A Robust Vision-Based Method for Displacement Measurement under Adverse Environmental Factors Using Spatio-Temporal Context Learning and Taylor Approximation

Abstract

Currently, the majority of studies on vision-based measurement have been conducted under ideal environments so that an adequate measurement performance and accuracy is ensured. However, vision-based systems may face some adverse influencing factors such as illumination change and fog interference, which can affect measurement accuracy. This paper developed a robust vision-based displacement measurement method which can handle the two common and important adverse factors given above and achieve sensitivity at the subpixel level. The proposed method leverages the advantage of high-resolution imaging incorporating spatial and temporal contextual aspects. To validate the feasibility, stability, and robustness of the proposed method, a series of experiments was conducted on a two-span three-lane bridge in the laboratory. The illumination changes and fog interference were simulated experimentally in the laboratory. The results of the proposed method were compared to conventional displacement sensor data and current vision-based method results. It was demonstrated that the proposed method gave better measurement results than the current ones under illumination change and fog interference.

Bridge Damage Detection Approach Using a Roving Camera Technique

“…A laboratory model of a two-span bridge was developed in the Experimental Design and Monitoring (EDM) laboratory of Civil Infrastructure Technologies for Resilience and Safety (CITRS) at the University of Central Florida (UCF), as shown in Figure 3 . The laboratory bridge model was designed with multiple purposes of investigating structural behaviour under various types of external loads, such as the live loads induced by vehicles crossing the structure, and impact loads induced by the impact hammer [ 44 , 71 ]. The bridge has two 300 cm main continuous spans supported by three steel frame sections, as shown in Figure 3 .…”

Deep learning based virtual point tracking for real-time target-less dynamic displacement measurement in railway applications

“…However, optical flow approaches are sensitive to the variation of illumination and backgrounds. Dong et al [22] applied spatio-temporal context learning for RoI tracking and Taylor approximation for subpixel motion estimation. The robustness of this approach has been validated for small motion tracking in laboratory experiments by varying the illumination and humidity.…”

A multiple camera position approach for accurate displacement measurement using computer vision

“…There are three broad steps in processing videos for structural displacement [8]-camera calibration, target tracking and displacement calculation. Many studies have developed image processing algorithms for measuring the motion of a single target on the structure and capturing structure's static or dynamic response [9][10][11][12][13][14][15]. Accurate multi-point displacement measurements of different parts of large structures have been obtained using time-synchronized camera systems [16,17].…”