Elliptical head tracking using intensity gradients and color histograms

An algorithm for tracking a person´s head is presented. The head´s projection onto the image plane is modeled as an ellipse whose position and size are continually updated by a local search combining the output of a module concentrating on the intensity gradient around the ellipse´s perimeter with that of another module focusing on the color histogram of the ellipse´s interior. Since these two modules have roughly orthogonal failure modes, they serve to complement one another. The result is a robust, real-time system that is able to track a person´s head with enough accuracy to automatically control the camera´s pan, tilt, and zoom in order to keep the person centered in the field of view at a desired size. Extensive experimentation shows the algorithm´s robustness with respect to full 360-degree out-of-plane rotation, up to 90-degree tilting, severe but brief occlusion, arbitrary camera movement, and multiple moving people in the background