Proceedings of the KSRS Conference (대한원격탐사학회:학술대회논문집)
- 1999.11a
- /
- Pages.304-309
- /
- 1999
- /
- 1226-9743(pISSN)
Refinement of Disparity Map using the Rule-based Fusion of Area and Feature-based Matching Results
- Um, Gi-Mun (RS Team, Image Processing Dept., ETRI/CSTL) ;
- Ahn, Chung-Hyun (RS Team, Image Processing Dept., ETRI/CSTL) ;
- Kim, Kyung-Ok (RS Team, Image Processing Dept., ETRI/CSTL) ;
- Lee, Kwae-Hi (Elec. Eng. Dept. Sogang University)
- Published : 1999.11.01
Abstract
In this paper, we presents a new disparity map refinement algorithm using statistical characteristics of disparity map and edge information. The proposed algorithm generate a refined disparity map using disparity maps which are obtained from area and feature-based Stereo Matching by selecting a disparity value of edge point based on the statistics of both disparity maps. Experimental results on aerial stereo image show the better results than conventional fusion algorithms in the disparity error. This algorithm can be applied to the reconstruction of building image from the high resolution remote sensing data.
Keywords