Vision-Based Motion Tracking for Risk Assessment During Seismic Events

Previous experiences during earthquake events emphasize the need for new technologies for real-time monitoring and assessment of facilities with high value nonstructural elements such as equipment or other contents. Moreover, there is substantial limitation in our ability to rapidly evaluate and identify potential hazard zones within a structure, exposing rescue workers, society and the environment to unnecessary risks. A real-time monitoring system, integrated with critical warning systems, would allow for improved channeling of resources. The optimal system would allow for non-intrusive, high-speed data, which is rapidly collected via a fast network and analyzed in a central repository for building owners and rescue workers to make informed decisions.

In recognition of these issues, the primary objective of this project is to summarize investigative work on the development, testing, and evaluation of vision-based motion tracking systems for use in monitoring and assessing seismic risk. Two fundamentally different types of vision-based systems are considered: (i) digital red light-based cameras and (ii) digital fully image-based cameras. Shake table experiments are used to test and evaluate the software and hardware infrastructure needed for such a system.

This report is subdivided into chapters detailing the results from investigation of (i) background and literature related to motion tracking using camera hardware and image processing algorithms, (ii) implementation and results of light-based systems and (iii) implementation and results of image-based systems.