Synthetic Sonar Image Simulation with Various Seabed Conditions for Automatic Target Recognition

TL;DR

This paper introduces a novel Unreal Engine-based method to generate realistic synthetic sonar images with various seabed conditions, aiding in training and evaluating automatic target recognition systems.

Contribution

It presents a new approach to produce acoustically compliant underwater imagery with visual effects for ATR training, improving dataset size and diversity.

Findings

Generated images include back-scatter noise and acoustic shadow effects.

The method enables fast rendering suitable for large datasets.

Analysis shows potential as a substitute for real sonar data.

Abstract

We propose a novel method to generate underwater object imagery that is acoustically compliant with that generated by side-scan sonar using the Unreal Engine. We describe the process to develop, tune, and generate imagery to provide representative images for use in training automated target recognition (ATR) and machine learning algorithms. The methods provide visual approximations for acoustic effects such as back-scatter noise and acoustic shadow, while allowing fast rendering with C++ actor in UE for maximizing the size of potential ATR training datasets. Additionally, we provide analysis of its utility as a replacement for actual sonar imagery or physics-based sonar data.