A low-cost video-based tool for clinical gait analysis

In physical and rehabilitation medicine physicians need to perform clinical gait analysis to assess patients walking ability. Despite the relevant research on motion tracking, gait analysis technologies are far to be commonly diffused in clinical practice since they are quite expensive, need high-structured laboratories and trained personnel who are not always available. In order to overcome such limitations, this work proposes a low-cost, video-based portable tool for clinical gait analysis which provides the bi-dimensional kinematic analysis of walking. The system processes a video stream by means of tracking different markers placed in five anatomical landmarks of the subject's leg, applying Kalman filter in conjunction with a method that copes with occlusions. The system has been validated on a healthy subject, showing that it is able to reconstruct marker position and leg kinematics even if several occlusions occur.