Finding Flood Survivors During Rescue Operations by Applying Deep Learning Technique on Aerial Radiometric Thermal Imaging

Abstract

During search and rescue operations in flood disaster, application of deep learning on aerial imaging is pretty good to find the humans when the environmental conditions are favorable and clear but it starts failing when the environmental conditions are adverse or not supporting. During our findings we realized that generally rescue teams stop their rescue work in night time because of invisibility .When orientation of sun comes at front, the drone aerial picture quality starts decaying. It does not work in different types of fog. Also it is difficult to find people when they are somehow hidden in vegetation. This study explains about infrared cameras potentially very useful in disaster management especially in flood [6]. It takes deep learning networks that were originally developed for visible imagery [1], [2] and applying it to long wave infrared or thermal cameras. Most missions for public safety occur in remote areas where the terrain can be difficult to navigate and in some cases inaccessible. So the drone allows you to fly high above the trees see through gaps of foliage and locate your target even in the darkness of night through thermal cameras and then applying deep learning techniques to identify them as human. Creating accurate machine learning models capable of localizing and identifying human objects in a single image/video remained a challenge in computer vision but with recent advancement in drone, radiometric thermal imaging, deep learning based computer vision models it is possible now to support the rescue team to a bigger extent.