PSI - Issue 84

Available online at www.sciencedirect.com

ScienceDirect

Procedia Structural Integrity 84 (2026) 81–88

© 2026 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Conference Keywords: bridge monitoring; computer-vision; digital image correlation; fiducial targets; structural health monitoring; target matching; vision based monitoring; synthetic videos; laboratory tests. Abstract Computer vision techniques offer new opportunities for non-contact measurement of structural displacement, particularly in bridge monitoring, where the installation of traditional sensors is often complex. This work analyses the use of template matching algorithms based on correlation, combined with specific subpixel estimation strategies, for automatic and accurate tracking of multiple targets using a single camera. Template identification exploits AprilTag visual markers, which allow for robust and repeatable definition of the regions of interest. The performance of the algorithms was evaluated through a detailed experimental process, including tests on synthetic videos, laboratory tests under controlled conditions with known displacements, and a field application on a post-tensioned concrete bridge in service. The results show good accuracy in the reconstruction of vertical displacements and strong consistency with the reference measurements. Under ideal conditions, a systematic error related to the real subpixel position emerges, while in analyses conducted on a real footage, this effect is attenuated or absent. Overall, the study confirms the reliability and potentialities of vision-based techniques for dynamic structural monitoring applications, offering a flexible, scalable, and low-cost solution. III Fabre Conference: Existing Bridges, Viaducts, and Tunnels: Research, Innovation, and Applications Some results on the evaluation of the accuracy of displacement measurements in bridge decks through computer-vision template-matching algorithms Francesco Allegrezza a , Fabio Micozzi a , Michele Morici b , Alessandro Zona b *, Andrea Dall’Asta a a Università degli Studi di Camerino, Scuola di Scienze e Tecnologie, Via Gentile III Da Varano 7, 62032 Camerino (MC), Italy b Università degli Studi di Camerino, Scuola di Architettura e Design, Viale della Rimembranza 3, 63100 Ascoli Piceno (AP), Italy

* Corresponding author. Tel.: +39 0737 40 4287. E-mail address: alessandro.zona@unicam.it

2452-3216 © 2026 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Conference 10.1016/j.prostr.2026.06.011