대한원격탐사학회:학술대회논문집 (Proceedings of the KSRS Conference)
- 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
- /
- Pages.421-424
- /
- 1999
- /
- 1226-9743(pISSN)
Filtering and Segmentation of radar imagery
- Kang, Sung-Chul (Department of Satellite Information Sciences, Pukyoung National University) ;
- Kim, Young-seup (Department of Satellite Information Sciences, Pukyoung National University) ;
- Yoon, Hong-Joo (Devision of Ocean System, Yousu National University) ;
- Baek, Seung-Gyun (Admap Korea Co.)
- 발행 : 1999.11.01
초록
The purpose of this study is to demonstrate a variety of methods for reducing the speckle noise content of SAR images, whilst at the same time retaining the fined details and average radiometric properties of the original data. In order to increase the accuracy of classification, Two categories of filters are used (speckleblind(simple), Speckle aware(intelligent)) and Segmentation of highly speckled radar imagery is achieved by the use of the Gaussian Markov Random Field model(GMRF). The problems in applying filtering techniques to different object types are discussed and the GMRF procedure and efficiency of the segmentation also discussed.
키워드