Robust Gait Recognition Using Planar Homography and Shape Sequence Descriptor

被引：0

作者：

Jeong, Seungdo ^{[2
]}

Lee, Youngseok ^{[2
]}

Lee, Keun-Wang ^{[3
]}

Cho, Jungwon ^{[1
]}

机构：

[1] Jeju Natl Univ, Dept Comp Educ, 102 Jejudaehakno, Jeju Si 690756, Jeju Do, South Korea

[2] Hanyang Univ, Res Inst Elect & Comp Engn, Seoul 133791, South Korea

[3] Chungnam Natl Univ, Dept Multimedia, Chungnam 350701, South Korea

来源：

GRID AND DISTRIBUTED COMPUTING | 2011年 / 261卷

关键词：

Gait Recognition; Biometrics; Canonical View; Shape Sequence; View Synthesis;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In the gait recognition, the dependency to the direction of walking is very serious problem. To reduce this dependency, we propose a view synthesis method based on the planar homography. However, even though the synthesized gait is used, shape information is not enough to recognize individual. Thus, in this paper, we use shape sequence descriptor for recognition, which describes shape information and variation according to motion at a same time. Our experiments show that the proposed method efficiently reduces the dependency to directional variations of gait.

引用

页码：484 / +

页数：2