This study proposes a Network to recognize displacement of a RC frame structure from a video by a monocular camera. The proposed Network consists of two modules which is FlowNet2 and POFRN-Net. FlowNet2 is used to generate dense optical flow as well as POFRN-Net is to extract pose parameter H. FlowNet2 convert two video frames into dense optical flow. POFRN-Net is inputted dense optical flow from FlowNet2 to output the pose parameter H. The displacement of any points of structure can be calculated from parameter H. The Fast Fourier Transform (FFT) is applied to obtain frequency domain signal from corresponding displacement signal. Furthermore, the comparison of the truth displacement on the First floor of the First video is shown in this study. Finally, the predicted displacements on four floors of RC frame structure of given three videos are exhibited in the last of this study.

翻译：本研究提出一种网络，用于通过单目摄像头视频识别RC框架结构的位移。所提出的网络由FlowNet2和POFRN-Net两个模块组成。FlowNet2用于生成密集光流，而POFRN-Net用于提取位姿参数H。FlowNet2将两帧视频图像转换为密集光流，POFRN-Net以FlowNet2输出的密集光流为输入，输出位姿参数H，结构中任意点的位移均可通过参数H计算得出。采用快速傅里叶变换（FFT）从对应位移信号中获取频域信号。此外，本研究展示了第一个视频第一层真实位移的对比结果。最后，本研究展示了给定三个视频中RC框架结构四层位移的预测结果。