Test installation of a Marker-based Framework for Structural Health Monitoring of Bridges Milán Magdics 1,2,a , Rubén Jesús Garcia 1,b , Voravika Wattanasoontorn 1,c and Mateu Sbert 1,d 1 Institute of Informatics and Applications, University of Girona, Girona, Spain 2 Department of Control Engineering and Information Technology, Budapest University of Technology and Economics, Budapest, Hungary a magdics@imae.udg.edu, b rgarcia@imae.udg.edu, c voravika@gmail.com, d mateu@imae.udg.edu Abstract. Regular health monitoring of bridges is a vital process to prevent serious structural damage. Marker-based systems, which follow the trajectory of objects by placing a well-characterized pattern on their surface and identify them on photos or videos taken of these objects, have proven to be a cheap and flexible alternative for such tasks. In this work, we extend our previous laboratory implementation with a low-cost, fully automatic on-site installation at the bridge at Arosa Island, Galicia, Spain. Preliminary results presented in this paper show that our system is highly robust for the harsh climate of the installation site. Introduction High forces due to wind, traffic, fluctuation of temperature or other sources cause bridges to deteriorate, which must be monitored in order to prevent serious damage or even catastrophes. Automatic structural health monitoring systems determine the level of safety based on data provided by different types of sensors installed on the bridges and aim to replace traditional on-site inspection by human experts. It has been shown that computer vision based systems offer a flexible and low-cost solution for a specific type of health monitoring, tracking of the movement of structural elements [1][2]. In a previous work [1], we proposed a marker-based system that uses planar, well-characterized patterns called fiducial markers [3] painted on the surface of the tracked objects. Standard computer vision algorithms [4] can determine the three dimensional position and orientation (with respect to the camera) of planar markers present on a photo and thus, by taking photos regularly from a fixed camera position, we can obtain the trajectory of objects with the desired sampling rate. The system can be made fully automatic using IP cameras that are accessed via internet. Thus, measurement data is collected remotely and markers are located, i.e. object trajectories are obtained off-line, independently of the data acquisition (Fig. 1). In this paper, we present our results and experiences of an on-site installation. Application to elastomeric supports Our system was installed at the bridge connecting the Arosa island with the mainland at the Atlantic Coast of Galicia in Spain. The bridge was constructed using elastomeric supports that connect pillars with the deck. When the deck expands or shrinks due to fluctuation of the temperature, it can slide on the support, preventing the structure to be damaged by the changes in its volume (Fig. 2). The high forces arisen during sliding cause damage in the elastomeric support making it less and less capable of sliding, i.e. losing its functionality. The health of the elastomeric support can be characterized by the total distance it has moved so far, if this reaches a certain threshold, the support has to be replaced. Thus, by tracking the trajectory we can minimize the frequency of costly reparations while maintaining safety of the structure. Applied Mechanics and Materials Vols. 477-478 (2014) pp 813-816 Online available since 2013/Dec/19 at www.scientific.net © (2014) Trans Tech Publications, Switzerland doi:10.4028/www.scientific.net/AMM.477-478.813 All rights reserved. No part of contents of this paper may be reproduced or transmitted in any form or by any means without the written permission of TTP, www.ttp.net. (ID: 84.88.162.180-18/02/14,14:41:02)