Seabed segmentation using optimized statistics of sonar textures - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Geoscience and Remote Sensing Année : 2009

Seabed segmentation using optimized statistics of sonar textures

Résumé

We propose and compare two supervised segmentation algorithms for textured sonar images with respect to seafloor types. We characterize sea-floors by a set of empirical distributions estimated on texture responses to a wide set of different filters with various parameterizations and we introduce a novel similarity measure between sonar textures in this attribute space. Our similarity measure is defined as a weighted sum of Kullback-Leibler divergences between texture features. The weight setting is twofold. First we weight each filter, according to its discrimination power, the computation of these weights are issued from a margin maximization criterion. Second, an additional weight, evaluated as an angular distance between the incidence angles of the compared texture samples, is considered to take into account sonar image acquisition process that leads to a variability of the backscattered (BS) value and the texture aspect with the incidence angle range. The first algorithm is stated in a Bayesian framework and conditional likelihood are expressed using the proposed similarity measure between local pixel statistics and the seafloor prototype statistics. The second method is stated in a variational framework as the minimization of a region-based functional that involves the similarity between global region texture based statistics and the predefined prototypes.

Dates et versions

hal-01764977 , version 1 (12-04-2018)

Identifiants

Citer

Imen Karoui, Ronan Fablet, Jean-Marc Boucher, Jean-Marie Augustin. Seabed segmentation using optimized statistics of sonar textures. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47 (6), pp.1621 - 1631. ⟨10.1109/TGRS.2008.2006362⟩. ⟨hal-01764977⟩
19 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More