Kernel-Based Structural Binary Pattern Tracking

Abstract

In this paper, we propose a new pattern model, called the structural binary pattern (SBP) model, for object tracking. For the proposed SBP model, we introduce an alternate thresholding scheme to generate a set of multiple SBPs. The SBP encodes not only the binary pattern consisting of binarized differences between the average intensities of subregions within the target region, but also the spatial configuration of the subregions. With the proposed SBP model, we define a metric for similarity between the SBP models from the target and candidate for target localization, which is based on an isotropic kernel weighted Hamming distance. To further improve the tracking performance, we employ a color-based tracking method along with the SBP-based tracking method. The experimental results show that the proposed algorithm exhibits the better performance even when the object being tracked confronts drastic illumination changes, partial occlusion, a similar colored background, or low illumination as compared with conventional tracking methods.