Disaster management using Remote Sensing on Unsupervised Data

Abstract

One of the biggest challenges in real-world applications is recognizing various objects and the conditions of the land based on the natural disasters in a remote sensing image. Object recognition in remote sensing images is used to locate various geographical locations for monitoring and observing GIS information, but the accuracy is not satisfactory. This research considers it as a base problem and analyzes, and it is motivated to provide a better solution regarding classification accuracy. The main objective of this study is to design and implement a framework named Natural Disaster detection on Remote Sensing data (NDRSD) for detecting and classifying the objects from remote sensing images. The efficiency of the framework increased by applying various image processing stages such as Pre-processing, Image Enhancement, Object Detection, Bag-of-Words creation, and Training – Testing process. The bag-of-words process enables the user to maintain ground truth values for classifying the objects and improves the accuracy of classification. From the entire process, it notices that NDRSD is suitable for processing any RSD. The proposed framework experiments and results verified. By comparing the obtained results with the state-of-the-art methods and the performance is evaluated.