Hierarchical Segmentation of Polarimetric SAR Images using Heterogeneous Clutter Models

Lionel Bombrun (1) , Jean-Marie Beaulieu (2) , Gabriel Vasile (1) , Jean-Philippe Ovarlez (3) , Frédéric Pascal (4) , Michel Gay (1, 5)

1 GIPSA-SIGMAPHY - GIPSA - Signal Images Physique
2 Department of Computer Science and Software Engineering [Québec]
3 ONERA - The French Aerospace Lab [Palaiseau]
4 SONDRA - Sondra, CentraleSupélec, Université Paris-Saclay (COmUE)
5 GIPSA-Services - GIPSA-Services

In this paper, heterogeneous clutter models are introduced to describe Polarimetric Synthetic Aperture Radar (PolSAR) data. Based on the Spherically Invariant Random Vectors (SIRV) estimation scheme, the scalar texture parameter and the normalized covariance matrix are extracted. If the texture parameter is modeled by a Fisher PDF, the observed target scattering vector follows a KummerU PDF. Then, this PDF is implemented in a hierarchical segmentation algorithm. Segmentation results are shown on high resolution PolSAR data at L and X band.

Mots clés: PolSAR data; Segmentation; KummerU PDF; Fisher PDF; Spherically Invariant Random Vectors

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

Lionel Bombrun, Jean-Marie Beaulieu, Gabriel Vasile, Jean-Philippe Ovarlez, Frédéric Pascal, et al.. Hierarchical Segmentation of Polarimetric SAR Images using Heterogeneous Clutter Models. IGARSS 2009 - IEEE International Geoscience and Remote Sensing Symposium, Jul 2009, Le Cap, South Africa. pp.5-8, ⟨10.1109/IGARSS.2009.5418271⟩. ⟨hal-00398923⟩