Depth Data Denoising in Optical Laser Based Sensors for Metal Sheet Flatness Measurement: A Deep Learning Approach

Surface flatness assessment is necessary for quality control of metal sheets manufactured from steel coils by roll leveling and cutting. Mechanical-contact-based flatness sensors are being replaced by modern laser-based optical sensors that deliver accurate and dense reconstruction of metal sheet su...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Marcos Alonso, Daniel Maestro, Alberto Izaguirre, Imanol Andonegui, Manuel Graña
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	laser triangulation metal sheet flatness measurement smooth surface reconstruction depth data denoising Convolutional Neural Networks deep learning Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/671d0161841d42caa5a0e0910713ca97
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:671d0161841d42caa5a0e0910713ca97
record_format	dspace
spelling	oai:doaj.org-article:671d0161841d42caa5a0e0910713ca972021-11-11T19:03:33ZDepth Data Denoising in Optical Laser Based Sensors for Metal Sheet Flatness Measurement: A Deep Learning Approach10.3390/s212170241424-8220https://doaj.org/article/671d0161841d42caa5a0e0910713ca972021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7024https://doaj.org/toc/1424-8220Surface flatness assessment is necessary for quality control of metal sheets manufactured from steel coils by roll leveling and cutting. Mechanical-contact-based flatness sensors are being replaced by modern laser-based optical sensors that deliver accurate and dense reconstruction of metal sheet surfaces for flatness index computation. However, the surface range images captured by these optical sensors are corrupted by very specific kinds of noise due to vibrations caused by mechanical processes like degreasing, cleaning, polishing, shearing, and transporting roll systems. Therefore, high-quality flatness optical measurement systems strongly depend on the quality of image denoising methods applied to extract the true surface height image. This paper presents a deep learning architecture for removing these specific kinds of noise from the range images obtained by a laser based range sensor installed in a rolling and shearing line, in order to allow accurate flatness measurements from the clean range images. The proposed convolutional blind residual denoising network (CBRDNet) is composed of a noise estimation module and a noise removal module implemented by specific adaptation of semantic convolutional neural networks. The CBRDNet is validated on both synthetic and real noisy range image data that exhibit the most critical kinds of noise that arise throughout the metal sheet production process. Real data were obtained from a single laser line triangulation flatness sensor installed in a roll leveling and cut to length line. Computational experiments over both synthetic and real datasets clearly demonstrate that CBRDNet achieves superior performance in comparison to traditional 1D and 2D filtering methods, and state-of-the-art CNN-based denoising techniques. The experimental validation results show a reduction in error than can be up to 15% relative to solutions based on traditional 1D and 2D filtering methods and between 10% and 3% relative to the other deep learning denoising architectures recently reported in the literature.Marcos AlonsoDaniel MaestroAlberto IzaguirreImanol AndoneguiManuel GrañaMDPI AGarticlelaser triangulationmetal sheet flatness measurementsmooth surface reconstructiondepth data denoisingConvolutional Neural Networksdeep learningChemical technologyTP1-1185ENSensors, Vol 21, Iss 7024, p 7024 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	laser triangulation metal sheet flatness measurement smooth surface reconstruction depth data denoising Convolutional Neural Networks deep learning Chemical technology TP1-1185
spellingShingle	laser triangulation metal sheet flatness measurement smooth surface reconstruction depth data denoising Convolutional Neural Networks deep learning Chemical technology TP1-1185 Marcos Alonso Daniel Maestro Alberto Izaguirre Imanol Andonegui Manuel Graña Depth Data Denoising in Optical Laser Based Sensors for Metal Sheet Flatness Measurement: A Deep Learning Approach
description	Surface flatness assessment is necessary for quality control of metal sheets manufactured from steel coils by roll leveling and cutting. Mechanical-contact-based flatness sensors are being replaced by modern laser-based optical sensors that deliver accurate and dense reconstruction of metal sheet surfaces for flatness index computation. However, the surface range images captured by these optical sensors are corrupted by very specific kinds of noise due to vibrations caused by mechanical processes like degreasing, cleaning, polishing, shearing, and transporting roll systems. Therefore, high-quality flatness optical measurement systems strongly depend on the quality of image denoising methods applied to extract the true surface height image. This paper presents a deep learning architecture for removing these specific kinds of noise from the range images obtained by a laser based range sensor installed in a rolling and shearing line, in order to allow accurate flatness measurements from the clean range images. The proposed convolutional blind residual denoising network (CBRDNet) is composed of a noise estimation module and a noise removal module implemented by specific adaptation of semantic convolutional neural networks. The CBRDNet is validated on both synthetic and real noisy range image data that exhibit the most critical kinds of noise that arise throughout the metal sheet production process. Real data were obtained from a single laser line triangulation flatness sensor installed in a roll leveling and cut to length line. Computational experiments over both synthetic and real datasets clearly demonstrate that CBRDNet achieves superior performance in comparison to traditional 1D and 2D filtering methods, and state-of-the-art CNN-based denoising techniques. The experimental validation results show a reduction in error than can be up to 15% relative to solutions based on traditional 1D and 2D filtering methods and between 10% and 3% relative to the other deep learning denoising architectures recently reported in the literature.
format	article
author	Marcos Alonso Daniel Maestro Alberto Izaguirre Imanol Andonegui Manuel Graña
author_facet	Marcos Alonso Daniel Maestro Alberto Izaguirre Imanol Andonegui Manuel Graña
author_sort	Marcos Alonso
title	Depth Data Denoising in Optical Laser Based Sensors for Metal Sheet Flatness Measurement: A Deep Learning Approach
title_short	Depth Data Denoising in Optical Laser Based Sensors for Metal Sheet Flatness Measurement: A Deep Learning Approach
title_full	Depth Data Denoising in Optical Laser Based Sensors for Metal Sheet Flatness Measurement: A Deep Learning Approach
title_fullStr	Depth Data Denoising in Optical Laser Based Sensors for Metal Sheet Flatness Measurement: A Deep Learning Approach
title_full_unstemmed	Depth Data Denoising in Optical Laser Based Sensors for Metal Sheet Flatness Measurement: A Deep Learning Approach
title_sort	depth data denoising in optical laser based sensors for metal sheet flatness measurement: a deep learning approach
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/671d0161841d42caa5a0e0910713ca97
work_keys_str_mv	AT marcosalonso depthdatadenoisinginopticallaserbasedsensorsformetalsheetflatnessmeasurementadeeplearningapproach AT danielmaestro depthdatadenoisinginopticallaserbasedsensorsformetalsheetflatnessmeasurementadeeplearningapproach AT albertoizaguirre depthdatadenoisinginopticallaserbasedsensorsformetalsheetflatnessmeasurementadeeplearningapproach AT imanolandonegui depthdatadenoisinginopticallaserbasedsensorsformetalsheetflatnessmeasurementadeeplearningapproach AT manuelgrana depthdatadenoisinginopticallaserbasedsensorsformetalsheetflatnessmeasurementadeeplearningapproach
_version_	1718431649578876928

Depth Data Denoising in Optical Laser Based Sensors for Metal Sheet Flatness Measurement: A Deep Learning Approach

Ejemplares similares