Unsupervised Change Detection System Using ORB and Principal Component Analysis for Application on-Board Earth Observation Satellites

Change detection systems on-board satellites aim to decrease the amount of data transmitted to the ground station by sending only the part of the image containing the identified changes, referred to as change image. The objective of this paper is to propose an automatic change detection system for application on-board earth observation satellites. The aim is to provide useful information of the changes in disaster affected areas and to issue early warnings. The proposed system is based on two modules: a registration module based on Oriented FAST and Rotated BRIEF (ORB) algorithm and a change detection module based on Principal Components Analysis (PCA). The performance of the proposed system is evaluated using real satellite images of the Algerian Satellites Alsat-1b and Alsat-2. The results are scaled and compared to existing hardware used on-board Algerian Earth observation satellites.