Deep learning models for road passability detection during flood events using social media data

During natural disasters, situational awareness is needed to understand the situation and respond accordingly. A key need is assessing open roads for transporting emergency support to victims. This can be done via analysis of photos from affected areas with known location. This paper studies the problem of detecting blocked / open roads from photos during floods by applying a two-step approach based on classifiers: does the image have evidence of road? If it does, is the road passable or not? We propose a single double-ended neural network (NN) architecture which addresses both tasks at the same time. Both problems are treated as a single class classification problem by the usage of a compactness loss. The study is performed on a set of tweets, posted during flooding events, that contain (i)~metadata and (ii)~visual information. We study the usefulness of each source of data and the combination of both. Finally, we do a study of the performance gain from ensembling different networks. Through the experimental results we prove that the proposed double-ended NN makes the model almost two times faster and memory lighter while improving the results with respect to training two separate networks to solve each problem independently.