A Robust Color Tracker Employing a Two-dimensional Color Histogram with an Anisotropic Asymmetric Gaussian Distribution Model

This paper describes a robust color tracker employing a two-dimensional color histogram with an anisotropic asymmetric Gaussian distribution model. A robust color tracking is achieved by updating the color model employing two-dimensional histogram of the h-s plane of the hsv color space. The proposal technique is corresponding to unknown illumination change because the color model is acquired directly from the object. Moreover, we propose and adopt an anisotropic asymmetric Gaussian distribution model as a model of the changeable color range of the object. The color model is added and deleted one by one by update process. And, it is allowed some different color to add and disregarded too quite different color by estimating the changeable color range of the object. We developed a color tracking system with pan-tilt camera, do the experiment for confirming the effectiveness of the proposal technique, and tracked the color of the object robustly