Possibilistic Fuzzy Local Information C-Means for Sonar Image Segmentation

TL;DR

This paper introduces PFLICM, a novel clustering method combining fuzzy and possibilistic techniques with local spatial information to effectively segment high-quality SAS sonar images into different sea-floor textures.

Contribution

The paper proposes the PFLICM algorithm, integrating fuzzy and possibilistic clustering with spatial data for improved sonar image segmentation.

Findings

PFLICM outperforms existing segmentation methods on SAS images.

Effective differentiation of sea-floor textures like sand, rock, and sea grass.

Demonstrated robustness across multiple SAS scenes.

Abstract

Side-look synthetic aperture sonar (SAS) can produce very high quality images of the sea-floor. When viewing this imagery, a human observer can often easily identify various sea-floor textures such as sand ripple, hard-packed sand, sea grass and rock. In this paper, we present the Possibilistic Fuzzy Local Information C-Means (PFLICM) approach to segment SAS imagery into sea-floor regions that exhibit these various natural textures. The proposed PFLICM method incorporates fuzzy and possibilistic clustering methods and leverages (local) spatial information to perform soft segmentation. Results are shown on several SAS scenes and compared to alternative segmentation approaches.