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

Markus Hofinger, Thomas Pock, Thomas Moosbrugger

Research output: Contribution to conferencePaper

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.
Original languageEnglish
Pages97 - 104
Number of pages8
Publication statusPublished - 5 Feb 2018
Event23rd Computer Vision Winter Workshop: CVWW 2018 - Český Krumlov castle, Český Krumlov, Czech Republic
Duration: 5 Feb 20187 Feb 2018
Conference number: 23
http://cmp.felk.cvut.cz/cvww2018

Conference

Conference23rd Computer Vision Winter Workshop
Abbreviated titleCVWW 2018
CountryCzech Republic
CityČeský Krumlov
Period5/02/187/02/18
Internet address

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow'. Together they form a unique fingerprint.

Cite this