Synthetic aperture radar (SAR) ship detection based on deep learning has the advantages of high accuracy and end-to-end processing, which has received more and more attention. However, SAR ship detection faces many problems, such as fuzzy ship contour, complex background, large scale difference and dense distribution of small targets. To solve these problems, this paper proposes a SAR ship detection method with ultra lightweight and high detection accuracy based on YOLOX. Aiming at the problem of speckle noise and blurred ship contour caused by the special imaging mechanism of SAR, a SAR ship feature enhancement method based on high frequency sub-band channel fusion which makes full use of contour information is proposed. Aiming at the requirement of light-weight detection algorithms for micro-SAR platforms such as small unmanned aerial vehicle and the defect of spatial pooling pyramid structure damaging ship contour features, an ultra-lightweight and high performance detection backbone based on Ghost Cross Stage Partial (GhostCSP) and lightweight spatial dilation convolution pyramid (LSDP) is designed. Aiming at the characteristics of ship scale diversity and unbalanced distribution of channel feature information after contour enhancement in SAR images, four feature layers are used to fuse contextual semantic information and channel attention mechanism is used for feature enhancement, and finally the improved ship target detection method based on YOLOX (ImYOLOX) is formed. Experimental tests on the SAR Ship Detection Dataset (SSDD) show that the proposed method achieves an average precision of 97.45% with a parameter size of 3.31 MB and a model size of 4.35 MB, and its detection performance is ahead of most current SAR ship detection algorithms.

Attacking a naval vessel with multiple missiles is an important way to improve the hit rate of missiles. Missile-borne radars need to complete detection and antijamming tasks to guide missiles, but communication between these radars is often difficult. In this paper, an optimization method based on multi-agent reinforcement learning is proposed for the collaborative detection and antijamming tasks of multiple radars against one naval vessel. We consider the collaborative radars as one player to make their confrontation with the naval vessel a two-person zero-sum game. With temporal constraints of the radar’s and jammer’s recognition and preparation interval, the game focuses on taking a favorable position at the end of the confrontation. It is assumed the total jamming capability of a shipborne jammer is constant and limited, and the shipborne jammer allocates the jamming capability in the radar’s direction according to the radar threat assessment result and its probability of successful detection. The radars work collaboratively through prior centralized training and obtain a good performance by decentralized execution. The proposed method can make radars collaborate to detect the naval vessel, rather than only considering the detection result of each radar itself. Experimental results show that the proposed method in this paper is effective, improving the winning probability to 10% and 25% in the two-radar and four-radar scenarios, respectively.

The confrontation between radar and jammer is increasingly competitive in electromagnetic spectrum warfare. The current radar anti-jamming methods are constrained to some extent in complex electromagnetic environment. It is necessary to study not only radar specific action benefit but also confrontation strategy. To improve the anti-jamming capacity of radar system, a game theory-based optimization method is proposed to enhance the decision-making of anti-jamming strategy in this paper. First, we analyzed the radar winning conditions and discussed the temporal constraints of the recognition and preparation process of the radar and jammer actions. Second, a temporal sequence interaction based dynamic game model between radar and jammer is constructed. Then, Q-learning is performed to optimize the radar anti-jamming strategies with the temporal sequence interaction gain as the objective function. The simulation experimental results show that the proposed strategy can significantly improve the radar winning probability in the confrontation.

Radar is an important sensor in electromagnetic spectrum warfare. Its confrontation with naval vessels has become increasingly competitive in recent years. However, current radar anti‐jamming methods are limited to some extent in complex electromagnetic environments, which poses a severe challenge to radar's detection and anti‐jamming capabilities. To improve the anti‐jamming capacity of radar, the authors propose a Stackelberg game‐based optimisation method to enhance the decision‐making of anti‐jamming strategies. First, we analyse the radar's winning conditions by considering the temporal constraints of non‐real‐time radar recognition and preparation actions and construct the radar's actual utility matrix. Second, we construct a Stackelberg game‐based model under the condition of a certain recognition probability, and update the recognition probability and recognition interval during the game. Finally, we discuss the conditions under which the radar can obtain a positive benefit in the game and compare the benefit to the reinforcement learning optimisation method. The simulation experimental results show that the proposed strategy can significantly improve the radar's winning probability in the confrontation.

Frequency agility refers to the rapid variation of the carrier frequency of adjacent pulses, which is an effective radar active antijamming method against frequency spot jamming. Variation patterns of traditional pseudo-random frequency hopping methods are susceptible to analysis and decryption, rendering them ineffective against increasingly sophisticated jamming strategies. Although existing reinforcement learning-based methods can adaptively optimize frequency hopping strategies, they are limited in adapting to the diversity and dynamics of jamming strategies, resulting in poor performance in the face of complex unknown jamming strategies. This paper proposes an AK-MADDPG (Adaptive K-th order history-based Multi-Agent Deep Deterministic Policy Gradient) method for designing frequency hopping strategies in frequency agile radar. Signal pulses within a coherent processing interval are treated as agents, learning to optimize their hopping strategies in the case of unknown jamming strategies. Agents dynamically adjust their carrier frequencies to evade jamming and collaborate with others to enhance antijamming efficacy. This approach exploits cooperative relationships among the pulses, providing additional information for optimized frequency hopping strategies. In addition, an adaptive K-th order history method has been introduced into the algorithm to capture long-term dependencies in sequential data. Simulation results demonstrate the superior performance of the proposed method.

Distributed radar target detection in non-Gaussian noise, modeled as the sum of K-distributed clutter plus thermal noise, is considered in this paper. The conventional target techniques, e.g., constant false-alarm rate (CFAR), scatterer density-dependent generalized likelihood ratio test (SDD-GLRT), and energy integration (EI) detectors, have limited performance. On the other hand, since radar target detection can be considered a classification task, deep learning techniques have been widely applied as radar detectors in recent years, but such techniques require a larger amount of training samples to prevent overfitting, which is time-consuming. To balance detection efficiency and accuracy, this paper proposes an improved random forest algorithm based on the sparrow search algorithm (RF-SSA). First, we propose a mixed method of 3DT space-time adaptive processing and wavelet denoising (3DT-WD) to improve the output signal-to-clutter plus-noise ratio. Then, the SSA is applied to the RF algorithm to adaptively obtain the optimal parameters of the detection model. The simulation results show that the proposed RF-SSA ensures higher detection performance than the other classical methods, showing a gain of about 2 dB at the same detection probability. Moreover, the detection results of the real data further confirm the superiority of the proposed RF-SSA.