Seismic-induced permanent displacement estimation combining acceleration and computer vision measurements

In this study, a seismic-induced permanent displacement estimation technique that combines acceleration and computer vision measurements was proposed. The proposed technique involves installing a vision camera and an accelerometer on a target building, with the vision camera capturing the change in the position of surrounding objects after a seismic event to estimate the permanent displacement of the target building. During the installation, the vision camera and accelerometer were vibrated in a controlled manner using a shaker on the target building. Then, in the absence of any artificial target or prior knowledge of the size of natural targets, an automatic scale factor map was generated, which converts a translation of an image (in pixels) into a physical displacement. After an earthquake, a displacement map was constructed to estimate the relative movement of the target building to the natural targets and then clustered using Gaussian mixture modeling. Finally, the undeformed portions of the natural targets were retrieved to estimate the permanent displacement of the target building with respect to the distribution of the natural target movement. Both indoor and outdoor experiments were conducted to validate the performance of the proposed technique. The results demonstrate the improved performance of the proposed technique compared with the previous technique.

Automated summary

This study proposes a seismic-induced permanent displacement estimation technique that combines acceleration and computer vision measurements. The technique involves installing a vision camera and accelerometer on a target building to estimate the permanent displacement by capturing the change in position of surrounding objects after a seismic event. The performance of the proposed technique is validated through indoor and outdoor experiments, showing improved results compared to previous techniques.