Fast variational multi-view segmentation through backprojection of spatial constraints |
| |
Authors: | C. Reinbacher,M. Rü ther,H. Bischof |
| |
Affiliation: | Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16/II, Graz, Austria |
| |
Abstract: | We present a variational segmentation method which exploits color, edge and spatial information between an arbitrary number of views. In contrast to purely image based information like color and gradient, spatial consistency is a new cue for segmentation, which originates from the field of 3D reconstruction. We show that this cue can be easily integrated in a variational formulation and allows pixel-accurate segmentation, even for objects which are hard to segment. The use of inherently parallel algorithms and the implementation on modern GPUs allows us to apply this method to semi-supervised and completely automatic settings. On publicly available datasets we show that our method is faster and more accurate than the state of the art. The successful applications within a catadioptric measurement system and multi-view background subtraction shows its practical relevance. |
| |
Keywords: | Multi-view Variational segmentation GPU Catadioptric |
本文献已被 ScienceDirect 等数据库收录! |
|