Analysis of Multibeam SONAR Data using Dissimilarity Representations

TL;DR

This paper explores a novel approach to visualizing high-dimensional multibeam sonar data by employing dissimilarity representations and probabilistic models to enhance maritime situation awareness.

Contribution

It introduces a mathematical framework for dissimilarity-based visualization of sonar signals, incorporating uncertainty modeling and non-euclidean measures for improved data interpretation.

Findings

Effective visualization of simulated sonar data demonstrated

Incorporation of uncertainty improves data interpretability

Non-euclidean measures show potential for better similarity assessment

Abstract

This paper considers the problem of low-dimensional visualisation of very high dimensional information sources for the purpose of situation awareness in the maritime environment. In response to the requirement for human decision support aids to reduce information overload (and specifically, data amenable to inter-point relative similarity measures) appropriate to the below-water maritime domain, we are investigating a preliminary prototype topographic visualisation model. The focus of the current paper is on the mathematical problem of exploiting a relative dissimilarity representation of signals in a visual informatics mapping model, driven by real-world sonar systems. An independent source model is used to analyse the sonar beams from which a simple probabilistic input model to represent uncertainty is mapped to a latent visualisation space where data uncertainty can be accommodated. The use of euclidean and non-euclidean measures are used and the motivation for future use of non-euclidean measures is made. Concepts are illustrated using a simulated 64 beam weak SNR dataset with realistic sonar targets.