Recognition of Human Body Movements Trajectory Based on the Three-dimensional Depth Data

详细信息    查看全文

• 作者：Zheng Chang ^{elephant.cz@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Qing Shen ^{shenqingcc222333@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Xiaojuan Ban ^{banxj@ustb.edu.cn" class="auth_mail" title="E-mail the corresponding author} ; Jing Guo ^{guojing7192356@163.com" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Artificial intelligence ; Human-machine interface ; Image recognition ; Motion estimation
• 刊名：IFAC-PapersOnLine
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：47
• 期：3
• 页码：12331-12336
• 全文大小：426 K

文摘

based on the traditional machine vision recognition technology about human body movement trajectory, the paper finds out the shortcomings of the traditional recognition technology. By combining the three - dimensional depth data, the three-dimensional motion history image and the invariant moments of the three - dimensional motion history image computed as the eigenvector of body movements, the paper applies the method to the machine vision of the human body movements trajectory. In detail, the paper describes the algorithm and realization scheme of the human body movements trajectory recognition based on the three-dimensional depth data. Finally, comparing with the results of the recognition experiment, we verify that the method of human body movement trajectory recognition technology based on the three-dimensional data has a more accurate recognition rate and a better robustness.