Human tracking system
Kavita Wagh, Ramesh K. Kulkarni · 2014
Human tracking is a comprehensive framework for tracking coarse human model performed from sequences of synchronized monocular grayscale images in single or multiple camera system coordinates. It is nothing but segmenting an interested human from video scene and keep track if it continuously. It demonstrates the feasibility of an end to end person tracking system where initially it start background subtraction, then detection of the interested human and tracking of that human form one frame to another continuously. For detection of the interested human PCA algorithm is used. Finally Kalman filter is introduced into tracking the people. Our system have demonstrated that as compaired with other methods it reduces detection time comparitively and improves human detection and tracking accuracy.