Collapsed Building Detection Using Residual Siamese Neural Network On LiDAR Data

Evaluation of buildings is crucial to aid emergency response but it costs a lot of resources to do it manually. Many approaches have been proposed to automate the process using artificial intelligence. Most of them, use handcrafted feature, difference calculation between pre-disaster and post-disaster feature, and a classifier model separately. In this study, the process from feature extraction, feature difference and classification are represented by a single model which is siamese neural network. Furthermore, we modify siamese neural network by implementing residual connection for feature concatenation purposes. We evaluate our model on Kumamoto Prefecture earthquake LiDAR data. The result shows the modified model is able to outperform the baseline model with Accuracy and F-measure of 90.91% and 79.28% respectively.