Detection of natural disaster victims using You Only Look Once (YOLO)
No TL;DR found
Abstract
Natural disasters are events that cannot be predicted both by location and time of occurrence. Natural disasters cause property losses and can even take lives. The handling of rapid evacuation must be done by the SAR team to help victims of natural disasters to reduce the amount of loss. But in reality, there are many obstacles in the evacuation process. Starting from facing difficult terrain to necessary equipment limitation. In this research, a system designed to detect victims of natural disasters uses image processing where the picture is carried out using a drone that aims to help find victims in delicate or vulnerable locations when reached directly by humans. Based on this background, this research proposes the development of a method for the detection of victims of natural disasters that aims to assist the SAR team and natural disaster volunteers in searching for victims who are in hard to reach places. The You Only Look Once (YOLO) method is implemented using the python programming language related to image processing. From the research that has been done, the accuracy result of detecting objects of disaster victims is 89%.