Abstract
The displacement responses of a civil engineering structure can provide important information regarding structural behaviors that help in assessing safety and serviceability. A displacement measurement using conventional devices, such as the linear variable differential transformer (LVDT), is challenging owing to issues related to inconvenient sensor installation that often requires additional temporary structures. A promising alternative is offered by computer vision, which typically provides a low-cost and non-contact displacement measurement that converts the movement of an object, mostly an attached marker, in the captured images into structural displacement. However, there is limited research on addressing light-induced measurement error caused by the inevitable sunlight in field-testing conditions. This study presents a computer vision-based displacement measurement approach tailored to a field-testing environment with enhanced robustness to strong sunlight. An image-processing algorithm with an adaptive region-of-interest (ROI) is proposed to reliably determine a marker’s location even when the marker is indistinct due to unfavorable light. The performance of the proposed system is experimentally validated in both laboratory-scale and field experiments.
Highlights
Structural health monitoring (SHM) is an essential tool for the effective maintenance of civil infrastructure, with a number of SHM systems employed in real-world applications [1,2,3,4,5].Data acquisition of structural responses is a fundamental step in SHM systems where the data is subsequently processed for condition assessment and decision-making
To maximize the applicability of the vision-based based system to full-scale civil engineering structures, the proposed approach focused on addressing system to full-scale civil engineering structures, the proposed approach focused on addressing image image degradation due to excessive exposure
Three field experiments were subsequently conducted at the Samseung Bridge to validate the performance of the adaptive ROI method
Summary
Structural health monitoring (SHM) is an essential tool for the effective maintenance of civil infrastructure, with a number of SHM systems employed in real-world applications [1,2,3,4,5]. Displacement information is commonly employed for infrastructure maintenance purposes Displacement sensors, such as linear variable differential transformers (LVDT) and strain-based displacement transducers, are widely adopted for conducting displacement measurements in practice. (1) the development of indirect displacement estimation algorithms to convert other physical quantities, such as acceleration and strain, to displacement; and (2) an applicability investigation of relatively new sensors, including the laser Doppler vibrometer (LDV), global positioning systems (GPS), and computer vision-based approaches. The existing vision-based methods differ by (1) non-target approaches, (2) feature detection, and (3) coordinate transforms. Several practical issues in computer vision-based displacement sensing have been identified in the literature, including the use of target markers, the selection of camera locations, and light-induced error. This study presents a computer vision-based approach for displacement measurement tailored to field testing for civil engineering structures. Steel box girder bridge are presented to validate the performance of the proposed approach
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
