Title :
A hybrid real-time face tracking system
Author :
Wang, Ce ; Brandstein, Michael S.
Author_Institution :
Div. of Eng. & Appl. Sci., Harvard Univ., Cambridge, MA, USA
Abstract :
A hybrid real-time face tracker based on both sound and visual cues is presented. Initial talker locations are estimated acoustically from microphone array data while precise localization and tracking are derived from image information. A computationally efficient algorithm for face detection via motion analysis is employed to track individual faces at rates up to 30 frames per second. The system is robust to nonlinear source motions, complex backgrounds, varying lighting conditions, and a variety of source-camera depths. While the direct focus of this work is automated video conferencing, the face tracking capability has utility to many multimedia and virtual reality applications
Keywords :
acoustic transducer arrays; array signal processing; image processing; microphones; motion estimation; multimedia communication; real-time systems; teleconferencing; tracking; virtual reality; automated video conferencing; complex backgrounds; computationally efficient algorithm; face detection; hybrid real-time face tracking system; image information; microphone array data; motion analysis; multimedia applications; nonlinear source motions; sound cues; source-camera depths; talker locations; varying lighting conditions; virtual reality applications; visual cues; Cameras; Face detection; Humans; Image edge detection; Microphone arrays; Motion detection; Real time systems; Skin; Tracking; Videoconference;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.679696
