Multi-source face tracking with audio and visual data

Author

Wang, Ce ; Brandstein, Michael S.

Author_Institution

Div. of Eng. & Appl. Sci., Harvard Univ., Cambridge, MA, USA

fYear

1999

fDate

1999

Firstpage

169

Lastpage

174

Abstract

A 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 visual data. The image processing employs a hierarchical structure which utilizes source motion, contour geometry, color data, and facial features. The resulting system is capable of tracking multiple persons in complex backgrounds and robustly discriminating faces from similar objects. While the direct focus of this work is automated videoconferencing, the face tracking capability has utility to many multimedia and virtual reality applications

Keywords

edge detection; face recognition; image colour analysis; real-time systems; teleconferencing; tracking; audio data; automated videoconferencing; color data; complex backgrounds; contour geometry; facial features; hierarchical structure; image processing; initial talker location estimation; microphone array data; multi-source face tracking; multimedia; precise localization; precise tracking; real-time face tracker; robust face discrimination; similar objects; sound cues; source motion; virtual reality; visual cues; visual data; Acoustic signal detection; Cameras; Color; Face detection; Facial features; Geometry; Humans; Microphone arrays; Motion analysis; Skin;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Signal Processing, 1999 IEEE 3rd Workshop on

Conference_Location

Copenhagen

Print_ISBN

0-7803-5610-1

Type

conf

DOI

10.1109/MMSP.1999.793815

Filename

793815