Joe Eastwood
Improving the localisation of features for the calibration of cameras using EfficientNets
Eastwood, Joe; Gayton, George; Leach, Richard K.; Piano, Samanta
Authors
George Gayton
RICHARD LEACH RICHARD.LEACH@NOTTINGHAM.AC.UK
Chair in Metrology
Dr SAMANTA PIANO SAMANTA.PIANO@NOTTINGHAM.AC.UK
Professor of Metrology
Abstract
Camera-based methods for optical coordinate metrology, such as digital fringe projection, rely on accurate calibration of the cameras in the system. Camera calibration is the process of determining the intrinsic and distortion parameters which define the camera model and relies on the localisation of targets (in this case, circular dots) within a set of calibration images. Localising these features with sub-pixel accuracy is key to providing high quality calibration results which in turn allows for high quality measurement results. A popular solution to the localisation of calibration features is provided in the OpenCV library. In this paper, we adopt a hybrid machine learning approach where an initial localisation is given by OpenCV which is then refined through a convolutional neural network based on the EfficientNet architecture. Our proposed localisation method is then compared with the OpenCV locations without refinement, and to an alternative refinement method based on traditional image processing. We show that under ideal imaging conditions, both refinement methods provide a reduction in the mean residual reprojection error of approximately 50%. However, in adverse imaging conditions, with high noise levels and specular reflection, we show that the traditional refinement degrades the results given by pure OpenCV, increasing the mean residual magnitude by 34%, which corresponds to 0.2 pixels. In contrast, the EfficientNet refinement is shown to be robust to the unideal conditions and is still able to reduce the mean residual magnitude by 50% compared to OpenCV. The EfficientNet feature localisation refinement, therefore, enables a greater range of viable imaging positions across the measurement volume. leading to more robust camera parameter estimations.
Citation
Eastwood, J., Gayton, G., Leach, R. K., & Piano, S. (2023). Improving the localisation of features for the calibration of cameras using EfficientNets. Optics Express, 31(5), 7966-7982. https://doi.org/10.1364/OE.478934
Journal Article Type | Article |
---|---|
Acceptance Date | Jan 24, 2023 |
Online Publication Date | Feb 27, 2023 |
Publication Date | Feb 27, 2023 |
Deposit Date | Jan 31, 2023 |
Publicly Available Date | Feb 21, 2023 |
Journal | Optics Express |
Electronic ISSN | 1094-4087 |
Publisher | Optical Society of America |
Peer Reviewed | Peer Reviewed |
Volume | 31 |
Issue | 5 |
Pages | 7966-7982 |
DOI | https://doi.org/10.1364/OE.478934 |
Keywords | Atomic and Molecular Physics, and Optics |
Public URL | https://nottingham-repository.worktribe.com/output/16792646 |
Publisher URL | https://opg.optica.org/oe/fulltext.cfm?uri=oe-31-5-7966&id=526311 |
Files
Improving the localisation of features for the calibration of cameras using EfficientNets
(8.7 Mb)
PDF
Publisher Licence URL
https://creativecommons.org/licenses/by/4.0/
You might also like
Model-based defect detection on structured surfaces having optically unresolved features
(2015)
Journal Article
Surface texture measurement for additive manufacturing
(2015)
Journal Article
Study of weighted fusion methods for the measurement of surface geometry
(2016)
Journal Article
Metrology for additive manufacturing
(2016)
Journal Article
Downloadable Citations
About Repository@Nottingham
Administrator e-mail: discovery-access-systems@nottingham.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