Title :
Segmentation of SAR images with Weibull distribution
Author :
Fernandes, David
Author_Institution :
Inst. Tecnologico de Aeronaut., Centro Tecnico Aerosp., Sao Paulo, Brazil
Abstract :
The SAR amplitude image is represented by the speckle-texture multiplicative model with Weibull distribution. A nonlinear transformation to generate the texture image from the original speckled image is proposed. The extraction of the texture image from the Weibull-distributed SAR image employs the local estimation of the scale and form parameters of the Weibull distribution. Actual SAR images are used to show the performance of the proposed segmentation method
Keywords :
Weibull distribution; geophysical signal processing; geophysical techniques; image segmentation; image texture; radar imaging; remote sensing by radar; spaceborne radar; speckle; synthetic aperture radar; SAR amplitude image; SAR image; SAR imaging; Weibull distribution; geophysical measurement technique; image segmentation; image texture; land surface; nonlinear transformation; original speckled image; radar remote sensing; spaceborne radar; speckle-texture multiplicative model; synthetic aperture radar; terrain mapping; Electronic mail; Exponential distribution; Image generation; Image segmentation; Pixel; Probability density function; Random variables; Reflection; Speckle; Weibull distribution;
Conference_Titel :
Geoscience and Remote Sensing Symposium Proceedings, 1998. IGARSS '98. 1998 IEEE International
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4403-0
DOI :
10.1109/IGARSS.1998.702785
