0100498271

open access

Version of Record

Vision Freqformer for Vibration Monitoring using existing surveillance cameras

English (英語)

Signal, Image and Video Processing

19(16)

1375

Springer

2025-11-17

2025-11-27

Social infrastructure, such as road bridges and tunnels, is used in the long term; therefore, their structural integrity must be maintained during this period. Currently, the soundness of social infrastructure is confirmed through visual and sound inspections. However, these inspections are sensitive and difficult to perform and inexperienced inspectors may overlook them. Although camera-based inspection can examine wide areas simultaneously, they only examine the surface structures and not bridge components. Finite element method has been used to investigate the structural components by applying known vibrations and observing the frequency responses. Road bridges vibrate owing to traffic. The internal structure of road bridges can be investigated by measuring these vibrations. In this study, we propose a novel machine learning method that does not use a Fourier transform. Our method directly estimates vibration information from structural images by improving a transformer. We call this Vision Freqformer. Our method uses surveillance cameras to monitor road bridges. We assess the vibration estimation accuracy and robustness of the bit rate. Consequently, our method achieved an estimation accuracy exceeding 71.6 % in tests using vibration data from the damper equations and Z24 dataset simulations.

Surveillance camera

学術雑誌論文

This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.