Efficient Silhouette Extraction with Dynamic Viewpoint

8 years 5 months ago
Efficient Silhouette Extraction with Dynamic Viewpoint
A novel approach is proposed that extends the classical background subtraction method to extract silhouettes from videos in real time with dynamic viewpoint variation caused by camera movement. First, manifold learning is used to model the background under viewpoint variations. Then, for each new frame, the background image corresponding to the same viewpoint is synthesized on the fly by examining the local neighborhood on the manifold, and the silhouette is extracted via background subtraction. An extension is also presented to generate stabilized silhouettes at any fixed viewpoint within the training range. Experiments show that our approach can efficiently extract accurate silhouettes in complex situations while maintaining a low noise level.
Yueting Zhuang, Cheng Chen
Added 07 Dec 2010
Updated 07 Dec 2010
Type Conference
Year 2007
Where ICCV
Authors Yueting Zhuang, Cheng Chen
Comments (0)