Options
Semantic Segmentation of Underwater Imagery Using Deep Networks Trained on Synthetic Imagery
Date Issued
04 August 2018
Date Available
08T11:55:17Z May 2019
Abstract
Recent breakthroughs in the computer vision community have led to the emergence of efficient deep learning techniques for end-to-end segmentation of natural scenes. Underwater imaging stands to gain from these advances, however, deep learning methods require large annotated datasets for model training and these are typically unavailable for underwater imaging applications. This paper proposes the use of photorealistic synthetic imagery for training deep models that can be applied to interpret real-world underwater imagery. To demonstrate this concept, we look at the specific problem of biofouling detection on marine structures. A contemporary deep encoder–decoder network, termed SegNet, is trained using 2500 annotated synthetic images of size 960 × 540 pixels. The images were rendered in a virtual underwater environment under a wide variety of conditions and feature biofouling of various size, shape, and colour. Each rendered image has a corresponding ground truth per-pixel label map. Once trained on the synthetic imagery, SegNet is applied to segment new real-world images. The initial segmentation is refined using an iterative support vector machine (SVM) based post-processing algorithm. The proposed approach achieves a mean Intersection over Union (IoU) of 87% and a mean accuracy of 94% when tested on 32 frames extracted from two distinct real-world subsea inspection videos. Inference takes several seconds for a typical image.
Sponsorship
Science Foundation Ireland
Other Sponsorship
CAPACITES/IXEAD Society
Type of Material
Journal Article
Publisher
MDPI AG
Journal
Journal of Marine Science and Engineering
Volume
6
Issue
3
Start Page
1
End Page
15
Copyright (Published Version)
2018 the Authors
Language
English
Status of Item
Peer reviewed
ISSN
2077-1312
This item is made available under a Creative Commons License
File(s)
Owning collection
Scopus© citations
42
Acquisition Date
Dec 11, 2023
Dec 11, 2023
Views
730
Last Week
1
1
Last Month
1
1
Acquisition Date
Dec 10, 2023
Dec 10, 2023
Downloads
353
Last Month
6
6
Acquisition Date
Dec 10, 2023
Dec 10, 2023