Seabed Classification using a steerable Multibeam Eco Sounder - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Seabed Classification using a steerable Multibeam Eco Sounder

Résumé

The new steerable 3D multi-beam echo sounder system SEAPIX offers different operational modes to acquire supplementary information during the acquisition process. In this paper, we focused on 2 modes : the classical MBES mode and the longitudinal mode. The consistency of the data acquired from these two modes was verified through the evaluation of statistical features (mean, standard deviation, Kullback-Liebler divergence). Besides, the longitudinal mode also proposes a new date type : pixel-based data, which offers a complete backscatering profile for each pixel. A comparison of classification performance was perfomed with a sandard Bayesian method. The pixel-based date clearly outperformed the classical mode's data (93.36% vs. 50.65% using a level-based method and 81.5% using a profile-based method.
Fichier non déposé

Dates et versions

hal-01444309 , version 1 (23-01-2017)

Identifiants

Citer

Trung-Kien Nguyen, Didier Charlot, Jean-Marc Boucher, Gilles Le Chenadec, Ronan Fablet. Seabed Classification using a steerable Multibeam Eco Sounder. OCEANS 2016 - Monterey : MTS/IEEE international conference, Sep 2016, Monterey, United States. pp.1 - 4, ⟨10.1109/OCEANS.2016.7761020⟩. ⟨hal-01444309⟩
164 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More