When an earthquake strikes an area, unless the local infrastructure has a structural health monitoring system, it is difficult to obtain its health condition due to a lack of data. A smartphone could be competently used for many monitoring tasks to gather large amounts of data at a low cost. In this study, a smartphone is used as a sensor to obtain the interstory drift of buildings by recording a video of the ceiling with the front camera using a feature point matching algorithm. In addition, static and dynamic tests were carried out. In the static tests, the precision and error were investigated and compared with the reference sensor. In the dynamic tests, the displacement under a seismic wave was acquired by a smartphone and compared with the reference sensor, and the illumination condition was varied to test the robustness of the algorithm. The results indicated that feature point matching was suitable for calculating the displacement, and the smartphone was competent in monitoring the interstory drift during an earthquake.

中文翻译：

---

使用特征点匹配算法通过智能手机测量建筑物的层间漂移

当地震袭击某个地区时，除非当地基础设施具有结构性的健康监测系统，否则由于缺乏数据而很难获得其健康状况。智能手机可以胜任许多监视任务，以低成本收集大量数据。在这项研究中，智能手机被用作传感器，通过使用特征点匹配算法通过前置摄像头录制天花板的视频来获取建筑物的层间漂移。此外，还进行了静态和动态测试。在静态测试中，研究了精度和误差，并将其与参考传感器进行了比较。在动态测试中，通过智能手机获取地震波下的位移并将其与参考传感器进行比较，并改变照明条件以测试算法的鲁棒性。