基于深度信息的动态手势识别综述  

Review of Dynamic Gesture Recognition Based on Depth Information

作　　者：陈甜甜 姚璜 左明章 田元 杨梦婷 CHEN Tian-tian;YAO Huang;ZUO Ming-zhang;TIAN Yuan;YANG Meng-ting(School of Educational Information Technology,Central China Normal University,Wuhan 430079,China)

机构地区：[1]华中师范大学教育信息技术学院,武汉430079

出　　处：《计算机科学》2018年第12期42-51,76,共11页Computer Science

基　　金："十二五"国家科技支撑计划项目(2015BAK33B02;2015BAK27B02)资助

摘　　要：随着计算机技术的飞速发展,自然、简单、非接触式的手势识别在人机交互方面备受青睐。动态的手势识别一直是人机交互领域研究的热点与难点,深度传感器的出现为手势识别的研究提供了更加鲁棒的数据。为了解动态手势的发展现状,在广泛调研现有文献和最新成果的基础上,对基于深度信息的动态手势从手势分割、手势建模、特征提取、手势识别4个方面进行阐述,介绍动态手势识别相关的应用领域,并对其中存在的难点与问题进行讨论。With the rapid development of computer technology,natural,simple and non-contact gesture recognition is favored in human-computer interaction.Dynamic gesture recognition has always been a hot and difficult issue in the field of human-computer interaction.In order to understand the development status of dynamic gestures,this paper described the dynamic gestures based on depth information from four aspects of gesture segmentation,gesture modeling,feature extraction and gesture recognition based on the extensive investigation of the existing literature and the latest achievement s,introduced the applications of dynamic gesture recognition,and discussed the existing difficulties and problems.

关 键 词：人机交互 动态手势识别 深度信息 手势分割 特征提取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]