标题：Real-time Action Recognition based on a Modified Deep Belief Network Model
作者：Zhang, Haiting; Zhou, Fengyu; Zhang, Wei; Yuan, Xianfeng; Chen, Zhuming
作者机构：[Zhang, Haiting; Zhou, Fengyu; Zhang, Wei; Yuan, Xianfeng] Shandong Univ, Sch Control Sci & Engn, Jinan 250100, Peoples R China.; [Chen, Zhuming] Sh 更多
会议名称：IEEE International Conference on Information and Automation (ICIA)
会议日期：JUL 28-30, 2014
来源：2014 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION (ICIA)
关键词：Deep Belief Network; Action Recognition; Real-time; Coordinates of; Joints
摘要：This paper presents a real-time human action recognition method based on a modified Deep Belief Network (DBN) model. To recognize human actions, the positions of human joints are taken into account. Each action is made of a sequence of human joint positions. Since the classic DBN cannot deal with temporal information, the proposed method employs the conditional Restricted Boltzmann Machine (cRBM) to handle the human joint sequence. To verify the effectiveness of the proposed method, two skeletal representation datasets are used for testing. Experimental results show that the proposed method is able to achieve real-time human action recognition, and the recognition accuracy is comparable to state-of-the-arts methods.