Computer Vision-Based Structural Displacement Measurement Robust to Light-Induced Image Degradation for In-Service Bridges

Sensors

Soojin Cho¹  Kyoung-Chan Lee²  Sung-Han Sim³  Junhwa Lee³ 

[1] Department of Civil and Environmental Engineering, University of Seoul, Seoul 02504, Korea;Korea Railroad Research Institute, Uiwang 16105, Korea;School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan 44919, Korea;

关键词: adaptive ROI;    computer vision;    displacement;   

DOI  :  10.3390/s17102317

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown