《计算机应用研究》|Application Research of Computers

基于视觉的人体行为识别算法研究综述

Survey of human action recognition algorithm based on vision

免费全文下载 (已被下载 次)  
获取PDF全文
作者 陈煜平,邱卫根
机构 广东工业大学 计算机学院,广州 510006
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)07-002-1927-08
DOI 10.19734/j.issn.1001-3695.2018.04.0259
摘要 主要讲述人体行为识别的基础流程,归纳了人体行为识别常用的数据集,总结了时域分割的发展现状和常用的方法,讲解了人体行为识别比较经典的方法,并归纳了人体行为识别最新、最热的深度学习方法。引入了动作分割,再结合行为识别,能够实现连续的人体行为识别,使得行为识别适用于实际场景,而不再是对经过人工剪辑好的单个视频进行识别,这在实际应用中意义重大。
关键词 人体行为识别; 数据集; 动作分割; 深度学习; 双流网络
基金项目 国家自然科学基金资助项目(61572142)
广东省科技计划资助项目(14ZK0180)
本文URL http://www.arocmag.com/article/01-2019-07-002.html
英文标题 Survey of human action recognition algorithm based on vision
作者英文名 Chen Yuping, Qiu Weigen
机构英文名 School of Computers,Guangdong University of Technology,Guangzhou 510006,China
英文摘要 This paper focused on action recognition and included data sets and motion segmentation. It mainly described the basic flow of human action recognition. And it summarized the commonly used data sets of human action recognition. Then it summarized the development status and common methods of time domain segmentation. Next it explained the classic algorithms of human action recognition. At last, it summarized the the-state-of-art deep learning methods of human action recognition. The introduction of action recognition combines with action segmentation made the action recognition applicable to the actual scene, which could achieves continuous recognition of human action. Meanwhile it was no longer recognize a single video that has been manually edited. This has very important reference value in practical applications.
英文关键词 human action recognition; data set; motion segmentation; deep learning; two-stream network
参考文献 查看稿件参考文献
 
收稿日期 2018/4/30
修回日期 2018/6/11
页码 1927-1934
中图分类号 TP391.41
文献标志码 A