Polarimetric detection of maritime floating small target based on the Complex-valued Entropy Rate Bound Minimization

Abstract

Detection of sea-surface small floating targets in maritime high-resolution surveillance radar has been an active area of research in recent years. In this paper, we propose a new detector based on a complex-valued independent component analysis (cICA) algorithm proposed by Geng-Shen Fu et al. called complex entropy rate bound minimization (CERBM), to look for targets in polarimetric radars. It uses received time series at cell under test (CUT) with different polarizations as distinct mixtures. The proposed detector can exploit all information of polarimetric radar for an accurate detection. It does separation on the mixtures using CERBM which results in two output sources, i.e. clutter and target. Finally, the target is detected using estimation of the parameters of K-distribution for outputted sources. Our experiments on the recognized IPIX radar database show that the proposed detector obtains better detection performance in comparison to the newly proposed detectors. The robustness of the detector is also investigated by experiment in either low and high sea state which shows its appropriate results.

Convolutive Complex-Valued Independent Component Analysis for Nonlinear Radar Signal Processing and Maritime Weak Target Detection

“…In summary, the use of noncircularity and non-Gaussianity in the convolution model of the cICA results in the best separation performance in the field of complex-valued radar signal processing. To the best of our knowledge, a few convolutive cICA algorithms [32] so far been introduced. erefore, in this section, we present a new convolutive cICA algorithm to separate radar signals in practical scenarios via our proposed detector after reviewing the first two algorithms.…”

“…Some algorithms employ two types of diversity, i.e., non-Gaussianity and nonwhiteness. CEBM [1], noncircular FastICA [31], and the complex fixed-point algorithm (CFPA) [32] utilize both non-Gaussianity and noncircularity to perform separation tasks. Complex-valued entropy rate bound minimization (CERBM) [30] exploits all three important types of diversity: non-Gaussianity, sample dependence, and noncircularity.…”

Facilitating learning adaptive V-tail of a supersonic missile for radar cross-section reduction during interval flight

“…Multi-platform radar detection technology has wide applications in reconnaissance, terrain tasks, meteorological parameters and hydrological monitoring [ [32] , [33] , [34] ]. Cognitive radar systems and cognitive electronic warfare systems have been presented, and floating small targets and magnetic intercalation expansion models have been investigated [ [35] , [36] , [37] ]. Unstructured grid technology is used to process target surfaces for calculating their radar cross-section [ 38 ].…”