Abstract
This paper introduces the concept of domain-adapted probabilistic segmentation for marine vessel classification. The evolution of corrosion is continuous and it is, therefore, impossible to acquire marine vessel inspection datasets representative of the entire active fleet. Additionally, human surveyors introduce high levels of subjectiveness in the classification process, resulting in potentially multiple equally valid but ambiguous classification results. Consequently, deterministic inspection is flawed. The goal of this paper is to address these challenges by using a probabilistic approach to segmentation while performing domain adaptation to align the feature space across the different stages of age degradation. We test a Probabilistic U-Net on both simulated images and images from real vessels and compare it against two novel probabilistic models. We have evaluated the models using both quantitative — energy distance as distribution similarity — and qualitative — feature reduction visualization — approaches. Our results indicate that the combination of probabilistic segmentation and domain adaption could potentially have a high impact on marine vessel surveys in the future.
Original language | English |
---|---|
Article number | 113568 |
Journal | Ocean Engineering |
Volume | 270 |
Number of pages | 9 |
ISSN | 0029-8018 |
DOIs | |
Publication status | Published - 15 Feb 2023 |
Bibliographical note
Funding Information:This work has been funded by the Innovation Fund Denmark (IFD) , through the Inspectrone (Autonomous and high-level commanded system for remote inspection of marine vessels to support classification and commercial operations) project, under contract number 8090-00080B .
Publisher Copyright:
© 2022 The Author(s)
Keywords
- Domain adaptation
- Marine vessels
- Probabilistic segmentation