Automation technology of seismic damage investigation for timber houses using deep learning

In this paper, to achieve the fast and detailed evaluation of seismic damage, the novel diagnostic imaging applied multiple image recognition techniques (Classification, Detection, Segmentation) in deep learning is proposed. Dataset from images generated by Generative Adversarial Network (GAN) brings the high-accurate recognition of the real damaged images. It is revealed that the diagnostic imaging can extract precisely the damaged area with minimum noise. Furthermore, the result of the damage extraction can calculate the seismic damage rate of the exterior wall.