通过Kinect摄像头评估手臂运动速度：在健康受试者中的初步研究。
Arm movement speed assessment via a Kinect camera: a preliminary study in healthy subjects.
作者信息
Elgendi Mohamed, Picon Flavien, Magnenat-Thalmann Nadia, Abbott Derek
机构信息
Department of Computing Science, University of Alberta, 2-32 Athabasca Hall, T6G 2E1 Edmonton, Canada.
出版信息
Biomed Eng Online. 2014 Jun 27;13:88. doi: 10.1186/1475-925X-13-88.
BACKGROUND
Many clinical studies have shown that the arm movement of patients with neurological injury is often slow. In this paper, the speed of arm movements in healthy subjects is evaluated in order to validate the efficacy of using a Kinect camera for automated analysis. The consideration of arm movement appears trivial at first glance, but in reality it is a very complex neural and biomechanical process that can potentially be used for detecting neurological disorders.
METHODS
We recorded hand movements using a Kinect camera from 27 healthy subjects (21 males) with a mean age of 29 years undergoing three different arbitrary arm movement speeds: fast, medium, and slow.
RESULTS
Our developed algorithm is able to classify the three arbitrary speed classes with an overall error of 5.43% for interclass speed classification and 0.49% for intraclass classification.
CONCLUSIONS
This is the first step toward laying the foundation for future studies that investigate abnormality in arm movement via use of a Kinect camera.
背景
许多临床研究表明，神经损伤患者的手臂运动往往缓慢。在本文中，对健康受试者的手臂运动速度进行评估，以验证使用Kinect摄像头进行自动分析的有效性。乍一看，手臂运动的考量似乎微不足道，但实际上它是一个非常复杂的神经和生物力学过程，有可能用于检测神经疾病。
方法
我们使用Kinect摄像头记录了27名健康受试者（21名男性）的手部运动，这些受试者平均年龄为29岁，进行了三种不同的任意手臂运动速度：快速、中等和慢速。
结果
我们开发的算法能够对这三种任意速度类别进行分类，类间速度分类的总体误差为5.43%，类内分类的总体误差为0.49%。
结论
这是为未来通过使用Kinect摄像头研究手臂运动异常的研究奠定基础的第一步。
Zotero 插件