Real time tracking of multiple persons by Kalman filtering and face pursuit for multimedia applications

We present an algorithm that can track multiple persons and their faces simultaneously in a video sequence, even if they are completely occluded from the camera's point of view. The algorithm is based on the detection and tracking of person masks and their faces. Face localization uses skin detection based on color information with an adaptive thresholding. In order to handle occlusions, a Kalman filter is defined for each person that allows the prediction of the person bounding box, of the face bounding box and of its speed. In case of incomplete measurements (for instance, in case of partial occlusion), a partial Kalman filtering is done. Several results show the efficiency of this method. This algorithm allows real time processing.