This paper presents a novel warning system framework for detecting people and vehicles in danger. The system was tested in several images compiled from Flickr and other social media sources and is highly suggested to get integrated in future warning surveillance and safety systems for preventing or solving crisis events. The proposed framework recruits State-ofthe-Art deep learning technologies so as to solve a series of image processing and machine learning challenges and provides a near real-time localization solution for detecting and scoring severity safety levels of people and vehicles in flood and fire images.

This work was supported by beAWARE and EOPEN project partially funded by the European Commission under grant agreement No 700475 and 776019