Adaptive window method with sizing vectors for reliable correlation-based target tracking

We propose an adaptive window method that can provide a tracker with a tigh t reference window by adaptively adjusting its window size independently in to all four side directions for enhancing the reliability of correlation-ba sed image tracking in complex cluttered environments. When the size and sha pe of a moving object changes in an image, a correlator often accumulates w alk-off error. A success of correlation-based tracking depends largely on c hoosing the suitable window size and position and thus transferring the pro per reference image template to the next frame. We generate sizing vectors from the corners and sides, and then decompose the sizing vector from the c orner into two corresponding sides. Since our tracker is capable of adjusti ng a reference image size more properly, stable tracking has been achieved minimizing the influence of complex background and clutters. We tested the performance of our method using 39 artificial image sequences made of 4260 images and 45 real image sequences made of more than 3400 images, and had t he satisfactory results for most of them. (C) 1999 Pattern Recognition Soci ety. Published by Elsevier Science Ltd. All rights reserved.