This project aims to develop an AI-driven, non-invasive, and cost-effective system for identifying, monitoring, and assessing defects in critical underwater infrastructure. The research will focus on advanced deep learning methods tailored to challenging underwater environments, using innovative data augmentation techniques that combine generative AI with physics-based simulations. The proposed methods and integrated prototype will be validated in controlled and real-world environments, supporting the sustainable, reliable, and efficient monitoring of underwater infrastructure.
Project funding:
Research Council of Lithuania, Designated Programme “Information technologies for the development of science and knowledge society”
Period of project implementation: 2026-09-01 - 2028-08-31
Project coordinator: Kaunas University of Technology
