Estudo da modelagem estatística em imagens SAR

Abstract

SAR images have become important tools with applications in areas such as environmental monitoring and national security. Statistical modeling is an important step in SAR image processing and analysis, and its results are widely used in research areas such as target detection and image classification. In this study, five probability distribution functions are explored: K, G0, Rayleigh, Lognormal, and Weibull to model vehicle regions in the forest, lake, forest, and road. The data collected from these regions by the CARABAS-II aircraft at VHF frequency (20-90 MHz) are analyzed for the number of scatterers and distributions that best describe the studied regions. The parameters of each distribution are estimated based on the Maximum Likelihood Method and the Method of Moments, and the distributions are compared using the KS distance as a metric.