Physics-informed simulation framework for realistic sonar image generation and statistical validation

2026-05-19

AI Summary

Existing synthetic sonar imagery lacks rigorous quantitative validation, limiting its reliability in real-world applications. This work proposes ACOUSIM, a physics-based simulation platform implemented in Gazebo that generates controllable sonar images with adjustable seabed textures, shadows, platform altitude, and noise characteristics. For the first time without relying on generative models, the study establishes a quantitative sim-to-real alignment benchmark using distributional distances—specifically Kullback–Leibler (KL) divergence, Jensen–Shannon (JS) divergence, and Earth Mover’s Distance. Through statistical analysis of Local Binary Pattern (LBP) features, the method achieves high texture distribution alignment (KL < 0.07) on the SeabedObjects-KLSG-II and SCTD datasets. Furthermore, intensity distributions of planar objects align more closely than those of ship-like objects, demonstrating the approach’s effectiveness and reproducibility.

Abstract

Synthetic sonar datasets offer a scalable alternative to costly real-world acquisition, yet their utility remains limited by the absence of rigorous quantitative validation. We present ACOUSIM (ACOustic SIMulation and Validation Platform), a physics-informed framework that evaluates the statistical alignment between synthetic and real sonar imagery without relying on generative models. A Gazebo-based environment generates sonar-like images by explicitly controlling seabed texture, illumination-driven shadowing, platform altitude, and noise. Realism is quantified against two public sonar datasets, SeabedObjects-KLSG-II and Sonar Common Target Detection (SCTD), using global intensity and local texture (LBP) distributions assessed via Kullback-Leibler divergence, Jensen-Shannon divergence, and Earth Mover's Distance. Results show strong texture alignment (KL < 0.07) across all classes, with plane-class intensity alignment outperforming ship-class due to shadow geometry complexity. ACOUSIM establishes a reproducible, distribution-level baseline for sim-to-real sonar evaluation and directly supports reliable dataset validation for underwater image analysis.

Problem

• synthetic sonar
• statistical validation
• sim-to-real gap
• realism evaluation
• underwater imaging

Innovation

• physics-informed simulation
• sonar image generation
• statistical validation
• distribution alignment
• Gazebo-based rendering