KummerU clutter model for PolSAR data: Application to segmentation and classification
Résumé
In this paper, Spherically Invariant Random Vectors (SIRV) are introduced to describe the heterogeneity of the Polarimetric Synthetic Aperture Radar (PolSAR) clutter. In this context, the scalar texture parameter and the normalized covariance matrix are extracted from the PolSAR images. If the texture parameter is modeled by a Fisher Probability Density Function (PDF), the observed target scattering vector follows a KummerU PDF. This PDF is then implemented in a hierarchical segmentation algorithm. Finally, segmentation results are shown on both synthetic and real images.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
Loading...