Gait Analysis Based On The Human Skeleton Extraction

With a growing need for security in security-sensitive environment,biometrics recognition,as a human identification approach , has been greatly researched and developed.Compared to the traditional ID recognition method, the second-generation biometric recognition technology based on vision movement can identify individuals by their unique walking manners. Gait has its own advantages which are long-distant, untouched, non body-invading and difficult to conceal, is very attractive in the field of visual surveillance.Based on a gait video clip and applying MATLAB7.0 software to processing images, the gait recognition method of using the human skeleton is proposed in this paper, which mainly covers the following issues:Firstly, the background subtraction is used in gait detection to recover the moving object after scanning the original image. Principal curves can reflect the inherent structure of the data and describe nonlinear data, which is beneficial to the contour extraction. Secondly, Gait cycle is analyzed,then width and height of body analysis is performed to computer it.Lastly, based on the idea that joint-angle trajectories of body parts in walking motion include sufficient dynamic identity information,a gait recognition method based on lower-limb motion analysis and dynamic time wrapping is proposed.For each gait sequence,according to the knowledge of human body anatomy, the coordinates of lower-limb joints are obtained by analyzing lower-limb motion,and then the trajectories of lower-1imb angles in one cycle are extracted as feature vectors.Undoubtedly, gait is a quite potential biometric. However, relevant study mainly stays at in the phase of theory research at present, and in order to apply the technology into practice, there are still a lot of urgent problems needed to be resolved. Experimental results that the characteristic of the human gait can be identified based on the analysis of human skeleton, which has significant importance for the improvement of individual recognition. Experiments further show the research value and the bright future of the gait recognition.