重庆大学学报2017，Vol.40Issue(11)：99-106,8.DOI:10.11835/j.issn.1000-582X.2017.11.012
基于深度卷积神经网络和深度视频的人体行为识别
Action recognition based on deep convolution neural network and depth sequences
摘要
Abstract
Traditional methods for action recognition include several isolated processes and depend on welldesigned features,which makes them has the shotcomings of large time cost and difficult to optimize the parameters from the whole.In this paper,we use depth sequences to study deep learning-based action recognition and construct a 3D-based deep convolution neural network to automatically learn spatiotemporal features from raw depth sequences.A Softmax classifier is used on the learned features to take action recognition.Experimental results demonstrate that our method can learn feature representation automatically from depth sequences.The proposed method performs comparable results to the state-of-the-art methods on the MSR-Action3D dataset and achieves good performance in comparison to baseline methods on the UTKinect-Action3D dataset.And the proposed method is simpler in feature extracting and action recognition consist of a closed loop system which can learn features automatically.We further investigate the generalization of the trained model by transferring the learned features from one dataset (MSR-Action3D) to another dataset (UTKinect-Action3D) without retraining and obtain very promising classification accuracy.关键词
深度学习/人体行为识别/深度卷积神经网络/深度视频/3维卷积Key words
deep learning/human action recognition/deep convolution neural network/depth sequence/3dimension convolution分类
信息技术与安全科学引用本文复制引用
刘智,冯欣,张杰..基于深度卷积神经网络和深度视频的人体行为识别[J].重庆大学学报,2017,40(11):99-106,8.基金项目
国家自然科学基金-青年科学基金资助项目(61502065) （61502065）
重庆市教委科学技术研究资助项目(KJ1600937,KJ1500922,KJ1501504).Supported by National Natural Science Foundation of China for Young Scientists (61502065) and Scientific and Technological Research Program of Chongqing Municipal Education Commission (KJ1600937,KJ1500922,KJ1501504). （KJ1600937,KJ1500922,KJ1501504）
