Title :
Terrain classification via texture modelling of SAR and SAR coherency images
Author :
Meagher, Jonathan P. ; Homer, John ; Paget, Rupert ; Longstaff, Dennis
Author_Institution :
Dept. of Electr. & Comput. Eng., Queensland Univ., Brisbane, Qld., Australia
Abstract :
The authors investigate the use of the SAR coherence image and SAR intensity images for terrain classification. In particular, they present two algorithms which utilise both the coherence and intensity images, to produce an improved classification map. A kernel-based density estimation Markov random field methodology is employed for texture modelling
Keywords :
Markov processes; geophysical signal processing; geophysical techniques; image classification; image texture; radar imaging; remote sensing by radar; synthetic aperture radar; Markov random field method; SAR coherency image; algorithm; geophysical measurement technique; image classification; image texture modelling; intensity image; kernel-based density estimation; land surface; radar imaging; radar remote sensing; synthetic aperture radar; terrain mapping; Coherence; Image generation; Image sensors; Information processing; Markov random fields; Pixel; Probability; Satellites; Signal processing; Testing;
Conference_Titel :
Geoscience and Remote Sensing, 1997. IGARSS '97. Remote Sensing - A Scientific Vision for Sustainable Development., 1997 IEEE International
Print_ISBN :
0-7803-3836-7
DOI :
10.1109/IGARSS.1997.609223
