：6