Robust Detection and Tracking of Human Faces with an Active Camera

We present an e cient framework for the detection and tracking of human faces with an active camera. The Bhattacharyya coe cient is employed as a similarity measure between the color distribution of the face model and face candidates. The proper derivation of these distributions allows the use of the spatial gradient of the Bhattacharyya coe cient to guide a fast search for the best face candidate. The optimization, which is based on mean shift analysis, requires only a few iterations to converge. Scale changes of the tracked face are handled by exploiting the scale invariance of the similarity measure and the luminance gradient computed on the border of the hypothesized face region. The detection and tracking modules are almost identical, the difference being that the detection involves mean shift optimization with multiple initializations. Our dual-mode implementation of the camera controller determines the pan, tilt, and zoom camera to switch between smooth pursuit and saccadic movements, as a function of the target presence in the fovea region. The resulting system runs in real-time on a standard PC, being robust to partial occlusion, clutter, face scale variations, rotations in depth, and fast changes in subject/camera position.