Parameter estimation in SAR imagery using stochastic distances and asymmetric kernels

The Statistical modeling of the data is essential in order to interpret synthetic aperture radar (SAR) images. Speckled data have been described under the multiplicative model using the G family of distributions, which is able to describe rough and extremely rough areas better than the K distribut...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Gambini, María Juliana, Cassetti, Julia Analía, Lucini, María Magdalena, Frery, Alejandro César
Formato: Artículo
Lenguaje:Inglés
Publicado: Institute of Electrical and Electronics Engineers Inc. 2024
Materias:
Acceso en línea:http://repositorio.unne.edu.ar/handle/123456789/55296
Aporte de:
Descripción
Sumario:The Statistical modeling of the data is essential in order to interpret synthetic aperture radar (SAR) images. Speckled data have been described under the multiplicative model using the G family of distributions, which is able to describe rough and extremely rough areas better than the K distribution. The survey article discusses in detail several statistical models for this kind of data. Under the G model, different degrees of roughness are associated with different parameter values; therefore, it is of paramount importance to have high quality estimators. Several works have been devoted to the subject of improving estimation with two main venues of research, namely, analytic and resampling procedures.