Tracking in Presence of Total Occlusion and Size Variation using Mean Shift and Kalman Filter

Abstract

The classical mean shift algorithm for tracking in perfectly arranged conditions constitutes a good object tracking method. However, in the real environment it presents some limitations, especially under the presence of noise, objects with varying size, or occlusions. In order to deal with these problems, this paper proposes a reliable object tracking algorithm using mean shift and the Kalman filter, which was added to the traditional algorithm as a predictor when no reliable model of the object being tracked is found. Experimental work demonstrates that the proposed mean shift Kalman filter algorithm improves the tracking performance of the classical algorithms in complicated real scenarios. The results involve the tracking of an object in a gray level and in a color sequence, with varying size and in presence of total occlusion.