TOU03: Automated Anomaly Detection on Naval Frigate Structures Using Drone Photogrammetry
- made by Chat GPT
Toulon
- Organisation
- Service de Soutien de la Flotte (SSF Toulon)
- Patrick DEBONS
The Fleet Support Service (SSF) provides high-definition images and videos captured by drones flying around a naval frigate. These data sets have been used to generate a detailed 3D model of the ship’s exterior structure via photogrammetry. Currently, inspection of the ship’s hull, superstructure, and critical external components is performed manually by experts reviewing visual footage and 3D reconstructions. This is time-consuming and prone to human oversight.
- What the challenge owner would like to develop over 48h
- Develop a prototype solution that automatically analyzes drone-collected imagery and the associated 3D model to detect anomalies such as cracks, corrosion, deformations, or missing parts on the frigate’s structure. The goal is to demonstrate how AI and computer vision can support predictive maintenance, reduce inspection time, and improve reliability.
- Which skills the challenge owner is looking for
- Drone data processing, photogrammetry understanding, 3D data visualization, Front-end skills for a clear demo (web or desktop)
