Image-based recognition of natural disasters and other events that might require human assistance

Abstract

The work is going to consist on building a dataset with images from incidents such as fires, earthquakes, floodings, contamination… in different scenarios. The data needs to be cleaned and is going to be annotated using Amazon Mechanical Turk.

Meanwhile a model for recognising the scenes and the incidents is going to be trained and tested using deep learning techniques in order to achieve good results. The model is going to use computer vision techniques.