Geodesic tree-based dynamic programming for fast stereo reconstruction
National Tsing Hua University, Hsinchu, Taiwan, R.O.C.
IEEE 12th International Conference on Computer Vision Workshops (ICCV Workshops), 2009
@inproceedings{sin2009geodesic,
title={Geodesic tree-based dynamic programming for fast stereo reconstruction},
author={Sin, C.H. and Cheng, C.M. and Lai, S.H. and Yang, S.Y.},
booktitle={Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on},
pages={801–807},
year={2009},
organization={IEEE}
}
In this paper, we present a novel tree-based dynamic programming (TDP) algorithm for efficient stereo reconstruction. We employ the geodesic distance transformation for tree construction, which results in sound image over-segmentation and can be easily parallelized on graphic processing unit (GPU). Instead of building a single tree to convey message in dynamic programming (DP), we construct multiple trees according to the image geodesic distance to allow for parallel message passing in DP. In addition to efficiency improvement, the proposed algorithm provides visually sound stereo reconstruction results. Compared with previous related approaches, our experimental results demonstrate superior performance of the proposed algorithm in terms of efficiency and accuracy.
August 7, 2011 by hgpu
