Next Article in Journal
Wave and Tidal Controls on Embayment Circulation and Headland Bypassing for an Exposed, Macrotidal Site
Previous Article in Journal
Optimized Reliability Based Upgrading of Rubble Mound Breakwaters in a Changing Climate
Previous Article in Special Issue
A Novel Iterative Water Refraction Correction Algorithm for Use in Structure from Motion Photogrammetric Pipeline
Article Menu
Issue 3 (September) cover image

Export Article

Open AccessArticle
J. Mar. Sci. Eng. 2018, 6(3), 93; https://doi.org/10.3390/jmse6030093

Semantic Segmentation of Underwater Imagery Using Deep Networks Trained on Synthetic Imagery

1
Dynamical Systems and Risk Laboratory, School of Mechanical and Materials Engineering, University College Dublin, 4 Dublin, Ireland
2
Marine and Renewable Energy Ireland (MaREI), University College Dublin, 4 Dublin, Ireland
3
Research Institute of Civil Engineering and Mechanics (GeM, CNRS UMR 6183), Sea and Littoral Research Institute (IUML, CNRS FR 3473), Université de Nantes, Centrale Nantes, 2 rue de la Houssinière BP 92208, 44322 Nantes, France
4
IXEAD/CAPACITES Society, 26 bd Vincent Gâche, 44200 Nantes, France
5
Department of Civil, Structural and Environmental Engineering, Trinity College Dublin, 2 Dublin, Ireland
*
Author to whom correspondence should be addressed.
Received: 4 July 2018 / Revised: 25 July 2018 / Accepted: 30 July 2018 / Published: 4 August 2018
(This article belongs to the Special Issue Underwater Imaging)
Full-Text   |   PDF [4664 KB, uploaded 7 August 2018]   |  

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. View Full-Text
Keywords: semantic segmentation; biofouling; image processing; underwater imaging semantic segmentation; biofouling; image processing; underwater imaging
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

O’Byrne, M.; Pakrashi, V.; Schoefs, F.; Ghosh, B. Semantic Segmentation of Underwater Imagery Using Deep Networks Trained on Synthetic Imagery. J. Mar. Sci. Eng. 2018, 6, 93.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
J. Mar. Sci. Eng. EISSN 2077-1312 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top