A tracking algorithm based on SIFT and kalman filter

Abstract

This paper presents a method of target tracking based on SIFT and Kalman filter. SIFT algorithm has the ability to detect the invariant feature points which used in tracking and Kalman filter has the ability to predict the target location. Firstly, this paper uses SIFT to compute the location of target. Secondly, this paper uses Kalman filter to optimize the target location in order to correct the error of SIFT algorithm precisely. Lastly, this paper uses 2 groups of videos to test this algorithm. The results show that this is an effective tracking method. © The Authors.