Indoor disaster analyzer

Abstract

In minor to moderate natural and man-made disasters, such as earthquakes and fires, people may be trapped inside buildings and hurt by the disaster. Considering that trapped victims may be severely injured or unconscious, there is a high demand by emergency responders to get information on the locations and physical statuses of trapped victims inside a building during a disaster. In this paper, a smartphone controlled robotic vehicle, indoor disaster emergency response assistance system, named Indoor Disaster Analyzer, is presented. The system is comprised of two subsystems: a Robotic vehicle and a smartphone. Robotic vehicle will be sent to disastrous environment to get live feed and other environmental data via different sensors installed on vehicle. Image processing algorithm Convolutional Neural Network (CNN) is employed to classify victim bodies in disastrous environment. An analyzed summary of disastrous environment will be presented on android device enabling rescue team to plan their rescue operations in well-organized way.