Stereo Matching with Nonlinear Diffusion
International Journal of Computer Vision
Digital Image Processing
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Stereo with Multiple Windowing
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Fast Boundary Detection: A Generalization and a New Algorithm
IEEE Transactions on Computers
Hi-index | 0.00 |
In this paper, we propose a stereo matching algorithm using multiple windows to recover sharp object boundaries. In order to achieve this goal, we employ commonly used techniques, such as left-right consistency, uniqueness constraint, and expansible multiple windows. By adding a new idea of multiple windows over these techniques, we can minimize the boundary overreach, which is usually caused by the unsuitable window size or shape. We demonstrate that the algorithm using a new multiple windows can display the dense and sharp disparity map and the windows adaptively used according to features of boundary edges. A problem generated by the disposition order of multiple windows is also presented.