대한원격탐사학회:학술대회논문집 (Proceedings of the KSRS Conference)
- 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
- /
- Pages.361-364
- /
- 2008
- /
- 1226-9743(pISSN)
A STUDY ON SPATIAL FEATURE EXTRACTION IN THE CLASSIFICATION OF HIGH RESOLUTIION SATELLITE IMAGERY
- Han, You-Kyung (Department of Civil and Environmental Engineering, Seoul National University) ;
- Kim, Hye-Jin (Department of Civil and Environmental Engineering, Seoul National University) ;
- Choi, Jae-Wan (Department of Civil and Environmental Engineering, Seoul National University) ;
-
Kim, Yong-Il
(Department of Civil and Environmental Engineering, Seoul National University)
- 발행 : 2008.10.29
초록
It is well known that combining spatial and spectral information can improve land use classification from satellite imagery. High spatial resolution classification has a limitation when only using the spectral information due to the complex spatial arrangement of features and spectral heterogeneity within each class. Therefore, extracting the spatial information is one of the most important steps in high resolution satellite image classification. In this paper, we propose a new spatial feature extraction method. The extracted features are integrated with spectral bands to improve overall classification accuracy. The classification is achieved by applying a Support Vector Machines classifier. In order to evaluate the proposed feature extraction method, we applied our approach to KOMPSAT-2 data and compared the result with the other methods.