ShipwreckFinder: A QGIS Tool for Shipwreck Detection in Multibeam Sonar Data

2025-09-23

AI Summary

To address the labor-intensive and inefficient manual detection of shipwrecks in multibeam sonar data, this paper proposes an end-to-end deep learning–based automatic detection framework. Our method introduces three key contributions: (1) a hybrid training strategy integrating real and synthetically generated sonar imagery to enhance model generalization across diverse seafloor topographies; (2) an open-source QGIS plugin that unifies preprocessing, semantic segmentation inference—supporting both pixel-wise masks and bounding-box outputs—and interactive visualization; and (3) demonstrably superior detection accuracy and robustness over ArcGIS-based workflows and the classical inverse watershed algorithm, validated on multi-site empirical datasets. The proposed solution lowers domain-specific expertise requirements, advances automation and reproducibility in wreck detection, and is fully open-sourced—including code, models, and the QGIS plugin.

Technology Category

• Computer Vision: Segmentation
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification

Application Category

• Web Mining and Content Analysis: Web data integration and cleaning
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

In this paper, we introduce ShipwreckFinder, an open-source QGIS plugin that detects shipwrecks from multibeam sonar data. Shipwrecks are an important historical marker of maritime history, and can be discovered through manual inspection of bathymetric data. However, this is a time-consuming process and often requires expert analysis. Our proposed tool allows users to automatically preprocess bathymetry data, perform deep learning inference, threshold model outputs, and produce either pixel-wise segmentation masks or bounding boxes of predicted shipwrecks. The backbone of this open-source tool is a deep learning model, which is trained on a variety of shipwreck data from the Great Lakes and the coasts of Ireland. Additionally, we employ synthetic data generation in order to increase the size and diversity of our dataset. We demonstrate superior segmentation performance with our open-source tool and training pipeline as compared to a deep learning-based ArcGIS toolkit and a more classical inverse sinkhole detection method. The open-source tool can be found at https://github.com/umfieldrobotics/ShipwreckFinderQGISPlugin.

Problem

• Automates shipwreck detection in multibeam sonar data
• Reduces manual inspection time with deep learning model
• Generates segmentation masks or bounding boxes for wrecks

Innovation

• Open-source QGIS plugin for shipwreck detection
• Deep learning model trained with synthetic data
• Automated preprocessing and segmentation of sonar data