利用基于信息熵的解耦表示学习实现步态识别  

GAIT RECOGNITION USING DISENTANGLED REPRESENTATION LEARNING BASED ON INFORMATION ENTROPY

作　　者：曹震军 朱子奇 Cao Zhenjun;Zhu Ziqi(School of Computer Science and Technology,Wuhan University Science and Technology,Wuhan 430065,Hubei,China)

机构地区：[1]武汉科技大学计算机科学与技术学院,湖北武汉430065

出　　处：《计算机应用与软件》2025年第4期150-155,222,共7页Computer Applications and Software

基　　金：国家自然科学基金项目(61702382)。

摘　　要：步态识别在现实生活中有着广泛的应用。步态识别问题的关键是从行走的人的视频帧中提取出与步态相关的特征。针对现有的方法不能获得基于外观特征不变的步态特征的问题,利用解耦表示学习的方法,提出一种自编码器架构用于分解步态特征和外观特征,利用基于仁义熵的联合熵最小化步态特征和外观特征之间的互信息。通过在CASIA-B、FVG数据集上的大量实验,该方法在步态识别问题中表现出了更好的解耦能力,并且识别准确率更高。Gait recognition has a wide range of applications in real life.The key of gait recognition is to extract gait related features from the video frames of walking people.Aimed at the problem that the existing methods can not obtain gait features based on appearance features,using the disentangled representation learning method,an autoencoder architecture was proposed to decompose gait features and appearance features,and the joint entropy based on Renyi entropy was used to minimize the mutual information between gait features and appearance features.Through a large number of experiments on CASIA-B and FVG data sets,this method shows better decoupling ability and higher recognition accuracy in gait recognition.

关 键 词：步态识别 解耦表示学习 仁义熵 自编码器 互信息 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]