Dilated Convolution and Residual Network based Convolutional Neural Network for Recognition of Disastrous Events

Natural disasters include earthquakes, land sliding, floods, and typhoons causing great damage to manmade structures. To efficiently manage natural disasters, it is important to develop an automatic disaster recognition system based on deep learning algorithms such as Convolutional Neural Network. This research aims to introduce the application of Deep learning algorithms in the recognition of different disasters such as building collapse, and burning buildings caused by earthquakes and fire respectively. In this research, a novel approach using a single deep convolution neural network is implemented based on two main characteristics e.g. dilated convolution in which convolution is applied on an input image using defined gaps to capture more contextual information and fine details, and residual connection in which the input layer is not only connected to adjacent layer but maybe the summation of previous layers to reduce the problem of vanishing gradient. Dilated Residual Network is trained and tested on publicly available datasets of disasters that are NWPU-RESICS45, BOWFire, and Satellite image of Hurricane Damage, and Accident Image Analysis dataset that achieved testing accuracy of 92.06%, 76%, 98.15%, and 93.16% respectively. As there is a lack of a single disastrous event dataset so images of disasters were collected using different web scraping tools. These tools allow downloading images in bulk. After discarding irrelevant images disastrous event dataset consists of four classes having 10,000 images each. DRN was applied to the disastrous event dataset and the result showed model achieved 95.67% testing accuracy. The results proved that the proposed methodology is efficient enough and can be generalized for other disaster classification problems.