Gary A. Atkinson
Image segmentation of underfloor scenes using a mask regions convolutional neural network with two-stage transfer learning
Atkinson, Gary A.; Zhang, Wenhao; Hansen, Mark F.; Holloway, Mathew L.; Napier, Ashley A.
Authors
Dr Wenhao Zhang Wenhao.Zhang@uwe.ac.uk
Associate Professor of Computer Vision and Machine Learning
Mark Hansen Mark.Hansen@uwe.ac.uk
Professor of Machine Vision and Machine Learning
Mathew L. Holloway
Ashley A. Napier
Abstract
© 2020 Elsevier B.V. Enclosed spaces are common in built structures but pose a challenge to many forms of manual or robotic surveying and maintenance tasks. Part of this challenge is to train robot systems to understand their environment without human intervention. This paper presents a method to automatically classify features within a closed void using deep learning. Specifically, the paper considers a robot placed under floorboards for the purpose of autonomously surveying the underfloor void. The robot uses images captured using an RGB camera to identify regions such as floorboards, joists, air vents and pipework. The paper first presents a standard mask regions convolutional neural network approach, which gives modest performance. The method is then enhanced using a two-stage transfer learning approach with an existing dataset for interior scenes. The conclusion from this work is that, even with limited training data, it is possible to automatically detect many common features of such areas.
Citation
Atkinson, G. A., Zhang, W., Hansen, M. F., Holloway, M. L., & Napier, A. A. (2020). Image segmentation of underfloor scenes using a mask regions convolutional neural network with two-stage transfer learning. Automation in Construction, 113, Article 103118. https://doi.org/10.1016/j.autcon.2020.103118
Journal Article Type | Article |
---|---|
Acceptance Date | Feb 1, 2020 |
Online Publication Date | Feb 13, 2020 |
Publication Date | May 1, 2020 |
Deposit Date | May 6, 2020 |
Publicly Available Date | Mar 29, 2024 |
Journal | Automation in Construction |
Print ISSN | 0926-5805 |
Publisher | Elsevier |
Peer Reviewed | Peer Reviewed |
Volume | 113 |
Article Number | 103118 |
DOI | https://doi.org/10.1016/j.autcon.2020.103118 |
Keywords | Control and Systems Engineering; Civil and Structural Engineering; Building and Construction; Computer vision; Underfloor maintenance; Convolutional neural network |
Public URL | https://uwe-repository.worktribe.com/output/5963692 |
Additional Information | This article is maintained by: Elsevier; Article Title: Image segmentation of underfloor scenes using a mask regions convolutional neural network with two-stage transfer learning; Journal Title: Automation in Construction; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.autcon.2020.103118; Content Type: article; Copyright: © 2020 Elsevier B.V. All rights reserved. |
Files
R2
(9 Mb)
PDF
Licence
http://creativecommons.org/licenses/by-nc-nd/4.0/
Publisher Licence URL
http://creativecommons.org/licenses/by-nc-nd/4.0/
Copyright Statement
This is the author’s accepted manuscript. The published version can be found on the publishers website here: https://doi.org/10.1016/j.autcon.2020.103118
You might also like
3D face recognition using photometric stereo and deep learning
(2020)
Conference Proceeding
Eye centre localisation with convolutional neural network based regression
(2020)
Conference Proceeding
Weed classification in grasslands using convolutional neural networks
(2019)
Conference Proceeding
Downloadable Citations
About UWE Bristol Research Repository
Administrator e-mail: repository@uwe.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search