SAR Image Classification with Non-stationary Multinomial Logistic Mixture of Amplitude and Texture Densities

Koray Kayabol (1) , Aurélie Voisin (1) , Josiane Zerubia (1)

1 ARIANA - Inverse problems in earth monitoring

We combine both amplitude and texture statistics of the Synthetic Aperture Radar (SAR) images using Products of Experts (PoE) approach for classification purpose. We use Nakagami density to model the class amplitudes. To model the textures of the classes, we exploit a non-Gaussian Markov Random Field (MRF) texture model with t-distributed regression error. Non-stationary Multinomial Logistic (MnL) latent class label model is used as a mixture density to obtain spatially smooth class segments. We perform the Classification Expectation-Maximization (CEM) algorithm to estimate the class parameters and classify the pixels. We obtained some classification results of water, land and urban areas in both supervised and semi-supervised cases on TerraSAR-X data.

Mots clés: High resolution SAR; TerraSAR-X; classification; texture; multinomial logistic; Classification EM; Products of Experts

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Koray Kayabol, Aurélie Voisin, Josiane Zerubia. SAR Image Classification with Non-stationary Multinomial Logistic Mixture of Amplitude and Texture Densities. IEEE International Conference on Image Processing ICIP, Sep 2011, Brussels, Belgium. pp.173-176. ⟨inria-00592252⟩