IEEE Transactions on Aerospace and Electronic Systems · 2017 · 33 citations · 21 references
ComputingComputer ScienceComputer VisionMachine LearningRemote SensingImage ClassificationRadar Signal ProcessingRadar SystemsRemote Sensing ImageryInverse Synthetic Aperture RadarInverse Synthetic Aperture Radar ProcessingSynthetic Aperture RadarSynthetic Aperture Radar ClassificationSynthetic Aperture Radar DataSynthetic Aperture Radar Image AnalysisSynthetic Aperture Radar ImagingSynthetic Aperture Radar Remote Sensing
This paper proposes a new scheme for improving the classification performance of inverse synthetic aperture radar (ISAR) images. The proposed scheme utilizes the trace transform to gather abundant information from an ISAR image, regardless of the spatial distribution of the target response in the ISAR image. In simulations using ISAR images with various spatial distributions, the proposed scheme substantially improved the classification performance compared with existing methods, which are highly vulnerable to spatial variation.
21