15 November 2007 Tracking face poses toward meeting video analysis
Author Affiliations +
Proceedings Volume 6786, MIPPR 2007: Automatic Target Recognition and Image Analysis; and Multispectral Image Acquisition; 678603 (2007) https://doi.org/10.1117/12.751049
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China
Abstract
We perform face tracking and pose estimation jointly within a mixed-state particle filter framework. Previous methods often used generative appearance models and naive prior state transition. We propose to use discriminating models, Adaboosted face detectors, to both measure observations and provide information for the proposal distribution which is combined with detection responses and prior transition model. Due to pose continuity, faces between discrete poses can be detected by neighboring pose-specific detectors and serve as importance samples. Thus continuous poses are obtained instead of discrete poses. Experiments show that our method is robust to large location and pose changes, partial occlusions and expressions.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ligeng Dong, Ligeng Dong, Linmi Tao, Linmi Tao, Guangyou Xu, Guangyou Xu, } "Tracking face poses toward meeting video analysis", Proc. SPIE 6786, MIPPR 2007: Automatic Target Recognition and Image Analysis; and Multispectral Image Acquisition, 678603 (15 November 2007); doi: 10.1117/12.751049; https://doi.org/10.1117/12.751049
PROCEEDINGS
7 PAGES


SHARE
RELATED CONTENT


Back to Top