Abstract: Due to its noticeable advantages of working ,Synthetic aperture radar (SAR), has become a significant device for many remote sensing applications. The Existing methods for SAR images perform well under some constraints. In this work, ship detection method based on CNN (Convolutional Neural Network) called VGGnet (Visual Geometry Group) is proposed. To improve the performance of ship detection by adopting multi-level features constructed by the convolution layers, which fits ships the different sizes of ships. The Simulation result of the proposed method is comparable with the existing method.

Keywords : Synthetic aperture radar (SAR), Convolutional Neural Network(CNN), Visual Geometry Group(VGGnet), SAR ship detection dataset (SSDD), etc.,

| DOI: 10.17148/IARJSET.2021.8421