Supporting First Responders in Emergencies using Computer Vision and Drones
Ning Zhang is a PhD student in the department of Applied Earth Sciences. Promotors are prof.dr. N. Kerle, prof.dr.ir. M.G. Vosselman and prof.dr.ing. F.C. Nex from the faculty Geo-information and Earth Observation (ITC).
First responders (FRs) are the first to arrive after a disaster. It is dangerous for them to enter the disaster area without knowing anything about the situation. In order to improve FRs' situational awareness of the emergency environment and to facilitate their rescue planning, the European Union launched INGENIOUS, a project aimed at developing the Next Generation Integrated Toolkit (NGIT) for emergency services of the future. Work Package 3 of the INGENIOUS project was to develop "smart devices in the air and on the ground". As one of the partners in this work package, our aim was to develop computer vision algorithms for scene understanding to support the decision-making and rescue of FRs. Although computer vision had gained a great deal of attention in recent years, its applications in disaster scenarios were limited, and existing methods did not meet FRs' specific requirements. To this end, This dissertation developed several novel computer vision algorithms to support FRs' post-disaster missions within the INGENIOUS project. In particular, the lack of training data was discussed and resolved, and the speed of real-world application was considered.
