欢迎访问《图学学报》 分享到：
图学学报

图学学报

• 专论：第12届中国计算机图形学大会 (CHINAGRAPH 2018 广州) • 上一篇    下一篇

基于双特征匹配层融合的步态识别方法

  

  1. 1. 西安科技大学计算机科学与技术学院，陕西 西安 710054； 
    2. 江苏理工学院计算机工程学院，江苏 常州 213001； 
    3. 中国矿业大学银川学院机电动力与信息工程系，宁夏 银川 750021
  • 出版日期:2019-06-30 发布日期:2019-08-02
  • 基金资助:
    陕西省自然科学基础研究计划项目(2019JM-162)；中国博士后科学基金项目(2016M601845)；宁夏高等学校科学研究项目(NGY2017234)； 西安科技大学博士启动金项目(2019QDJ007)

Research on Gait Recognition Algorithm Based on Double Features Using the Layer Matching Fusion Method

  1. 1. College of Computer Science and Technology, Xi’an University of Science and Technology, Xi’an Shaanxi 710054, China; 
    2. Computer Engineering School, Jiangsu University of Technology, Changzhou Jiangsu 213001, China; 
    3. Department of Mechatronics Power and Information Engineering, China University of Mining and Technology Yinchuan College, Yinchuan Ningxia 750021, China
  • Online:2019-06-30 Published:2019-08-02

PDF (PC)

106

摘要： 步态识别是根据人类走路的姿态来进行远距离的身份识别。针对轮廓不完整的图 像和关键帧容易造成部分信息丢失而引起的识别率下降问题，提出一种基于双特征匹配层融合 的步态识别方法。步态既有静态图像特征，又有动态速度变化特征，因此本文提出用匹配层融 合方法将静态的 Hu 矩 6 个不变矩特征和动态的帧差百分比特征融合后进行步态身份识别。首 先对一个周期内的归一化步态图像进行 Hu 矩特征以及帧差百分比的特征提取，将 Hu 矩 6 个不 变矩特征描述成一个特征向量，然后运用匹配层融合算法对 2 个特征进行融合；最后使用 K 近 邻分类器进行身份识别。实验表明，该方法较单一方法能够有效地提高步态识别正确率。

关键词: 步态识别, Hu 矩特征, 帧差百分比特征, 匹配层融合

Abstract: The gait recognition method is a kind of identity recognition method according to the walking postures in the distance. For the low recognition rate caused by the incomplete outline image and the selected key frame which would easily lose information, we propose a gait recognition method based on double features using the layer matching fusion method. The gaits have both the static image characters and the dynamic speed characters, and we use the layer matching method to fuse 6 invariable moment features of the Hu moment with the frame difference percentage features. Firstly, the Hu moment features and the frame difference percentage features are extracted from a period of the normalized gait images, and the 6 invariable moment features are described as one feature vector. Secondly, the layer matching fusion method is used to fuse the tow features. Lastly, the k-Nearest neighbor method is used for the identity recognition. The experiments show that our method could efficiently raise the recognition rate.

Key words: gait recognition, Hu moment feature, frame difference percentage, layer matching fusion