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

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.