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

A new head tracking algorithm for automatically detecting and tracking huma n heads in complex backgrounds is proposed. By using an elliptical model fo r the human head, our Maximum Likelihood (ML) head detector can reliably lo cate human heads in images having complex backgrounds and is relatively ins ensitive to illumination and rotation of the human heads. Our head detector consists of two channels: the horizontal and the vertical channels. Each c hannel is implemented by multiscale template matching. Using a hierarchical structure in implementing our head detector, the execution time for detect ing the human heads in a 512 x 512 image is about 0.02 second in a Spare 20 workstation (not including the time for image acquisition). Based on the e llipse-based ML head detector, we have developed a head tracking method tha t 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 h ead. In this method, the ML head detector and the mutually-supported constr aint are used to extract the corresponding ellipses in a stereo image pair. To implement a practical and reliable face detection and tracking system, further verification using facial features, such as eyes, mouth and nostril s, may be essential. The 3D position computed from the centers of the two c orresponding ellipses is then used for fixation. An active stereo head has been used to perform the experiments and has demonstrated that the proposed approach is feasible and promising for practical uses.