Image Classification Based on Disaster type Using Deep Learning

Abstract

People nowadays use social media platforms to capture and share real-time incidents in the form of images, videos and text. However, sharing too much information at once makes it harder for first responders to determine where exactly individuals are in need and whether they require immediate assistance. In the past, machine learning techniques were used to automatically identify and infer disaster response from images, as manually identifying disaster types is currently challenging. Therefore, in this paper, deep learning models are used to investigate how well they can classify the images according to their disaster type by learning the features extracted from the input images on their own. In this study, 2 existing datasets namely the ‘Comprehensive Disaster Dataset’ (CDD) and ‘Natural Disaster Dataset’ (NDD) based on disaster types were customized into a dataset entitled as ‘Customized Disaster Dataset’. The Customized Disaster Dataset comprises of a total of ten classes, three of which are non-damage images, Pre-trained models like the MobileNetV2, VGG16 and InceptionV3 were used to train the datasets to allow for further comparison with existing studies. Along with that, a customized neural network model was created and trained on the datasets. Different scenarios were devised to assess the top 3 performing models. The InceptionV3 being best model had a classification accuracy of 96.86%. In this study, we have demonstrated the effectiveness of CNN models as a tool for automatic disaster type classification.