Detecção de mudanças no entorno de reservatórios a partir de série temporal de imagens orbitais

Abstract

Perform change detection of Earth's surface features is important to understanding both the dynamics of the phenomena and for the prediction of impacts and to support decision-making. During the last decades were developed several change detection techniques from images, among them those based on remote sensing images. In general, the change detection involves the use of a set of multi-temporal data, which allows quantitative analysis of the phenomenon of interest. An application of great interest of these techniques is the automatic detection of changes in the vicinity of reservoirs, which can be used as auxiliary data in a monitoring system of the areas of interest. In such a system it is expected that the changes resulting from human activity are detected even if there are factors that cause differences between scenes, such as atmospheric conditions, scene lighting, sensor view point, soil moisture, among other factors. Considering this context, this paper presents the evaluation results of a change detection approach based on a modification applied to the RCEN technique (Radiometric Rotation Controlled by Nonchange axis). The method was implemented and applied to a set of orthorectified images obtained by orbital system SPOT-6, taken at two different times on the Canoas I reservoir, under concession from Duke Energy. The results showed that the algorithm based on modified RCEN technique was efficient to detect automatically changes.