It is a compelling task to detect sea-surface small targets in the background of strong sea clutter. Traditional detection methods usually suffer from poor detection performance and a high probability of false alarm (PFA). In this letter, a PFA-controllable and feature-based detection method is proposed based on an enhanced convolutional neural network (CNN). The time-frequency features of received signals are first extracted by the short-time Fourier transform and converted into feature images. These feature images are then employed as inputs of an enhanced CNN with a PFA control unit. The enhanced CNN takes full advantage of the subtle feature extraction ability of the asymmetric convolution and robust time-frequency maps. Finally, detection results are obtained according to the given PFA. The results on the IPIX dataset show that the probability of detection of the proposed method is about 0.864 when the observation time is 1.024s and PFA is 10-3. Compared with five typical detection methods, the proposed method achieves better detection performance. Besides, results also verify the stable PFA control ability of the proposed method. The source code is available at https://github.com/quqizhe-whu/STDN.

The emerging field of combining compressed sensing (CS) and three-dimensional synthetic aperture radar (3D SAR) imaging has shown significant potential to reduce sampling rate and improve image quality. However, the conventional CS-driven algorithms are always limited by huge computational costs and non-trivial tuning of parameters. In this article, to address this problem, we propose a two-path iterative framework dubbed TPSSI-Net for 3D SAR sparse imaging. By mapping the AMP into a layer-fixed deep neural network, each layer of TPSSI-Net consists of four modules in cascade corresponding to four steps of the AMP optimization. Differently, the Onsager terms in TPSSI-Net are modified to be differentiable and scaled by learnable coefficients. Rather than manually choosing a sparsifying basis, a two-path convolutional neural network (CNN) is developed and embedded in TPSSI-Net for nonlinear sparse representation in the complex-valued domain. All parameters are layer-varied and optimized by end-to-end training based on a channel-wise loss function, bounding both symmetry constraint and measurement fidelity. Finally, extensive SAR imaging experiments, including simulations and real-measured tests, demonstrate the effectiveness and high efficiency of the proposed TPSSI-Net.

Compressed sensing theory has attracted extensive attention in the field of linear array 3-D Synthetic Aperture Radar (SAR) sparse imaging. However, conventional CS-based algorithms always suffer from quite huge computational cost. In this paper, we propose a new method for 3-D SAR sparse imaging based on convolutional neural network (CNN). Inspired by the work of ISTA-NET, a complex-valued version for imaging tasks is modified. Furthermore, we introduce a approximate phase correction scheme for 3-D imaging, it makes the proposed method works with only a constant measurement matrix corresponding to any slice. Moreover, Using a random training strategy, ISTA-NET networks for 3-D SAR imaging are effectively trained. Experimental results demonstrate that the proposed method outperforms conventional ISTA large margins in both accuracy and speed.