Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks

TL;DR

This paper introduces MC-pix2pix, a novel Markov conditional GAN for generating realistic full-length sonar data, enhancing training and validation for underwater autonomous systems with high speed and control.

Contribution

The paper presents a new Markov conditional GAN architecture for realistic synthetic sonar data generation, addressing artefacts and environmental factors, with improved speed and control.

Findings

Generated data is nearly indistinguishable from real sonar data.

Bootstrapping ATR systems with synthetic data improves performance.

Synthetic data generation is 18 times faster than real data acquisition.

Abstract

Deployment and operation of autonomous underwater vehicles is expensive and time-consuming. High-quality realistic sonar data simulation could be of benefit to multiple applications, including training of human operators for post-mission analysis, as well as tuning and validation of autonomous target recognition (ATR) systems for underwater vehicles. Producing realistic synthetic sonar imagery is a challenging problem as the model has to account for specific artefacts of real acoustic sensors, vehicle altitude, and a variety of environmental factors. We propose a novel method for generating realistic-looking sonar side-scans of full-length missions, called Markov Conditional pix2pix (MC-pix2pix). Quantitative assessment results confirm that the quality of the produced data is almost indistinguishable from real. Furthermore, we show that bootstrapping ATR systems with MC-pix2pix data can improve the performance. Synthetic data is generated 18 times faster than real acquisition speed, with full user control over the topography of the generated data.