Human motion analysis based on extraction of skeleton and dynamic time warping algorithm using RGBD camera

摘要

Human action analysis is an extremely popular topic in the field of computer vision. It has wide application prospects in intelligent monitoring, virtual reality, pedestrian tracking, etc. This paper present an algorithm for human motion analysis based on extraction of skeleton and dynamic time warping algorithm using RGBD camera. First, to solve the problem of the limitation of information in two-dimensional space, the RGBD camera is adopted to obtain the three-dimensional spatial information of the human body. Then, in the process of feature extraction, 11 skeleton points are selected from the depth image and the relative distance of the space is calculated, reducing the computational complexity significantly. Furthermore, an optimisation algorithm of dynamic time warping is introduced so that the adverse effects of time difference are decreased. Finally, the human motion analysis is studied. The experimental results show that the proposed method can recognise single action and double action effectively.