Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (3): 712-718.DOI: 10.11772/j.issn.1001-9081.2018071638

Previous Articles     Next Articles

Gait recognition method based on multiple classifier fusion

HUAN Zhan, CHEN Xuejie, LYU Shiyun, GENG Hongyang   

  1. School of Information Science and Engineering, Changzhou University, Changzhou Jiangsu 213164, China
  • Received:2018-08-08 Revised:2018-10-23 Online:2019-03-10 Published:2019-03-11
  • Contact: 陈学杰
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61772248).


郇战, 陈学杰, 吕士云, 耿宏杨   

  1. 常州大学 信息科学与工程学院, 江苏 常州 213164
  • 作者简介:郇战(1969-),男,陕西咸阳人,副教授,硕士,主要研究方向:物联网、智能控制;陈学杰(1994-),男,江苏宿迁人,硕士研究生,主要研究方向:物联网、智能控制;吕士云(1995-),女,江苏盐城人,硕士研究生,主要研究方向:物联网、智能控制;耿宏杨(1995-),男,江苏宿迁人,硕士研究生,主要研究方向:物联网、智能控制。
  • 基金资助:

Abstract: To improve the performance of gait recognition based on smartphone accelerometer, a recognition method based on Multiple Classifier Fusion (MCF) was proposed. Firstly, as the gait features extracted from the existing methods were relatively simple, the speed variation of the relative gradual acceleration extracted from each single gait cycle and the acceleration variation per unit time were taken as two new types of features (16 in total). Secondly, combing the new features with the frequently-used time domain and frequency domain features to form a new feature set, which could be used to train multiple classifiers with excellent recognition effect and short training time. Finally, Multiple Scale Voting (MSV) was used to fuse the output of the multiple classifiers to obtain the final classification result. To test the performance of the proposed method, the gait data of 32 volunteers were collected. Experimental results show that the recognition rate of new features for a single classifier is increased by 5.95% on average, and the final recognition rate of MSV fusion algorithm is 97.78%.

Key words: Multiple Classifier Fusion (MCF), fusion algorithm, multiple scale voting, gait feature, motion feature

摘要: 为了提高现有基于智能手机加速度传感器步态身份识别的性能,提出了一种基于多分类器融合(MCF)的识别方法。首先,针对现有方法所提取的步态特征较为单一的问题,对单个步态周期提取相对匀变加速度的速度变化量,以及单位时间内加速度变化量作为两类新特征(共16个);其次,将新特征结合常用的时域、频域特征组成新的特征集,用于训练识别效果与训练时间俱佳的多个分类器;最后,采用多尺度投票法(MSV)对多分类器的输出进行融合处理,得到最终的分类结果。为了检测该方法的性能,采集了32个志愿者的步态数据。实验结果表明,新特征对于单个分类器的识别率平均提升5.95个百分点,最终通过MSV融合算法的识别率为97.78%。

关键词: 多分类器融合, 融合算法, 多尺度投票法, 步态特征, 运动特征

CLC Number: