Automatic detection and tracking of human heads using an active stereo vision system

Abstract

A head tracking system for automatically detecting and tracking human heads in complex backgrounds is developed. In this paper, two issues are addressed: the detection of human heads and the development of a head tracking system. First, based on an elliptical model for the human head, we propose a Maximum Likelihood (ML) detector to reliably locate human heads in images having complex backgrounds. This ellipse-based ML head detector is relatively insensitive to illumination and rotation of the human heads, and its computation is similar to template matching. Second, we develop a head tracking system that can monitor the entrance of a person, detect and track the person's head, and then control the stereo cameras to focus their gaze on this person's head. Difference images are used to detect the entrance of a human. The ellipse-based ML head detector and the mutually-supported constraint are used to extract the corresponding ellipses in a stereo image pair. Then, the 3D position computed from the centers of the two corresponding ellipses can be used for fixation. A well-calibrated active stereo head, the IIS-head, is used to perform the experiments and demonstrate that our approach is feasible and promising.