A coupled stochastic image model for restoration of Synthetic Aperture Radar (SAR) images affected by speckle and for extraction of related intensity discontinuities is presented. The two problems are ill-posed [2], as defined by Hadamard [7], and require the use of regularization methods. It is shown that the coupled Gibbs-Markov Random Fields technique for piecewise constant image reconstruction [10] can be utilized by means of the SAR-image observation model proposed in [5]. Simulation results on test images are reported.
A coupled MRF model for SAR image restoration and edge-extraction
REGAZZONI, CARLO
1992-01-01
Abstract
A coupled stochastic image model for restoration of Synthetic Aperture Radar (SAR) images affected by speckle and for extraction of related intensity discontinuities is presented. The two problems are ill-posed [2], as defined by Hadamard [7], and require the use of regularization methods. It is shown that the coupled Gibbs-Markov Random Fields technique for piecewise constant image reconstruction [10] can be utilized by means of the SAR-image observation model proposed in [5]. Simulation results on test images are reported.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
