Real Time Victim Detection with Mobile Robot in Smoky Environments

Abstract

Human victim detection in smoky indoor environments during search and rescue missions is still challenging. This situation is because firefighters are on the one hand exposed to unstable building structures and on the other hand their cognitive fatigue, due to long search missions, reduce the efficient victim detection in these hazardous environments. In this paper, an approach to detect victims in real time with a detection model assisting firefighters in their mission is presented. Thereby, an optical camera mounted on a remote-controlled mobile robot with a trained detection model using deep learning is used for victim detection in real time displaying the localisation to an operator outside the scene. Experiments show that this approach enables victim detection in smoky indoor environments. The victim detection model achieves a real time victim detection rate ranges from 0.6 to 0.9 in a light smoky environment.