SAR image segmentation using level sets and region competition under the GH model

Mostrar todas las versiones(3)

Synthetic Aperture Radar (SAR) images are dificult to segment due to their characteristic noise, called speckle, which is multiplicative, non-gaussian and has a low signal to noise ratio. In this work we use the GH distribution to model the SAR data from the different regions of the image. We estima...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Buemi, M.E., Goussies, N., Jacobo, J., Mejail, M.
Formato: Artículo publishedVersion
Lenguaje:Inglés
Publicado: 2009
Materias:
GHdistribution
Level set
Multiregion competition
SAR images
Segmentation
Level Set
SAR Images
Algorithms
Competition
Computer applications
Computer vision
Imaging systems
Signal to noise ratio
Synthetic aperture radar
Image segmentation
Acceso en línea:http://hdl.handle.net/20.500.12110/paper_03029743_v5856LNCS_n_p153_Buemi
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
Descripción
Sumario:Synthetic Aperture Radar (SAR) images are dificult to segment due to their characteristic noise, called speckle, which is multiplicative, non-gaussian and has a low signal to noise ratio. In this work we use the GH distribution to model the SAR data from the different regions of the image. We estimate their statistical parameters and use them in a segmentation algorithm based on multiregion competition. We then apply this algorithm to segment simulated as well as real SAR images and evaluate the accuracy of the segmentation results obtained. © 2009 Springer-Verlag Berlin Heidelberg.

Ejemplares similares