Vishnoi Nalini, Duric Zoran, Gerber Naomi Lynn
Department of Computer Science, George Mason University, Fairfax, VA, USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:4839-42. doi: 10.1109/EMBC.2012.6347077.
Gait analysis has been an interesting area of research for several decades. In this paper, we propose image-flow-based methods to compute the motion and velocities of different body segments automatically, using a single inexpensive video camera. We then identify and extract different events of the gait cycle (double-support, mid-swing, toe-off and heel-strike) from video images. Experiments were conducted in which four walking subjects were captured from the sagittal plane. Automatic segmentation was performed to isolate the moving body from the background. The head excursion and the shank motion were then computed to identify the key frames corresponding to different events in the gait cycle. Our approach does not require calibrated cameras or special markers to capture movement. We have also compared our method with the Optotrak 3D motion capture system and found our results in good agreement with the Optotrak results. The development of our method has potential use in the markerless and unencumbered video capture of human locomotion. Monitoring gait in homes and communities provides a useful application for the aged and the disabled. Our method could potentially be used as an assessment tool to determine gait symmetry or to establish the normal gait pattern of an individual.
几十年来，步态分析一直是一个有趣的研究领域。在本文中，我们提出了基于图像流的方法，使用单个低成本摄像机自动计算不同身体部位的运动和速度。然后，我们从视频图像中识别并提取步态周期的不同事件（双支撑、摆动中期、蹬离和足跟撞击）。进行了实验，从矢状面捕捉了四名行走的受试者。进行自动分割以将移动的身体与背景分离。然后计算头部偏移和小腿运动，以识别与步态周期中不同事件对应的关键帧。我们的方法不需要校准相机或特殊标记来捕捉运动。我们还将我们的方法与Optotrak 3D运动捕捉系统进行了比较，发现我们的结果与Optotrak的结果非常吻合。我们方法的开发在无标记和无障碍的人体运动视频捕捉方面具有潜在用途。在家庭和社区中监测步态为老年人和残疾人提供了一个有用的应用。我们的方法有可能用作评估工具，以确定步态对称性或建立个体的正常步态模式。
