加权CCA多信息融合的步态表征方法

PDF下载HTML

Title:

A gait representation method based on weighted CCA for multi-information fusion

作者:

吕卓纹¹, 王一斌¹, 邢向磊², 王科俊²

1. 四川师范大学 工学院, 四川 成都 610068;
2. 哈尔滨工程大学 自动化学院, 黑龙江 哈尔滨 150001

Author(s):

LYU Zhuowen¹, WANG Yibin¹, XING Xianglei², WANG Kejun²

1. School of Engineering, Sichuan Normal University, Chengdu 610068, China;
2. College of Automation, Harbin Engineering University, Harbin 150001, China

关键词:

步态表征; 步态流图; 时序信息; 信息编码; 颜色空间; 类能量图; 典型相关分析; 单通道

Keywords:

gait representation; gait flow image; time information; information coding; color space; class energy image; canonical correlation analysis; single channel

分类号:

TP391.41

DOI:

10.11992/tis.201808012

摘要:

为了解决步态识别中步态表征不完备的问题，提出了一种新的步态表征方法。该方法是在步态流图的基础上，将能够表征时序信息的步宽特征编码到颜色空间，得到三通道的彩色类能量图，采用典型相关分析将多通道信息融合成单通道，同时去除了特征间的冗余信息，得到了更丰富的有益识别的步态特征。实验结果表明，提出的新方法能够有效提取步态特征，步态识别率得到显著提高。

Abstract:

In this paper, we propose a new gait representation method to address the problem of incomplete gait representation in current gait recognition technologies. The proposed method is based on gait flow images in which step-width timing information is encoded into the color space to obtain a three-channel colored class energy image. Multi-channel information can be fused into a single channel by canonical correlation analysis, whereby redundant feature information is removed. This process enriches the gait features and enables better recognition. Experimental results show that the proposed method effectively characterizes the gait features and significantly improves the recognition rate.