摘要
人体行为识别一直是计算机视觉研究中的热点.随着近几年人体行为识别在虚拟现实、短视频等方面的广泛应用,以及深度学习算法的快速发展,基于深度学习的行为识别算法层出不穷.相较于传统方法,基于深度学习的行为识别算法具有鲁棒性强、准确率高的优点.基于此,本文对近年来提出的基于深度学习的行为识别算法进行了梳理,并对由双流卷积网络和3D卷积网络结构发展而来的行为识别的系列算法进行了重点介绍,并总结了各种算法的性能和成果,最后对该领域进行了展望.
Human action recognition has always been a hot topic in computer vision research and widely applied in virtual reality,short video,etc.Meanwhile,the fast development of deep learning in recent years has also inspired the action recognition algorithms.Compared with traditional methods,the action recognition algorithms based on deep learning have advantages of strong robustness and high accuracy.Here,we make a survey on the action recognition algorithms based on deep learning proposed in recent years,and focus on those developed from two-stream network and 3D convolutional network,then summarize their performances and positive results,and finally make prospects in this field.
作者
胡凯
郑翡
卢飞宇
黄昱锟
HU Kai;ZHENG Fei;LU Feiyu;HUANG Yukun(School of Automation,Nanjing University of Information Science&Technology,Nanjing 210044;Collaborative Innovation Center of Atmospheric Environment and Equipment Technology,Nanjing University of Information Science&Technology,Nanjing 210044)
出处
《南京信息工程大学学报（自然科学版）》
CAS
北大核心
2021年第6期730-743,共14页
Journal of Nanjing University of Information Science & Technology（Natural Science Edition）
基金
国家自然科学基金(61773219,61701244)
国家重点研发计划(2018YFC1405703)。
关键词
行为识别
深度学习
卷积网络
action recognition
deep learning
convolution network
