KCF-Based Identification Approach for Vibration Displacement of Double-Column Bents under Various Earthquakes

Vibration displacements are one of the most significant indicators in health monitoring and condition assessment bridges life cycle. The traditional means, such as contact sensors, have relatively high-cost limited points for displacement measurement bridges. This paper proposes a low-cost non-contact monocular vision system based on KCF algorithm to accurately timely identify vibration A conversion method associated with scale ratio was established cope loss depth information images when camera is used monitor multiple targets different depths field. series shaking table tests two-column pier energy dissipation beams were conducted verify feasibility, accuracy, effectiveness, robustness KCF-based identification approach. results showed that column identified by almost consistent obtained laser sensors. peak discrepancies between both methods within 6% all cases amplitudes earthquake waves. RMSE histories very low. corresponding frequency spectra contents match well counterparts recorded from