Unsupervised amplitude and texture classification of SAR images with multinomial latent model

Koray Kayabol 1 Josiane Zerubia 2
1 ARIANA - Inverse problems in earth monitoring
CRISAM - Inria Sophia Antipolis - Méditerranée , Laboratoire I3S - SIS - Signal, Images et Systèmes
Abstract : We combine both amplitude and texture statistics of the Synthetic Aperture Radar (SAR) images for modelbased classification purpose. In a finite mixture model, we bring together the Nakagami densities to model the class amplitudes and a 2D Auto-Regressive texture model with t-distributed regression error to model the textures of the classes. A nonstationary Multinomial Logistic (MnL) latent class label model is used as a mixture density to obtain spatially smooth class segments. The Classification Expectation-Maximization (CEM) algorithm is performed to estimate the class parameters and to classify the pixels. We resort to Integrated Classification Likelihood (ICL) criterion to determine the number of classes in the model. We present our results on the classification of the land covers obtained in both supervised and unsupervised cases processing TerraSAR-X, as well as COSMO-SkyMed data.
Liste complète des métadonnées

Cited literature [73 references]  Display  Hide  Download

https://hal.inria.fr/hal-00745387
Contributor : Koray Kayabol <>
Submitted on : Thursday, October 25, 2012 - 2:22:04 PM
Last modification on : Monday, November 5, 2018 - 3:52:01 PM
Document(s) archivé(s) le : Saturday, January 26, 2013 - 3:55:08 AM

File

06305477.pdf
Publisher files allowed on an open archive

Identifiers

Collections

Citation

Koray Kayabol, Josiane Zerubia. Unsupervised amplitude and texture classification of SAR images with multinomial latent model. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2013, 22 (2), pp.561-572. ⟨10.1109/TIP.2012.2219545⟩. ⟨hal-00745387⟩

Share

Metrics

Record views

545

Files downloads

925