At present, deep learning has been widely used in SAR ship target detection, but the accurate and real-time detection of multi-scale targets still faces tough challenges. CNN-based SAR ship detectors are challenged to meet real-time requirements because of a large number of parameters. In this paper, we propose a lightweight, single-stage SAR ship target detection model called YOLO-based lightweight multi-scale ship detector (LMSD-YOLO), with better multi-scale adaptation capabilities. The proposed LMSD-YOLO consists of depthwise separable convolution, batch normalization and activate or not (ACON) activation function (DBA) module, Mobilenet with stem block (S-Mobilenet) backbone module, depthwise adaptively spatial feature fusion (DSASFF) neck module and SCYLLA-IoU (SIoU) loss function. Firstly, the DBA module is proposed as a general lightweight convolution unit to construct the whole lightweight model. Secondly, the improved S-Mobilenet module is designed as the backbone feature extraction network to enhance feature extraction ability without adding additional calculations. Then, the DSASFF module is proposed to achieve adaptive fusion of multi-scale features with fewer parameters. Finally, the SIoU is used as the loss function to accelerate model convergence and improve detection accuracy. The effectiveness of the LMSD-YOLO is validated on the SSDD, HRSID and GFSDD datasets, respectively, and the experimental results show that our proposed model has a smaller model volume and higher detection accuracy, and can accurately detect multi-scale targets in more complex scenes. The model volume of LMSD-YOLO is only 7.6MB (52.77% of model size of YOLOv5s), the detection speed on the NVIDIA AGX Xavier development board reached 68.3 FPS (32.7 FPS higher than YOLOv5s detector), indicating that the LMSD-YOLO can be easily deployed to the mobile platform for real-time application.

The deployment of deep convolutional neural networks (CNNs) in SAR ship real-time detection is largely hindered by huge computational cost. In this paper, we propose a novel learning scheme for training a lightweight ship detector called Tiny YOLO-Lite, which simultaneously 1) reduces the model storage size; 2) decreases the floating point operations (FLOPs) calculation; 3) guarantees the high accuracy with faster speed. This is achieved by self-designed backbone structure and network pruning, which enforces channel-level sparsity in the backbone network and yields a compact model. In addition, knowledge distillation is also applied to make up for the performance decline caused by network pruning. Hereinto, we propose to let small student model mimic cumbersome teacher's output to achieve improved generalization. Rather than applying vanilla full feature imitation, we redefine the distilled knowledge as the inter-relationship between different levels of feature maps and then transfer it from the large network to a smaller one. On account that the detectors should focus more on the salient regions containing ships while background interference is overwhelming, a novel attention mechanism is attached to the distilled feature for enhanced representation. Finally, extensive experiments are conducted on SSDD, HRSID and two large-scene SAR images to verify the effectiveness ofthe thinner SAR ship object detector in comparison of with other CNN-based algorithms. The detection results demonstrate that the proposed detector can achieve lighter architecture with 2.8M model size, more efficient inference (>200fps) with low computation cost, and more accurate prediction with knowledge transfer strategy.

Even after 50 years of development, narrowband high-power microwave (HPM) source technologies remain the focus of much research due to intense interest in innovative applications of HPMs in fields such as directed energy, space propulsion, and high-power radar. A few decades ago, the main aim of investigations in this field was to enhance the output power of a single HPM source to tens or hundreds of gigawatts, but this goal has proven difficult due to physical limitations. Therefore, recent research into HPM sources has focused on five main targets: phase locking and power combination, high power efficiency, compact sources with a low or no external magnetic field, high pulse energy, and high-power millimeter-wave generation. Progress made in these aspects of narrowband HPM sources over the last decade is analyzed and summarized in this paper. There is no single type of HPM source capable of excellent performance in all five aspects. Specifically, high pulse energy cannot be achieved together with high power efficiency. The physical difficulties of high power generation in the millimeter wave band are discussed. Semiconductor-based HPM sources and metamaterial (MTM) vacuum electron devices (VEDs) are also commented on here. Semiconductor devices have the advantage of smart frequency agility, but they have low power density and high cost. MTM VEDs have the potential to be high power efficiency HPM sources in the low frequency band. Moreover, problems relating to narrowband HPM source lifetime and stability, which are the important determinants of the real-world applicability of these sources, are also discussed.

Ship detection in polarimetric synthetic aperture radar (PolSAR) images has attracted widespread attention in recent years. However, pixel-level detection methods are heavily affected by inherent speckle noise. In this letter, we proposed a detection method that enhances the ship-sea contrast beforehand by combining local statistical saliency and scattering mechanism coherence in superpixel-level. First, simple linear iterative clustering (SLIC)-based segmentation method is adopted for PolSAR images to generate superpixels. Then, local saliency is calculated based on superpixel-level similarity from the perspective of statistical characteristics. Based on this, the superpixel-level modified polarimetric coherence metric is obtained from the perspective of physical scattering mechanisms, which can help distinguish small ships with low saliency and strong sea clutters with high saliency. Ship detection is achieved by combining the two features above. The experimental results based on real PolSAR data show that compared with other classic and state-of-the-art methods, the proposed method has improved the figure of merit (FoM) by at least 4.28% and has increased the target clutter ratio by at least 8.43 decibel (dB) on average.

In this article, an ultrahigh repetition frequency sub-nanosecond pulse generator based on vanadium-compensated semi-insulating (VCSI) 4H-SiC photoconductive semiconductor switch (PCSS) under high bias electric field is presented. In this work, the 0.8 mm-thick 4H-SiC PCSS was found to work with electric fields up to 200 kV/cm and power capacity of 176 kW. The VCSI 4H-SiC PCSS response test was performed with a 1 MHz, 1030 nm laser cluster driver with configurable optical pulsewidth and current viewing resistor (CVR) high frequency response circuit. In the experiment, the laser pulsewidth was varied between 300 and 500 ps, and 1.5 ns. The system generated a 1 MHz repetition frequency pulse with a minimum half-width of 365 ps and less than 100 ps of jitter. The results revealed higher response performance for single/continuous pulse triggered light of various pulsewidths. Due to the low absorption efficiency of 4H-SiC for non-intrinsic light, an axial optical reflection trap structure was utilized to boost the light absorption efficiency of PCSS. The proposed structure significantly improved the light absorption performance of PCSS devices. The photocurrent increase ratio of roughly 115% was obtained. This study presents the first results of MHz re-frequency high-power switching in bulk semi-insulating 4H-SiC.

A frequency-agile microwave generating system is examined in this letter. Vanadium-compensated semi-insulation (VCSI) 4H-SiC photoconductive semi- conductor switch (PCSS) has been introduced to achieve wide-range frequency tuning. The output microwave frequency is tuned by adjusting the pulse width of the laser. Both the simulation and the experimental results show a tuning frequency range of 0.5 GHz to 10.0 GHz. The maximum operating output power of the system at 10 GHz is 1.13 W, equivalent to a charging voltage of 1.5 kV and a modulated light wavelength of 1064 nm. Further experiment revealed that with 355 nm laser and charging voltage of 5 kV, the output power could be increased to 86.5 kW.