Early Flood and Victim Detection

Abstract

Thousands of people die because of earthquake and sometimes because of Tsunamis. The resulting damage can be minimized and lives can be saved if people living in the earthquake- tsunami prone area are already prepared to survive the strike. The warning systems can reduce the losses, by alerting people and monitors rising water in residential areas and fastest method to monitor flood that will help motorists or road user to avoid problem when flood occurred. Flood is an unavoidable natural disaster across the world, causing heavy flow of traffic and can also cause severe damage to properties and lives. For this reason, we created a flood detection system to monitor rising water level, flow rate and the rainfall density in residential areas. Using ultrasonic sensor, we created flood level sensing device which is attached to Node MCU controller to process the sensor’s analog signal into a usable digital value of distance. Each node will update its information in regular intervals and data stored in the Blynk application. Flood height is determined by subtracting the sensor’s height with respect to the floor minus the sensed distance between the sensor and the flood water. Natural disasters can cause losses, both assets and objects can even take lives. Convolutional Neural Network is one of the developments of Artificial Neural Networks for image classification, image segmentation, and object recognition with high accuracy and high performance. Convolutional Neural Network can learn to detect various images according to images from the dataset studied. The user can get real-time information on monitoring floods and victim detection over SMS based service. So to reduce the number of losses, the System is designed for detecting victims of natural disasters using the CNN method.