Rapid post-diaster structural damage inspection and repair cost evaluation are crucial for building owners and policymakers to make informed risk management decisions. To improve the efficiency of such inspection, an automated end-to-end structural damage detection and repair cost estimation framework has been proposed, which consists of advanced computer vision techniques for classification and localization built on convolution neural networks.
Damage and loss assessment framework
The proposed method first identifies system-level collapse, followed by recognition of component-level damages. In the system-level assessment, ResNet has been adopted. In the component-level damage assessment, an advanced object detection neural network, named YOLO-v2, is implemented which achieves 98.2% and 84.5% average precision in training and testing, respectively. The proposed YOLO-v2 is used in combination with the classification neural network, which improves the identification accuracy for the critical damage state of reinforced concrete structures by 7.5%. The improved classification procedures allow engineers to rapidly and more accurately quantify the damage states of the structures and also localize the critical damage features.
 |
 |
System-level and component level assessment
The identified damage state can then be integrated with the state-of-the-art performance evaluation framework to quantify the financial losses of critical reinforced concrete buildings. The results can be used by the building owners and decision-makers to make informed risk management decisions immediately after the strong earthquake shaking. Hence, resources can be allocated rapidly to improve the resiliency of the community.
Cumulative loss curve
Team composition: Xiao Pan and T.Y. Yang
If you feel our work is inspiring or helpful to your research, please consider citing the following:
Reference: Pan, X., & Yang, T. Y. (2020). Postdisaster image‐based damage detection and repair cost estimation of reinforced concrete buildings using dual convolutional neural networks. Computer‐Aided Civil and Infrastructure Engineering, 35(5), 495-510.