A New Scale and Orientation Adaptive Object Tracking System Using Kalman Filter and Expected Likelihood Kernel

摘要

This paper presents a new scale and orientation adaptive object tracking system using Kalman filter in a video sequence. This object tracking is an important task in many vision applications. The main steps in video analysis are two: detection of interesting moving objects and tracking of such objects from frame to frame. We use an efficient local search scheme (based on expected likelihood kernel) to find the image region with a histogram most similar to the histogram of the tracked object. In this paper, we address the problem of scale adaptation. The proposed approach tracker with scale selection is compared with recent state-of-the-art algorithms. Experimental results have been presented to show the effectiveness of our proposed system.