<title>Four-directional adaptive windowing algorithm using variable sizing vectors for correlation-based tracking</title>

Abstract

We propose an adaptive windowing algorithm that could provide a tracker with the tight reference window by adaptively adjusting its window size independently into all four side directions for enhancing the reliability of correlation-based image tracking in complex cluttered environments. When the size and shape of a moving object changes in an image, a correlator often accumulates walk-off error. A success of correlation-based tracking depends largely on choosing suitable window size and position and thus transferring the proper reference image template to the next frame. We generate sizing vectors from the corners and sides, and then decompose sizing vectors from the corner into two corresponding sides. Since our tracker is capable of adjusting a reference image size more rapidly and properly, stable tracking has been achieved minimizing the influence of complexed background and clutters. We tested performance of our method using 18 artificial image sequences made of 2160 images and 45 real image sequences made of more than 3400 images, and had the satisfied results for most of them.