Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow

Markus Hofinger, Thomas Pock, Thomas Moosbrugger

Research output: Contribution to conferencePaperResearchpeer-review

Abstract

Wood-composite materials are widely used today as they homogenize humidity related directional deformations. Quantification of these deformations as coefficients is important for construction and engineering and topic of current research but still a manual process.
This work introduces a novel computer vision approach that automatically extracts these properties directly from scans of the wooden specimens, taken at different humidity levels during the long lasting humidity conditioning process. These scans are used to compute a humidity dependent deformation field for each pixel, from which the desired coefficients can easily be calculated.
The overall method includes automated registration of the wooden blocks, numerical optimization to compute a variational optical flow field which is further used to calculate dense strain fields and finally the engineering coefficients and their variance throughout the wooden blocks. The methods regularization is fully parameterizable which allows to model and suppress artifacts due to surface appearance changes of the specimens from mold, cracks, etc. that typically arise in the conditioning process.
LanguageEnglish
Pages97 - 104
Number of pages8
StatusPublished - 5 Feb 2018
EventComputer Vision Winter Workshop: 23rd Computer Vision Winter Workshop - Český Krumlov castle, Český Krumlov, Czech Republic
Duration: 5 Feb 20187 Feb 2018
Conference number: 23
http://cmp.felk.cvut.cz/cvww2018

Conference

ConferenceComputer Vision Winter Workshop
Abbreviated titleCVWW 2018
CountryCzech Republic
CityČeský Krumlov
Period5/02/187/02/18
Internet address

Fingerprint

Optical flows
Optical Flow
Humidity
Composite Materials
Atmospheric humidity
Wood
Composite materials
Conditioning
Coefficient
Engineering
Numerical Optimization
Regularization Method
Computer Vision
Quantification
Computer vision
Registration
Flow Field
Flow fields
Crack
Pixel

ASJC Scopus subject areas

  • Control and Optimization
  • Mechanics of Materials
  • Computer Vision and Pattern Recognition

Cite this

Hofinger, M., Pock, T., & Moosbrugger, T. (2018). Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow. 97 - 104. Paper presented at Computer Vision Winter Workshop, Český Krumlov, Czech Republic.

Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow. / Hofinger, Markus; Pock, Thomas; Moosbrugger, Thomas.

2018. 97 - 104 Paper presented at Computer Vision Winter Workshop, Český Krumlov, Czech Republic.

Research output: Contribution to conferencePaperResearchpeer-review

Hofinger, M, Pock, T & Moosbrugger, T 2018, 'Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow' Paper presented at Computer Vision Winter Workshop, Český Krumlov, Czech Republic, 5/02/18 - 7/02/18, pp. 97 - 104.
Hofinger M, Pock T, Moosbrugger T. Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow. 2018. Paper presented at Computer Vision Winter Workshop, Český Krumlov, Czech Republic.
Hofinger, Markus ; Pock, Thomas ; Moosbrugger, Thomas. / Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow. Paper presented at Computer Vision Winter Workshop, Český Krumlov, Czech Republic.8 p.
@conference{37387ac73c00446ba63dc30abfd8042e,
title = "Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow",
abstract = "Wood-composite materials are widely used today as they homogenize humidity related directional deformations. Quantification of these deformations as coefficients is important for construction and engineering and topic of current research but still a manual process.This work introduces a novel computer vision approach that automatically extracts these properties directly from scans of the wooden specimens, taken at different humidity levels during the long lasting humidity conditioning process. These scans are used to compute a humidity dependent deformation field for each pixel, from which the desired coefficients can easily be calculated.The overall method includes automated registration of the wooden blocks, numerical optimization to compute a variational optical flow field which is further used to calculate dense strain fields and finally the engineering coefficients and their variance throughout the wooden blocks. The methods regularization is fully parameterizable which allows to model and suppress artifacts due to surface appearance changes of the specimens from mold, cracks, etc. that typically arise in the conditioning process.",
author = "Markus Hofinger and Thomas Pock and Thomas Moosbrugger",
year = "2018",
month = "2",
day = "5",
language = "English",
pages = "97 -- 104",
note = "Computer Vision Winter Workshop : 23rd Computer Vision Winter Workshop, CVWW 2018 ; Conference date: 05-02-2018 Through 07-02-2018",
url = "http://cmp.felk.cvut.cz/cvww2018",

}

TY - CONF

T1 - Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow

AU - Hofinger, Markus

AU - Pock, Thomas

AU - Moosbrugger, Thomas

PY - 2018/2/5

Y1 - 2018/2/5

N2 - Wood-composite materials are widely used today as they homogenize humidity related directional deformations. Quantification of these deformations as coefficients is important for construction and engineering and topic of current research but still a manual process.This work introduces a novel computer vision approach that automatically extracts these properties directly from scans of the wooden specimens, taken at different humidity levels during the long lasting humidity conditioning process. These scans are used to compute a humidity dependent deformation field for each pixel, from which the desired coefficients can easily be calculated.The overall method includes automated registration of the wooden blocks, numerical optimization to compute a variational optical flow field which is further used to calculate dense strain fields and finally the engineering coefficients and their variance throughout the wooden blocks. The methods regularization is fully parameterizable which allows to model and suppress artifacts due to surface appearance changes of the specimens from mold, cracks, etc. that typically arise in the conditioning process.

AB - Wood-composite materials are widely used today as they homogenize humidity related directional deformations. Quantification of these deformations as coefficients is important for construction and engineering and topic of current research but still a manual process.This work introduces a novel computer vision approach that automatically extracts these properties directly from scans of the wooden specimens, taken at different humidity levels during the long lasting humidity conditioning process. These scans are used to compute a humidity dependent deformation field for each pixel, from which the desired coefficients can easily be calculated.The overall method includes automated registration of the wooden blocks, numerical optimization to compute a variational optical flow field which is further used to calculate dense strain fields and finally the engineering coefficients and their variance throughout the wooden blocks. The methods regularization is fully parameterizable which allows to model and suppress artifacts due to surface appearance changes of the specimens from mold, cracks, etc. that typically arise in the conditioning process.

M3 - Paper

SP - 97

EP - 104

ER -