Structure-Awareness SAR Imagery by Exploiting Structure Tensor TV Regularization Under Multitask Learning Framework

Conventional sparsity-driven synthetic aperture radar (SAR) imagery often encounters the problem of loss of structural features in weak scattering. Although there are algorithms that focus on structure enhancement, no proper balance between accuracy and efficiency can be achieved. In this article, a novel feature enhancement algorithm, named structure-awareness SAR (SA-SAR), is proposed by exploiting an emerging regularizer of structure tensor total variation (STV). By imposing the STV norm onto the prior of the scenes or targets to be imaged, the intended structure feature can be analytically solved under the proximal algorithm. More specifically, the regularization method is developed within the alternating direction method of multipliers (ADMM) framework, where closed-form proximity operators can be derived. Due to the ADMM framework, it facilitates to incorporate with more features to be enhanced in a fully synergistic way. Therefore, the $\ell _{1}$ and entropy norms are involved so that the sparse and focusing features can be enhanced accordingly. Considering the coherence of the SAR data, a linear proximal operator is developed within the multitask learning framework. The unavoidable error propagations can be alleviated in a great extent. In such cases, the proposed algorithm is superior in terms of convergence and efficiency. To facilitate the implementation and computation, the STV proximal mapping is optimized under the Vieta theorem. Finally, both simulated and raw SAR data are applied to verify the effectiveness of the proposed algorithm. Comparisons with conventional algorithms are carried out to show the superiority of the proposed algorithm.