In order to improve the problem that the existing equipment for measuring the center of gravity of human body is expensive and inconvenient to carry,a method to rapidly estimate center of gravity of human body using Kinect depth camera is proposed. This method uses the segmented method and Matsui Xiuzhi model,and the skeletal information obtained by Kinect is combined to divide the human body into 15 segments. The center of gravity of each segment is calculated according to the segment mass,proximal and distal coordinates and the radius coefficient of the center of gravity,and then the total center of gravity of the human body is estimated by combining moment synthesis method. Finally,the data of the center of gravity is modified by the model of machine learning algorithm. The comparative experimental results between Kinect and three-dimensional force measuring plate show that this method has better accuracy in measuring the center of gravity of human body with large movements, Kinect is cheaper than traditional equipment,easy to be popularized and used,which can be used as a standing balance assessment tool.
关键词
人体重心/Kinect软件/深度图像
Key words
center of gravity of human body/Kinect software/depth image
维普
万方数据