TerraSAR-X Image Analysis using PCA, ICA and SVM
Conference: EUSAR 2008 - 7th European Conference on Synthetic Aperture Radar
06/02/2008 - 06/05/2008 at Friedrichshafen, Germany
Proceedings: EUSAR 2008
Pages: 4Language: englishTyp: PDF
Personal VDE Members are entitled to a 10% discount on this title
Authors:
Chaabouni-Chouayakh, Houda; Datcu, Mihai (German Aerospace Center (DLR), Oberpfaffenhofen D-82234 Wessling - Germany)
Mata-Moya, David de la (Departamento de Teoría de la Señal y Comunicaciones, Universidad de Alcalá-Spain)
Datcu, Mihai (Germany and Paris Institute of Technology GET/Télécom Paris, 46 rue Barrault, F-75 013 Paris-France)
Abstract:
Recognizing scenes using high resolution Synthetic Aperture Radar (SAR) images requires the capability to identify relevant signal signatures, depending on variable image acquisition geometry, arbitrary objects poses and configurations. This paper addresses a target recognition problem in high resolution SAR images using Principal Components Analysis (PCA), Independent Components Analysis (ICA), as well as a combination of both, for feature extraction; and Support Vector Machine (SVM) for classification. The performance of these techniques were analyzed and tested on a four-class database collected from the same TerraSAR-X High Resolution spotlight Mode (HS), Multi Look Ground Range Detected (MGD) image, over the Pyramids of Gizeh in Egypt.