A framework for Human tracking using Kalman filter and fast mean shift algorithms

Abstract

The task of reliable detection and tracking of multiple objects becomes highly complex for crowded scenarios. In this paper, a robust framework is presented for multi-Human tracking. It includes a combination of Kalman filter and fast mean shift algorithm. Kalman prediction is measurement follower. It may be misled by wrong measurement. The search for solution is guided by a fast mean shift procedure. It is used to locate densities extrema, which gives clue that whether Kalman prediction is right or it is misled by wrong measurement. Tracking results are demonstrated for crowded scenes and evaluation of the proposed tracking framework is presented.