Abstract = 0 times | PDF = 48 times
This paper investigates a new 3D skeleton-based gait recognition method for motion captured by a low-cost consumer level camera, called Kinect sensor. In this work, a new representation of human gait signature is proposed based on the spatio-temporal changes in relative angles among different skeletal joints and changing of measured distance between limbs and land. These measurements are computed over a complete gait cycle. Further, we have created our own dataset based on Kinect sensor and extract two sets of dynamic features. Nearest Neighbour and Linear discriminant Classifier (LDC) are used for classification. The experimental results show that the proposed method can effectively represent and recognize human gait in comparison with current Kinect-based gait recognition methods.