A vision-based deep learning approach for non-contact vibration measurement using (2+1)D CNN and optical flow

This paper introduces a proof-of-concept vision-based deep learning approach for vibration measurement, proposing a factorized (2+1)D Convolutional Neural Network (CNN) model to predict four vibration metrics: acceleration, velocity, displacement, and frequency, with a focus on rigid body motion. Un...

Full description

Bibliographic Details

Main Authors:	Harold Harrison, Mazlina Mamat, Farah Wong, Hoe Tung Yew, Racheal Lim, Wan Mimi Diyana Wan Zaki
Format:	Article
Language:	en
Published:	Vibromechanika 2025
Subjects:	TA401-492 Materials of engineering and construction. Mechanics of materials
Online Access:	https://eprints.ums.edu.my/id/eprint/45594/1/FULLTEXT.pdf https://eprints.ums.edu.my/id/eprint/45594/ https://doi.org/10.21595/jve.2025.25002
Tags:	Add Tag No Tags, Be the first to tag this record!