Geodesic Tree-Based Dynamic Programming for Fast Stereo Reconstruction
| Chin-Hong Sin | Chia-Ming Cheng | Shang-Hong Lai | Shan-Yung Yang |
| g9662553(at)oz.nthu.edu.tw | cmcheng(at)cs.nthu.edu.tw | lai(at)cs.nthu.edu.tw | syyang(at)iii.org.tw |
| National Tsing Hua University | National Tsing Hua University | National Tsing Hua University | Institute for Information Industry |
Abstract
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.
Related publications
-
Geodesic Tree-Based Dynamic Programming for Fast Stereo Reconstruction
C.-H. Sin, C.-M. Cheng, S.-H. Lai, S.-Y. Yang
IEEE Embedded Computer Vision Workshop (ICCV Workshops), Kyoto, Japan, Oct. 2009.(pdf)
Last updated on November 25, 2010.
