arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv cs/0510063cs.AI
收藏

用于步态分析的无标记人体运动捕捉

Markerless Human Motion Capture for Gait Analysis

Jamal Saboune, François Charpillet

摘要:

我们研究的目的是检测平衡障碍和老年人跌倒的趋势,了解步态参数。在本文中,我们提出了一种新的工具,步态分析的基础上无标记的人体运动捕捉,从相机饲料。在这里介绍的系统,恢复人体的几个关键点的3D位置,而步行。前景分割,一个关节的身体模型和粒子滤波是我们的方法的基本要素。没有使用动态模型,因此该系统可以被描述为通用的和简单的实现。一种改进的粒子滤波算法,我们称之为区间粒子滤波,是用来重组和搜索通过模型的配置搜索空间在一个确定性的最佳方式。该算法能够成功地进行人体运动跟踪。从一个单一的凸轮饲料的治疗结果示出,并使用基于标记的人体运动捕捉系统获得的结果进行比较。

英文摘要:

The aim of our study is to detect balance disorders and a tendency towards the falls in the elderly, knowing gait parameters. In this paper we present a new tool for gait analysis based on markerless human motion capture, from camera feeds. The system introduced here, recovers the 3D positions of several key points of the human body while walking. Foreground segmentation, an articulated body model and particle filtering are basic elements of our approach. No dynamic model is used thus this system can be described as generic and simple to implement. A modified particle filtering algorithm, which we call Interval Particle Filtering, is used to reorganise and search through the model's configurations search space in a deterministic optimal way. This algorithm was able to perform human movement tracking with success. Results from the treatment of a single cam feeds are shown and compared to results obtained using a marker based human motion capture system.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑