The Lower Limbs Motion Analysis

Human motion tracking and analysis has been receiving increasing attention from researchers in the fields of image processing and computer vision during the past few years. It has a lot of applications in smart surveillance system, virtual reality, advanced user interface, motion analysis and model-based coding, etc. Generally speaking, the procedure of the human motion tracking and analysis from a sequence of images involves three main stages: (1) moving objects segmentation in a complex scene; (2) human body segmentation from moving objects; (3) human motion tracking and body structure re-construction; (4) motion analysis and action recognition. As the base of the human action recognition and understanding, human motion tracking and body structure re-construction is the key of the whole procedure. This paper proposes a method of detecting the lower limb joints in human walking automatically, which is based on the geometry properties of walking human.The image sequence is acquired by a single camera firstly, and the human region is extracted from the image by the background subtraction. After the human region and height are obtained, we can further complete the lower limb joints detection of walking human.Above all, the lower limb detection in human walking from side view is finished based on the limb length limit, because the limb length has no distortion in human walking from side view. Next, we detect the knee joints from front according to the edge information and limb length limit. Towards the detection of ankle joints from front, we adjust the length of lower leg by edge information and use this new length to detect the ankle joints. Finally a further research on detection of lower limbs joint from any view is completed, which is according to the linear curve fitting of lower limb edge and lower limb length.This paper gives the experiment results of lower limb joints detection from any views. The image sequences include real sequence from side view and model sequences from side, front and any views by human model software(3DMAX and POSER 3.0). The experiment results prove that the method in this paper is simple and easy to complete. At last the further suggestions for the improvement of the system are discussed.