Structural motion measurement is crucial for structural shake table tests and structural health monitoring. Traditional contact type sensors are usually required to be attached to the test specimens, which may be difficult to install, and may affect the structural properties and response. Non-contact type wireless sensors are usually expensive and require specialized workers to install and operate. In recent years, vision-based methods for structural motion tracking have gained increasing interest due to their high accuracy, non-contact feature, and low cost. However, traditional vision-based tracking algorithms are susceptible to external environmental changes such as illumination variation and background noise. This research project is intended to develop and apply more accurate and reliable computer vision algorithms to provide vibration measurements for civil structures. The algorithms will be investigated through shake table tests in the UBC structural laboratory.
Shake table test of the steel frame
Team composition: Xiao Pan, Yifei Xiao, and T.Y. Yang
Pan, X., Xiao, Y., Yao, H., Yang, T. Y., & Adeli, H. (2022). Vision-based real-time structural vibration measurement through interactive deep-learning-based detection and tracking methods. [Under review].
Xiao, Y., Pan, X., Yang, T. Y. (2022). Nonlinear backstepping hierarchical control of shake table using high-gain observer, Earthquake Engineering & Structural Dynamics. https://doi.org/10.1002/eqe.3726