Computer vision-based post-earthquake inspections for building safety assessment

Assessing the safety of earthquake-affected buildings is a critical structural health monitoring task that facilitates the timely response to present dangers and reduces potential threats to life and property. However, post-earthquake time constraints and harsh environmental conditions mean that images and videos taken on -site are frequently affected by poor resolution and blurriness, which may negatively affect the accuracy and usefulness of artificial intelligence image recognition tools. In this study, a HybridGAN model was developed that incorporates ESRGAN for resolution improvement and DeblurGANv2 for blurriness improvement. Additionally, a transfer learning U-Net (TF-Unet) was integrated to detect building components (i.e., columns and structural walls), classify building damage types, and identify building damage levels. Based on recognition results from three case studies and the relevant Taiwan codes, an automated system for building safety evaluation was proposed. The model was trained to directly classify and recognize the level of building component damage. The mean Intersection over Union (mIoU) results for the column and structural wall using the testing dataset were 81.326 % and 57.009 %, respectively. The pre-trained model was used to predict three case studies to test the capability of TF-Unet to handle real-word datasets.