Loading…

The Simulation-Based Approach for Random Speckle Pattern Representation in Synthetically Generated Video Sequences of Dynamic Phenomena

Structural health monitoring systems that employ vision data are under constant development. Generating synthetic vision data is an actual issue. It allows, for example, for obtention of additional data for machine learning techniques or predicting the result of observations using a vision system wi...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2022-12, Vol.22 (23), p.9489
Main Authors: Zdziebko, Paweł, Dworakowski, Ziemowit, Holak, Krzysztof
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Structural health monitoring systems that employ vision data are under constant development. Generating synthetic vision data is an actual issue. It allows, for example, for obtention of additional data for machine learning techniques or predicting the result of observations using a vision system with a reduced number of experiments. A random speckle pattern (RSP) fixed on the surface of the observed structure is usually used in measurements. The determination of displacements of its areas using digital image correlation (DIC) methods allows for extracting the structure's deformation in both static and dynamic cases. An RSP modeling methodology for synthetic image generation is developed within this paper. The proposed approach combines the finite element modeling technique and simulation results with the Blender graphics environment to generate video sequences of the mechanical structure with deformable RSP attached to it. The comparative analysis showed high compliance of the displacement between the synthetic images processed with the DIC method and numerical data.
ISSN:1424-8220
1424-8220
DOI:10.3390/s22239489