自动化学报2016，Vol.42Issue(6)：848-857,10.DOI:10.16383/j.aas.2016.c150710
基于深度学习的人体行为识别算法综述
A Review of Human Action Recognition Based on Deep Learning
摘要
Abstract
Human action recognition is an active research topic in intelligent video analysis and is gaining extensive attention in academic and engineering communities. This technology is an important basis of intelligent video analysis, video tagging, human computer interaction and many other fields. The deep learning theory has been made remarkable achievements on still image feature extraction and gradually extends to the time sequences of human action videos. This paper reviews the traditional design of action recognition methods, such as spatial-temporal interest point, introduces and analyzes different human action recognition framework based on deep learning, including convolution neural network (CNN), independent subspace analysis (ISA) model, restricted Boltzmann machine (RBM), and recurrent neural network (RNN). Finally, this paper summarizes the advantages and disadvantages of these methods.关键词
行为识别/深度学习/卷积神经网络/限制玻尔兹曼机Key words
Action recognition/deep learning/convolution neural network (CNN)/restricted Boltzmann machine (RBM)引用本文复制引用
朱煜,赵江坤,王逸宁,郑兵兵..基于深度学习的人体行为识别算法综述[J].自动化学报,2016,42(6):848-857,10.基金项目
国家自然科学基金(61370174,61271349),中央高校基本科研业务费专项资金(WH1214015)资助Supported by National Natural Science Foundation of China (61370174,61271349) and the Fundamental Research Funds for the Central Universities (WH1214015) （61370174,61271349）
