Self Organizing Map Based Radar Shadow Detection Using Textural Features

Conference: EUSAR 2006 - 6th European Conference on Synthetic Aperture Radar
05/16/2006 - 05/18/2006 at Dresden, Germany

Proceedings: EUSAR 2006

Pages: 4Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Gorener, Suleyman Hakan (Informatics Institute, Istanbul Technical University, Turkey)
Kartal, Mesut (Electrical and Electronics Engineering Faculty, Istanbul Technical University, Turkey)

This paper demonstrates the adaptation of a neural network based classification method to radar shadow detection process. The method which is previously used for automatic cloud detection and classification for satellite images using textural features is newly applied to radar shadow detection process. A novel utilization of Gray Level Co-occurrence Matrices (GLCM) method is preferred to extract textural features and Self Organized Maps (SOM) are used to classify the data according to pre-classified training set.