Using Self-Organizing Maps Approach to Pipeline Localization

Abstract : The aim of this paper is to detect and follow the pipeline in sonar imagery. This work is performed in two steps. The first is to split an image (first experiment) or an transformed line image of pipeline image (second experiment) into regions of uniform texture using the Gray Level Co-occurrence Matrix Method (GLCM). The second addresses the unsupervised learning method based on the Artificial Neural Networks (Self-Organizing Map or SOM) used for determining the comparative model of pipeline from the image. To increase the performance of SOM, we propose a penalty function based on data histogram visualization for detecting the position of pipeline. After a brief review of both techniques (GLCM and SOM), we will present our methods and some results from several experiments on the real world data set
Type de document :
Communication dans un congrès
OCEANS, Sep 2003, San Diego, CA, United States. MTS/IEEE International Conference, pp.2398-2403, 2003
Liste complète des métadonnées

Littérature citée [8 références]  Voir  Masquer  Télécharger

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00141703
Contributeur : Bruno Jouvencel <>
Soumis le : samedi 14 avril 2007 - 12:27:45
Dernière modification le : jeudi 11 janvier 2018 - 06:26:17
Document(s) archivé(s) le : vendredi 21 septembre 2012 - 14:07:16

Identifiants

  • HAL Id : lirmm-00141703, version 1

Collections

Citation

Amornrit Puttipipatkajorn, Bruno Jouvencel, Tomas Salgado-Jimenez. Using Self-Organizing Maps Approach to Pipeline Localization. OCEANS, Sep 2003, San Diego, CA, United States. MTS/IEEE International Conference, pp.2398-2403, 2003. 〈lirmm-00141703〉

Partager

Métriques

Consultations de la notice

127

Téléchargements de fichiers

138