Today ship hull inspection including the examination of the external coating, detection of defects, and other types of external degradation such as corrosion and marine growth is conducted underwater by means of Remotely Operated Vehicles (ROVs). The inspection process consists of a manual video analysis which is a time-consuming and labor-intensive process. To address this, we propose an automatic video analysis system using deep learning and computer vision to improve upon existing methods that only consider spatial information on individual frames in underwater ship hull video inspection. By exploring the benefits of adding temporal information and analyzing frame-based classifiers, we propose a multi-label video classification model that exploits the self-attention mechanism of transformers to capture spatiotemporal attention in consecutive video frames. Our proposed method has demonstrated promising results and can serve as a benchmark for future research and development in underwater video inspection applications.
@article{arxiv.2305.17338,
title = {Multi-label Video Classification for Underwater Ship Inspection},
author = {Md Abulkalam Azad and Ahmed Mohammed and Maryna Waszak and Brian Elvesæter and Martin Ludvigsen},
journal= {arXiv preprint arXiv:2305.17338},
year = {2023}
}
Comments
Accepted to be presented at OCEANS 2023 Limerick conference and will be published by IEEE