Torwads real time kinect anlysis system for early diagnosis of gait cycle abnormalities

Abstract

The main purpose of this paper is to develop a system for the early diagnosis and detection of abnormalities of any patient during gait cycle. A malfunction in the gait cycle leads to pain, and undesirable effects on the bones of the legs due to large forces exerted on specific areas. The gait cycle is divided into two main phases, the stance that is characterized as the contact of the right leg with ground, and the swing phase where the right leg has no interface with ground. In order to detect and analyze gait cycle stages, a Kinect camera was used since it possesses depth sensor, allows the tracking of skeletal information, and covers distance ranged between 0.8m and 4m. The Kinect camera is linked to Matlab to compare the recorded frames with database for a normal gait. The database will be built considering the stages and sub stages of each phase to detect and localize the abnormalities and specify the joints or organs involved.