Semantic Segmentation in Underwater Ship Inspections: Benchmark and Dataset
Journal article, Peer reviewed
Published version
Permanent lenke
https://hdl.handle.net/11250/3052506Utgivelsesdato
2022Metadata
Vis full innførselSamlinger
- Institutt for marin teknikk [3472]
- Publikasjoner fra CRIStin - NTNU [38672]
Originalversjon
10.1109/JOE.2022.3219129Sammendrag
In this paper, we present the first large-scale dataset for underwater ship Lifecycle Inspection, Analysis and Condition Information (LIACI). It contains 1893 images with pixel annotations for 10 object categories: defects, corrosion, paint peel, marine growth, sea chest gratings, overboard valves, propeller, anodes, bilge keel, and ship hull. The images have been collected during underwater ship inspections and annotated by human domain experts. We also present a benchmark evaluation of state-of-the-art semantic segmentation approaches based on standard performance metrics. Consequently, we propose to use U-Net with a MobileNetV2 backbone for the segmentation task due to its balanced trade-off between performance and computational efficiency which is essential if used for real-time evaluation. Also, we demonstrate its benefits for in-water inspections by providing quantitative evaluations of the inspection findings. With a variety of use cases, the proposed segmentation pipeline and the LIACI dataset create new promising opportunities for future research in underwater ship inspections. The dataset is made publicly available for non-commercial use on https://liaci.sintef.cloud. Semantic Segmentation in Underwater Ship Inspections: Benchmark and Dataset