Vision-based real-time motion capture system using multiple cameras
Vision-based real-time motion capture system using multiple cameras
复制标题
DOI：
10.1109/mfi-2003.2003.1232665
复制
发表时间：
2003-09
期刊：
影响因子：
--
通讯作者：
H. Yoshimoto;N. Date;S. Yonemoto
中科院分区：
文献类型：
--
作者：
H. Yoshimoto;N. Date;S. Yonemoto
在本文中，我们讨论了一个基于视觉的实时运动捕捉系统，这是构建在PC集群。基于视觉的运动捕捉不对人施加物理限制，这提供了测量人体运动的自然方式。然而，有几个问题需要解决，这是鲁棒的估计人体运动从有限数量的视觉线索和估计算法的计算成本。为了处理这些问题，我们已经开发了多个基于多视图的算法，使用多个摄像机，并已实现的PC集群上的算法来解决计算问题。在本文中，我们提出了我们的实验研究基于视觉的实时运动捕捉，重点是三维人体姿态估计。
In this paper, we discuss a vision-based real-time motion capture system, which is constructed on a PC-cluster. Vision-based motion capture does not impose physical restrictions on humans, which provides a natural way of measuring human motion. However, there are several issues to be solved, which are robust estimation of human motion from a limited number of visual cues and computation cost of the estimation algorithm. To deal with these issues, we have developed multi-view-based algorithms using multiple cameras and have implemented the algorithms on a PC-cluster to solve the computation problem. In this paper, we present our experimental study on vision-based real-time motion capture with emphasis on 3D human posture estimation.