The main goal of twist+1 project is to develop a framework that enables solutions to practical problems of computer vision using approaches that strongly use structure. This framework shall be applicable to the areas where structural computer vision methods are foreseen to be very useful like Segmentation, Tracking and Stereo Vision. Therefore we will focus on the following subgoals:
- finding object correspondences in image sequences,
- finding object correspondences in images from different viewpoints, and
- finding object correspondences in image sequences from different viewpoints
The combination of these approaches into a single framework, would simplify the solutions of many practical problems. We expect these methods to perform better, especially in terms of robustness and speed. Possible limits of such methods and corresponding questions that need to be answered are:
- What kind of influences have to be considered in case of drastic scene changes (i.e. object changes, illumination changes etc.)?
- How can an update of the scene representation (object model) be accomplished?
- Are the existing segmentation and graph matching methods under the assumption of structural search fast enough to allow real time performance?
- How can coarse-to-fine approaches be realized (e.g. using subsegmentations)?
Last modified: June 7, 2006 by Yll Haxhimusa