Cargando…

Fringe Detection and Displacement Sensing for Variable Optical Feedback-Based Self-Mixing Interferometry by Using Deep Neural Networks

Laser feedback-based self-mixing interferometry (SMI) is a promising technique for displacement sensing. However, commercial deployment of such sensors is being held back due to reduced performance in case of variable optical feedback which invariably happens due to optical speckle encountered when...

Descripción completa

Detalles Bibliográficos
Autores principales: Siddiqui, Asra Abid, Zabit, Usman, Bernal, Olivier D.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9785218/
https://www.ncbi.nlm.nih.gov/pubmed/36560198
http://dx.doi.org/10.3390/s22249831
_version_ 1784857995554848768
author Siddiqui, Asra Abid
Zabit, Usman
Bernal, Olivier D.
author_facet Siddiqui, Asra Abid
Zabit, Usman
Bernal, Olivier D.
author_sort Siddiqui, Asra Abid
collection PubMed
description Laser feedback-based self-mixing interferometry (SMI) is a promising technique for displacement sensing. However, commercial deployment of such sensors is being held back due to reduced performance in case of variable optical feedback which invariably happens due to optical speckle encountered when sensing the motion of non-cooperative remote target surfaces. In this work, deep neural networks have been trained under variable optical feedback conditions so that interferometric fringe detection and corresponding displacement measurement can be achieved. We have also proposed a method for automatic labelling of SMI fringes under variable optical feedback to facilitate the generation of a large training dataset. Specifically, we have trained two deep neural network models, namely Yolov5 and EfficientDet, and analysed the performance of these networks on various experimental SMI signals acquired by using different laser-diode-based sensors operating under different noise and speckle conditions. The performance has been quantified in terms of fringe detection accuracy, signal to noise ratio, depth of modulation, and execution time parameters. The impact of network architecture on real-time sensing is also discussed.
format Online
Article
Text
id pubmed-9785218
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97852182022-12-24 Fringe Detection and Displacement Sensing for Variable Optical Feedback-Based Self-Mixing Interferometry by Using Deep Neural Networks Siddiqui, Asra Abid Zabit, Usman Bernal, Olivier D. Sensors (Basel) Article Laser feedback-based self-mixing interferometry (SMI) is a promising technique for displacement sensing. However, commercial deployment of such sensors is being held back due to reduced performance in case of variable optical feedback which invariably happens due to optical speckle encountered when sensing the motion of non-cooperative remote target surfaces. In this work, deep neural networks have been trained under variable optical feedback conditions so that interferometric fringe detection and corresponding displacement measurement can be achieved. We have also proposed a method for automatic labelling of SMI fringes under variable optical feedback to facilitate the generation of a large training dataset. Specifically, we have trained two deep neural network models, namely Yolov5 and EfficientDet, and analysed the performance of these networks on various experimental SMI signals acquired by using different laser-diode-based sensors operating under different noise and speckle conditions. The performance has been quantified in terms of fringe detection accuracy, signal to noise ratio, depth of modulation, and execution time parameters. The impact of network architecture on real-time sensing is also discussed. MDPI 2022-12-14 /pmc/articles/PMC9785218/ /pubmed/36560198 http://dx.doi.org/10.3390/s22249831 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Siddiqui, Asra Abid
Zabit, Usman
Bernal, Olivier D.
Fringe Detection and Displacement Sensing for Variable Optical Feedback-Based Self-Mixing Interferometry by Using Deep Neural Networks
title Fringe Detection and Displacement Sensing for Variable Optical Feedback-Based Self-Mixing Interferometry by Using Deep Neural Networks
title_full Fringe Detection and Displacement Sensing for Variable Optical Feedback-Based Self-Mixing Interferometry by Using Deep Neural Networks
title_fullStr Fringe Detection and Displacement Sensing for Variable Optical Feedback-Based Self-Mixing Interferometry by Using Deep Neural Networks
title_full_unstemmed Fringe Detection and Displacement Sensing for Variable Optical Feedback-Based Self-Mixing Interferometry by Using Deep Neural Networks
title_short Fringe Detection and Displacement Sensing for Variable Optical Feedback-Based Self-Mixing Interferometry by Using Deep Neural Networks
title_sort fringe detection and displacement sensing for variable optical feedback-based self-mixing interferometry by using deep neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9785218/
https://www.ncbi.nlm.nih.gov/pubmed/36560198
http://dx.doi.org/10.3390/s22249831
work_keys_str_mv AT siddiquiasraabid fringedetectionanddisplacementsensingforvariableopticalfeedbackbasedselfmixinginterferometrybyusingdeepneuralnetworks
AT zabitusman fringedetectionanddisplacementsensingforvariableopticalfeedbackbasedselfmixinginterferometrybyusingdeepneuralnetworks
AT bernalolivierd fringedetectionanddisplacementsensingforvariableopticalfeedbackbasedselfmixinginterferometrybyusingdeepneuralnetworks