Objectives  The building collapse is the main cause of casualties and economic losses in all kinds of disasters. Accurate assessment of the collapse of buildings is an important basis for disaster rescue and government decision-making, and plays an important role in the proper placement of the victims, the protection of the lives and property of the victims. Therefore, the rapid assessment of building collapse after disaster is a research hotspot in the field of remote sensing and civil engineering. The main objectives of this study was to apply the deep learning technology to automatically identify and assess building collapse and structural damage with on-site images.

  Methods   The building collapse assessment method used in this paper is ResNet (residual network). A ResNet-50 architecture was implemented in TensorFlow, which consists of 5 stages each with a convolution and identity block, 3 convolution layers in each convolution block and 3 convolution layers in each identity block. According to the building damage assessment standard developed by the China Earthquake Administration, the evaluation output of this model is adjusted to three types: Completely collapsed, semi-collapsed, and non-collapse. In the data augmentation process, geometry transformation and blur processing were used to simulate different shooting environments, to reduce the overfitting of the classifier model by enhancing the training image. Through data expansion, the number of training data has been increased by at least 10 times on the basis of PEER Hub ImageNet Challenge open dataset. In the process of transfer learning, the gradient descent algorithm was used to adjust and optimize the parameters of the neural network. The results of this method were evaluated by using accuracy and Kappa coefficient.

  Results   Finally, in the building collapse assessment experiment, the classification accuracy of the assessment model reached 77.23% and the Kappa coefficient was 0.65; in the structural damage assessment experiment, the classification accuracy of the assessment model reached 77% and the Kappa coefficient was 0.693.The proposed collapse classification successfully attains a relatively high rate for true-positives.Overall, this method performed well. This method shows great promise in supporting on-site decision-making for the rapid accurate assessment of building collapse after disaster.

  Conclusions   A novel automatic classification method for post-disaster building collapse evaluation is proposed,which meets the buil- ding damage evaluation standard. The method is demonstrated on a specific example classification focused on collapse classification and structural damage type identification.The experiment results show great pro- mise in the rapid accurate assessment of building collapse after disaster. In the future we plan to improve the model to enhance the ability to extract subtle features in the image.