With the development of satellite technology, up to date imaging mode of synthetic aperture radar (SAR) satellite can provide higher resolution SAR imageries, which benefits ship detection and instance segmentation. Meanwhile, object detectors based on convolutional neural network (CNN) show high performance on SAR ship detection even without land-ocean segmentation; but with respective shortcomings, such as the relatively small size of SAR images for ship detection, limited SAR training samples, and inappropriate annotations, in existing SAR ship datasets, related research is hampered. To promote the development of CNN based ship detection and instance segmentation, we have constructed a High-Resolution SAR Images Dataset (HRSID). In addition to object detection, instance segmentation can also be implemented on HRSID. As for dataset construction, under the overlapped ratio of 25%, 136 panoramic SAR imageries with ranging resolution from 1m to 5m are cropped to 800 × 800 pixels SAR images. To reduce wrong annotation and missing annotation, optical remote sensing imageries are applied to reduce the interferes from harbor constructions. There are 5604 cropped SAR images and 16951 ships in HRSID, and we have divided HRSID into a training set (65% SAR images) and test set (35% SAR images) with the format of Microsoft Common Objects in Context (MS COCO). 8 state-of-the-art detectors are experimented on HRSID to build the baseline; MS COCO evaluation metrics are applicated for comprehensive evaluation. Experimental results reveal that ship detection and instance segmentation can be well implemented on HRSID.

As electromagnetic environments in battlefields are more and more complex, there are more kinds of suppression jamming noise including both single jamming signals and compound jamming signals. Thus, suppression jamming recognition especially for compound jamming signals is becoming vital and challenging. Whereas conventional methods are prone to owning the low recognition accuracy and the high computational complexity, especially under low jamming-to-noise ratio (JNR) conditions. In this paper, a novel jamming recognition network (JRNet) based on robust power-spectrum features is proposed to recognize ten kinds of suppression jamming signals including four single jamming patterns and six compound jamming patterns. The proposed method combines the significant representative power of the JRNet and distinguished power-spectrum features of jamming signals to promote the recognition performance. By integrating residual blocks and asymmetric convolution blocks, the JRNet is capable to address the degradation problem and enhance the recognition ability for subtle features. The simulation results show that the overall recognition accuracy of the proposed method is more than 90% even when the JNR is -18 dB and is close to 100% at -6 dB. Compared with five comparison methods in recent literatures, the proposed JRNet achieves better and stable recognition performance especially under low JNR conditions with relatively less storage source and a bit more FLOPs and inference time.

As the electromagnetic environment in battlefields is more and more complex, automatic modulation recognition for radar signals is becoming vital and challenging. Traditional methods are more likely to cause lower recognition accuracy with higher computational complexity in low signal-to-noise ratio (SNR). Feature redundancy especially for handcrafted features is one of the shortcomings of deep-learning-based methods. In this article, a novel end-to-end sequence-based network that consists of a shallow convolutional neural network, a bidirectional long short-term memory (Bi-LSTM) network strengthening with a self-attention mechanism, and a dense neural network is constructed to recognize eight kinds of intrapulse modulations of radar signals. The autocorrelation functions of received radar signals are first calculated as autocorrelation features. Then, these features are employed as inputs of the proposed network which owns significant sequence processing advantages and adaptive selection ability of features. Finally, the proposed network outputs prediction modulations directly. The simulation results verify the robustness and effectiveness of autocorrelation features. And the proposed network achieves about 61.25% accuracy at −20 dB and more than 95% accuracy at −10 dB. Compared with four state-of-the-art networks, the proposed network has better recognition performance especially at low SNRs with much lower computational complexity. Results on measured signals also demonstrate that the proposed network outperforms these four networks.

Automatic modulation classification of radar signals, which plays a significant role in both civilian and military applications, is researched in this study through a deep learning network. In this study, a novel network combined a shallow convolution neural network (CNN), long short‐term memory (LSTM) network and deep neural network (DNN) is proposed to recognise six types of radar signals with different signal‐to‐noise ratio (SNR) levels from −14 to 20 dB. First, raw signal sequences in the time domain, frequency domain and autocorrelation domain are as input for a shallow CNN. Then the features extracted by CNN will be the input of LSTM network. Finally, DNNs will output the signal modulation types directly. The simulation results demonstrate that the accuracies in autocorrelation domain are all more than 90% at −6 dB and close to 100% when SNR > −2 dB. The recognition performances of the three domains are compared. Compared with other recognition methods, the proposed method has higher average accuracy and better performance under low SNR condition. The measured results show that the proposed method has achieved high accuracies of common four kinds of measured radar signals.

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 (TF) features of received signals are first extracted by the short-time Fourier transform (STFT) and converted into feature images. These feature images are then employed as the 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 TF maps (TFMs). Finally, detection results are obtained according to the given PFA. The results on the IPIX dataset show that the probability of detection (PD) of the proposed method is about 0.864 when the observation time is 1.024 s 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 .

Since the Compressed Sensing (CS) theory broke through the limitation of the traditional Nyquist sampling theory, it has attracted extensive attention in the field of microwave imaging. However, in three dimensional (3-D) microwave sparse reconstruction application, conventional CS-based algorithms always suffer from huge computational cost. In this paper, a novel 3-D microwave sparse reconstruction method based on a complex-valued sparse reconstruction network (CSR-Net) is proposed, which converts complex number operations into matrix operations for real and imaginary parts. Using the “unfolding + network approximate” scheme, each iteration process of CS-based iterative threshold optimization is designed as a block of CSR-Net, and a modified shrinkage term is introduced to improve the convergence performance of the approach. In addition, CSR-Net adopts a convolutional neural network module to replace a nonlinear sparse representation process, which dramatically reduces computational complexity and improves reconstruction performance over conventional CS-based iterative threshold optimization algorithms. Then, we divide the 3-D scene into a series of 2-D slices, and a phase correction scheme is adopted to ensure that the whole 3-D scene can be reconstructed with measurement matrix of a slice. Moreover, an efficient Position-Amplitude-Random (PAR) training method without additional real-measured data is employed for the proposed network, which effectively train the CSR-Net without enough real-measured data. Extensive experiment results demonstrate that CSR-Net outperforms both conventional iterative threshold optimization methods and deep network-based ISTA-NET-plus large margins. Its speed and reconstruction accuracy in 3-D imaging can achieve a state-of-the-art level.