Coarse-to-Fine Non-Rigid Registration for Side-Scan Sonar Mosaicking

2025-11-19

AI Summary

Side-scan sonar image mosaicking is challenged by complex, spatially varying nonlinear distortions; conventional rigid/affine methods lack sufficient modeling capacity, while existing non-rigid approaches suffer from overfitting and poor robustness under sparse-texture conditions. This paper proposes a coarse-to-fine hierarchical non-rigid registration framework: (1) initialization via thin-plate splines coupled with superpixel-guided structured segmentation to enhance geometric consistency; (2) integration of global deformation priors and local detail-aware deformations, enabled by unsupervised pretraining of the SynthMorph network for dense correspondence estimation; and (3) multi-level deformation field fusion to ensure both smoothness and structural fidelity. Evaluated on real sonar data, the method substantially outperforms state-of-the-art rigid, traditional non-rigid, and deep learning-based approaches—achieving superior registration accuracy, structural consistency, and deformation smoothness.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Side-scan sonar mosaicking plays a crucial role in large-scale seabed mapping but is challenged by complex non-linear, spatially varying distortions due to diverse sonar acquisition conditions. Existing rigid or affine registration methods fail to model such complex deformations, whereas traditional non-rigid techniques tend to overfit and lack robustness in sparse-texture sonar data. To address these challenges, we propose a coarse-to-fine hierarchical non-rigid registration framework tailored for large-scale side-scan sonar images. Our method begins with a global Thin Plate Spline initialization from sparse correspondences, followed by superpixel-guided segmentation that partitions the image into structurally consistent patches preserving terrain integrity. Each patch is then refined by a pretrained SynthMorph network in an unsupervised manner, enabling dense and flexible alignment without task-specific training. Finally, a fusion strategy integrates both global and local deformations into a smooth, unified deformation field. Extensive quantitative and visual evaluations demonstrate that our approach significantly outperforms state-of-the-art rigid, classical non-rigid, and learning-based methods in accuracy, structural consistency, and deformation smoothness on the challenging sonar dataset.

Problem

• Addresses non-linear distortions in side-scan sonar mosaicking
• Overcomes overfitting in sparse-texture sonar data registration
• Integrates global and local deformations for accurate seabed mapping

Innovation

• Coarse-to-fine hierarchical non-rigid registration framework
• Superpixel-guided segmentation for structurally consistent patches
• Unsupervised SynthMorph network for dense flexible alignment