顾及人体骨架区域特征的行为识别研究  

Action Recognition Considering Skeleton Region Characteristics

作　　者：李雯静[1] 刘鑫[1] LI Wenjing;LIU Xin(School of Resources and Environmental Engineering,Wuhan University of Science and Technology,Wuhan 430000,China)

机构地区：[1]武汉科技大学资源与环境工程学院,湖北武汉430000

出　　处：《武汉大学学报(信息科学版)》2025年第3期571-578,共8页Geomatics and Information Science of Wuhan University

基　　金：湖北省高等学校优秀中青年科技创新团队计划(T2020002);武汉市重点研发计划(2024050702030122)。

摘　　要：基于人体骨架数据的行为识别研究目前已经取得较好的进展,然而现有方法大多仅考虑关节点的空间位置信息,忽视了关节点的区域变化特征。提出一种顾及人体骨架区域特征的行为识别方法,使用人体骨架数据表征人体行为特征,按照人体运动规律对骨架图进行区域划分,在关节坐标数据的基础上考虑区域内关节的角度变化情况,并将两种数据分别作为时空图卷积网络的输入,对两种数据流的预测结果进行融合。实验结果表明,所提方法较单个数据流的检测结果提高了1.9%;与几种经典模型比较,其Top-1和Top-5准确率分别达到了32.4%和54.2%,相较其他模型有更好的检测结果。Objectives:The research on action recognition based on human skeleton data has made good progress.However,most of the existing methods only consider the spatial position information of joint points and ignore the regional change characteristics of joint points.In order to solve this problem,an action recognition method considering the regional characteristics of skeleton is proposed.Methods:First,based on the human body structure,the joints and bones are constructed into a spatiotemporal skeleton map which represents the human action characteristics.The skeleton map is divided into regions according to the law of human movement.Then,the coordinates of nodes in the skeleton graph and the angle change data of the nodes in the region are used as the inputs of the spatiotemporal graph convolution network.Finally,the prediction results of the two data streams are fused to realize human action recognition.Results:In order to prove the effectiveness of the proposed method,it is verified on Florence 3D dataset and dynamics action dataset,respectively.The results show that the accuracy of the proposed method reaches 91.1% on Florence 3D dataset,which is 1.9% higher than that of a single data stream.The accuracies of Top-1 and Top-5 on dynamics action dataset reach 32.4% and 54.2%,respectively.Conclusions:Compared with the existing methods,the proposed method is proved to have better recognition accuracy and higher effectiveness through multiple sets of experiments.

关 键 词：行为识别 区域特征 骨架图 时空图卷积网络 

分 类 号：P208[天文地球—地图制图学与地理信息工程]