This paper presents a contactless multi-point displacement measurement system using multiple synchronized wireless cameras. Our system makes use of computer vision techniques to perform displacement calculations, which can be used to provide a valuable insight into the structural condition and service behaviour of bridges under live loading. The system outlined in this paper provides a low cost durable solution which is rapidly deployable in the field. The architecture of this system can be expanded to include up to ten wireless vision sensors, addressing the limitation of current existing solutions limited in scope by their inability to reliably track multiple points on medium and long span bridge structures. Our multi-sensor approach facilitates multi-point displacement and additional vision sensors for vehicle identification and tracking that could be used to accurately relate the bridge displacement response to the load type in the time domain. The performance of the system was validated in a series of controlled laboratory tests. This research will significantly advance current vision-based Structural health monitoring (SHM) systems which can be cost prohibitive and provides a rapid method of obtaining data which accurately relates to measured bridge deflections.
Development of a Time-Synchronised Multi-Input Computer Vision System for Structural Monitoring Utilising Deep Learning for Vehicle IdentificationAuthor: Lydon, D., Jul 2020
Student thesis: Doctoral Thesis › Doctor of PhilosophyFile