Structure modelling of the human body using FGMM

Human motion analysis and posture recognition have received increasing attention in the area of computer vision, for example, human-machine interaction. Structure modelling and analysis of human body is important for human motion analysis and posture recognition. In this paper, we propose a novel method based on fuzzy Gaussian mixture models (FGMM) to handle the task of structure modelling. To be more specific, Microsoft Kinect Sensor firstly captures raw 3D data of human body, followed by some data preprocessing steps, which include separating human body from the background and projection from 3D to 2D, etc. Then FGMM is applied to approximate the distribution of the processed 2D points. Experiments have been conducted to verify the effectiveness of proposed method on body structure modelling.