Out-of-plane full-field vibration displacement measurement with monocular computer vision

Abstract

Vibration displacement of civil structures is crucial information for structural health monitoring (SHM). The challenges and costs associated with traditional physical sensors make displacement measurement not always straightforward owing to difficulties such as inaccessibility. While recent computer vision based methods for displacement measurements offer simplicity, unfortunately they lag in terms of accuracy and robustness. This paper introduces a monocular camera system designed to measure out-of-plane vibration displacement. Compared to existing monocular-camera based methods, the proposed monocular vision-based measurement technique significantly enhances accuracy and robustness. This boost can be attributed to the generation of a vast and precise dataset and augmented by employing advanced techniques for object segmentation and background elimination. Experimental tests are conducted in the laboratory to investigate the feasibility of the proposed system. The results demonstrate that the proposed monocular 3D displacement system can produce highly accurate full-field out-of-plane displacement measurement.