A new approach for multi-view gait recognition on unconstrained paths
详细信息 查看全文
- 作者：D. Ló ; pez-Ferná ; ndez ; i52lofed@uco.es" class="auth_mail" title="E-mail the corresponding author ; F.J. Madrid-Cuevas1 ; fjmadrid@uco.es" class="auth_mail" title="E-mail the corresponding author ; A. Carmona-Poyato1 ; ma1capoa@uco.es" class="auth_mail" title="E-mail the corresponding author ; R. Muñ ; oz-Salinas1 ; rmsalinas@uco.es" class="auth_mail" title="E-mail the corresponding author ; R. Medina-Carnicer1 ; rmedina@uco.es" class="auth_mail" title="E-mail the corresponding author
- 关键词：Gait recognition ; Unconstrained paths ; Rotation-invariant ; Angular analysis ; Curved trajectories ; 3D reconstruction
- 刊名：Journal of Visual Communication and Image Representation
- 出版年：2016
- 出版时间：July 2016
- 年：2016
- 卷：38
- 期：Complete
- 页码：396-406
- 全文大小：2086 K
文摘
- •
We propose a new approach for multi-view gait recognition.
- •
The method is based on the analysis of 3D reconstructions of gait sequences.
- •
A new rotation invariant gait descriptor, based on 3D angular analysis is proposed.
- •
Experimental results demonstrate the effectiveness on unconstrained paths.
- •
The system can correctly identify about 99% of individuals on two public datasets.