For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
In inshore region, it is crucial to identify azimuth ambiguity for moving target (or ship) detection with multichannel synthetic aperture radar (SAR) system. To this end, a multi-feature classification approach based on tensor and affine invariant Riemannian (AIR) distance is proposed in this paper. The proposed method firstly extracts feature tensor (FT) of multichannel SAR images, including correlation coefficient between channels, multi-look interference phase, and spatial structural gradient information. Then, the core feature tensor (CFT) is obtained by alternating optimization and unfolded along the feature dimension and the feature covariance matrix (FCM) is constructed for each range-Doppler unit (RDU). With the AIR distance measure, the inshore region is divided into different clutter regions. Finally, the experiments on real measured data by TerraSAR-X demonstrate that the proposed method can accurately identify the azimuth ambiguity in inshore region.
Inspec keywords: synthetic aperture radar; remote sensing by radar; feature extraction; tensors; radar imaging; image classification; covariance matrices
Subjects: Optical, image and video signal processing; Radar equipment, systems and applications; Image recognition; Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Algebra; Algebra; Geophysical techniques and equipment; Computer vision and image processing techniques