A Novel Context-Adaptive Fusion of Shadow and Highlight Regions for Efficient Sonar Image Classification

TL;DR

This paper introduces a comprehensive sonar image classification framework that emphasizes shadow features, adaptive segmentation, and noise reduction, supported by a new dataset with physics-informed noise for improved underwater object detection.

Contribution

It presents a novel context-adaptive classification method focusing on shadow regions, a region-aware denoising model, and an extended dataset for underwater sonar analysis.

Findings

Enhanced classification accuracy with shadow features

Improved noise robustness through adaptive denoising

Effective detection of naval mines in sonar images

Abstract

Sonar imaging is fundamental to underwater exploration, with critical applications in defense, navigation, and marine research. Shadow regions, in particular, provide essential cues for object detection and classification, yet existing studies primarily focus on highlight-based analysis, leaving shadow-based classification underexplored. To bridge this gap, we propose a Context-adaptive sonar image classification framework that leverages advanced image processing techniques to extract and integrate discriminative shadow and highlight features. Our framework introduces a novel shadow-specific classifier and adaptive shadow segmentation, enabling effective classification based on the dominant region. This approach ensures optimal feature representation, improving robustness against noise and occlusions. In addition, we introduce a Region-aware denoising model that enhances sonar image quality by preserving critical structural details while suppressing noise. This model incorporates an explainability-driven optimization strategy, ensuring that denoising is guided by feature importance, thereby improving interpretability and classification reliability. Furthermore, we present S3Simulator+, an extended dataset incorporating naval mine scenarios with physics-informed noise specifically tailored for the underwater sonar domain, fostering the development of robust AI models. By combining novel classification strategies with an enhanced dataset, our work addresses key challenges in sonar image analysis, contributing to the advancement of autonomous underwater perception.