Pixel-wise structural motion tracking from rectified repurposed videos

After any disaster, there is an immediate need to assess the integrity of local structures. When available, the displacement time history of a structure during the event can provide an invaluable source of triage assessment information. Although conventional sensors such as accelerometers readily provide this information, many structures are not instrumented and in these cases an alternative is needed. This paper presents such an alternative: a flexible, low-cost, and target-free approach to extracting motion time histories from video recordings of structures during an event. The approach is designed for scenarios where video recordings have inadvertently captured a dynamic event, with the goal of repurposing them for structural triage assessment through a combination of computer vision and signal processing techniques. A combination of parametric video stabilization, 3D denoising, and outlier robust camera motion estimation are employed to mitigate of the effects of camera motion and video encoding artifacts. The approach leverages the computer vision concept of optical flow to provide motion estimates, and 4 canonical optical flow algorithms are assessed as part of this study. The developed approach was validated on the records of the Network for Earthquake Simulation database. The overall findings indicate that the developed method is effective at reconstructing dynamic structural time histories, though the choice of optical flow algorithm plays a significant role in the overall performance. In particular, any employed optical flow algorithm must not overpenalize the high motion gradients that occur at the boundary of in-motion buildings and the image background.