Paper Info
Title
A Real-Time Face Tracking using the Stereo Active Appearance Model
Abstract
This paper proposes a real-time 3D face tracking system. This system uses a stereo active appearance model fitting (STAAM) algorithm that uses multiple calibrated perspective cameras to compute the 3D shape and rigid motion parameters. The use of calibration information reduces the number of model parameters, restricts the degree of freedom in the model parameters, and increases the accuracy and speed of fitting. The real-time face tracking system works alternating two different modes: the detection mode detects the face and eyes in an image and the tracking mode tracks the detected face using the STAAM. In addition, it utilizes a histogram matching to make the system robust to lighting conditions, and uses the motion information to compensate the temporal fluctuation of the captured images. The experimental results show that the proposed system operates robustly under varying lighting conditions and fast in the real-time manner at above 8 frames/sec.
Year
DOI
Venue
2006
10.1109/ICIP.2006.312998
ICIP
Keywords
Field
DocType
motion compensation,face tracking,tracking mode,face recognition,multiple calibrated perspective cameras,calibration information,rigid motion parameters,staam algorithm,3d shape parameters,stereo active appearance model fitting algorithm,detection mode,histogram matching,real-time face tracking,tracking,object detection,temporal fluctuation,stereo image processing,stereo active appearance model,real-time systems,active appearance model,real time,degree of freedom,real time systems
Facial recognition system,Object detection,Computer vision,Degrees of freedom (statistics),Pattern recognition,Computer science,Motion compensation,Histogram matching,Tracking system,Active appearance model,Artificial intelligence,Facial motion capture
Conference
ISSN
ISBN
Citations 
1522-4880
1-4244-0480-0
10
PageRank 
References 
Authors
0.61
8
2
Name
Order
Citations
PageRank
Daijin Kim11882126.85
Jaewon Sung21529.57