Vision-based Vibration Monitoring Using Existing Cameras Installed Within a Building: Data Reuse Study from the BNCS Project

Surveillance cameras are ubiquitous within modern buildings and can be leveraged to extract meaningful data useful for system identification and structural health monitoring. The goal of this study was to demonstrate that the fundamental period of a structure could be accurately estimated by tracking natural features within surveillance camera footage. This project reuses videos (data) captured with internal cameras during previous full-scale shake table test conducted on the Large High Performance Outdoor Shake Table (LHPOST) at the University of California San Diego (UCSD) as part of the building nonstructural components and systems (BNCS) project (Hutchinson et al., 2012). The experimental data published here can be used by others to evaluate computer vision algorithms, system identification algorithms, and structural health monitoring approaches.