Deep Learning and Stereo Vision Based Detection of Post-Earthquake Fire Geolocation for Smart Cities within the Scope of Disaster Management: İstanbul Case

Cities, which are getting crowded day by day, face a number of issues, including increased planning, inadequate infrastructure, heavy traffic and security. Due to such issues, the cities are more susceptible to natural disasters. Although many preparations are made against natural disasters in urban life, it is evident that adequate measures are not taken against secondary disasters. One of the most destructive and frequent secondary disasters is fires after earthquakes. In this study, an early fire detection system is proposed in order to minimize the losses caused by fires in the potentially chaotic environment that may occur after earthquakes in cities. This system consists of a structure that detects fire with convolutional neural network (CNN) based You Only Look Once (YOLO) model, determines the geolocation of the fire with stereo vision/epipolar geometry and provides information to the disaster management center via wireless sensor network (WSN). Experimental test findings conducted in Istanbul verify that the proposed system would be useful for post-earthquake fire detection with low cost, high reliability and high accuracy.