A new method of pipeline detection in sonar imagery using self-organwing maps

Abstract

The main purpose of thLs paper is to detect and follow the pipeline in sonar image. This work is performed in two steps. The first is to split an transformed line image of pipeline signal into regions of uuiform texture usiug the Gray Level Cooccurrence Matrix Method (GLCM) which ts widely used in texture segmentation application. The second one addresses the unsupervised learning method based on the Arti5cial Neural Networks (SeU-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 method and some results from several experiments on the real world data set

Underwater digital terrain model with GPS-aided high-resolution profile-scan sonar images

“…Gray-level co-occurrence matrix (GLCM) is the two dimensional matrix of joint probabilities between pairs of pixels, The GLCM P represents the repeated occurrence of pairs of pixels i, j going from gray level i to gray level j through distance d along direction θ [10,11] . And neighborhood GLCM (NGLCM) without direction was proposed in Ref.…”

“…are defined for analyzing [10] . In this paper NGLCM is used the most probable echo strength region extraction, which depends on the grayscale value and spatial distribution in a given window.…”