Sparse Bayesian learning in ISAR tomography imaging

作者：Su Wu ge^*; Wang Hong qiang; Deng Bin; Wang Rui jun; Qin Yu liang

来源：Journal of Central South University (English Edition), 2015, 22(5): 1790-1800.

DOI：10.1007/s11771-015-2697-1

• inverse synthetic aperture radar (ISAR)
• tomography
• computer aided tomography (CT) imaging
• sparse recover
• compress sensing (CS)
• sparse Bayesian learning (SBL)

Inverse synthetic aperture radar (ISAR) imaging can be regarded as a narrow-band version of the computer aided tomography (CT). The traditional CT imaging algorithms for ISAR, including the polar format algorithm (PFA) and the convolution back projection algorithm (CBP), usually suffer from the problem of the high sidelobe and the low resolution. The ISAR tomography image reconstruction within a sparse Bayesian framework is concerned. Firstly, the sparse ISAR tomography imaging model is established in light of the CT imaging theory. Then, by using the compressed sensing (CS) principle, a high resolution ISAR image can be achieved with limited number of pulses. Since the performance of existing CS-based ISAR imaging algorithms is sensitive to the user parameter, this makes the existing algorithms inconvenient to be used in practice. It is well known that the Bayesian formalism of recover algorithm named sparse Bayesian learning (SBL) acts as an effective tool in regression and classification, which uses an efficient expectation maximization procedure to estimate the necessary parameters, and retains a preferable property of the l (0)-norm diversity measure. Motivated by that, a fully automated ISAR tomography imaging algorithm based on SBL is proposed. Experimental results based on simulated and electromagnetic (EM) data illustrate the effectiveness and the superiority of the proposed algorithm over the existing algorithms.

• 出版日期2015-5
• 单位中国人民解放军国防科学技术大学