Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Hi-index | 0.00 |
One of the merits of the Free-Viewpoint TV (FTV) is to generate a scene according to the user's viewpoint. In that case it is necessary to select a position within the 3D space as a basis to generate a scene. Therefore, we suggest an intelligent approach that automatically generates some reference viewpoints instead of FTV viewers. In this paper, a new approach to locate a focus of attention for the generation of candidate viewpoints is suggested. The suggested networked viewpoint controller exploits a spatiotemporal attention module for the smart user interaction of the future TV. It enables a viewer to change his viewpoints with easy by providing some candidate viewpoints automatically. It also prevents the viewer from disorientation caused occasionally from 3D space navigation.