Given its superior information acquisition capability, Polarimetric Synthetic Aperture Radar has been widely used in maritime target extraction and detection. However, due to the interference of complex imaging environment and the require of various-scale ship extraction, the capability of high-precision PolSAR ship extraction is still highly constrained. To this end, we propose a translation difference-based framework for complete ship extraction. A multi-sequence data generating strategy is firstly proposed, which acquires the master and slave data through data translation, offering a series space to fully highlight the difference information. Based on the generated multi-sequence data, a revised polarization ratio extraction operator is proposed by incorporating the optimal polarization state and depolarization effect, which can simultaneously achieve the purpose of target extraction, clutter cancellation, and interference rejection. Finally, in order to visualizes the scattering differences of different regions, we put forward a translation matrix representation diagram, which can display the parts where positive and negative change direction and trend of the constructed operator. Experiments carried out with real PolSAR data demonstrate that the proposed method can, on the one hand, effectively suppress interference and detect small-scale ship targets, and possess considerable receiving operating characteristic curve. On the other hand, it is able to extract the content of ship target completely with favorable target clutter ratio. Moreover, the directional sensitivity of the extraction operator and the potential of translation-based multi-sequence data in contour extraction is also demonstrated.

In the realm of bearings-only target tracking, the pseudo-linear Kalman filter (PLKF) has garnered significant interest, due to its low computational demands and robust stability. However, the interrelation between the measurement matrix and noise introduces bias into the PLKF’s target state estimation. To address this issue, we introduce a fusion unbiased PLKF (FUBKF) algorithm. This algorithm initiates with a global pseudo-linear treatment of the measurement equation, subsequently isolating the noise within the measurement matrix. By employing the unscented Kalman filter (UKF), the algorithm achieves precise estimation of the measurement matrix, thereby mitigating the estimation error stemming from the correlation between the measurement matrix and noise. Simulation outcomes demonstrate that the proposed algorithm substantially enhances tracking accuracy and sustains high stability in both 2D and 3D bearings-only target tracking scenarios, encompassing both non-maneuvering and maneuvering conditions.

Synthetic-aperture radar (SAR) can work in all weather conditions and at all times, and satellite-borne radar has the characteristics of short revisiting period and large imaging width. Therefore, satellite-borne synthetic-aperture radar has been widely deployed, and the SAR images have been widely used in geographic mapping, radar interpretation, ship detection, and other fields. Satellite-borne synthetic-aperture radar is also susceptible to various types of intentional or unintentional interference during the imaging process, and because the interference is a direct wave, its power is much stronger than the wave reflected by targets. As a common interference pattern, radio-frequency interference widely exists in various satellite-borne synthetic-aperture radars, which seriously deteriorates SAR image quality. In order to solve the above problems, this paper proposes a feature decomposition network to suppress interference based on regularization optimization. The contributions of this work are as follows: 1. By analyzing the performance limitations of the existing methods, this work proposes a novel regularization method for radio-frequency interference suppression tasks. From the perspective of data distribution histograms and residual components, the proposed method eliminates the variable components introduced by common regularization, greatly reduces the difficulty of data mapping, and significantly improves its robustness and performance. 2. This work proposes a feature decomposition network, where the feature decomposition module contains two parts; one part only represents the interference signal, and the other part only represents the radar signal. The neurons representing the interference signal are discarded, and the neurons representing the radar signal are used as input for the subsequent network. A cosine similarity constraint is used to separate the interference from the network as much as possible. Finally, this method is validated on the MiniSAR dataset and Sentinel-1A dataset.

With respect to the detection and recognition of an Artificial Modulation Target (AMT) with different modulated types, the state-of-the-art methods generally suffer the deficiencies of overfitting and insufficient generalization of existing neural network solutions. To address these problems, this paper proposes a multi-scale amplitude-phase feature discrimination method for AMTs in SAR images. First, a multi-type modulated AMT Dataset is generated (AMT Detection and Modulation Type Recognition Dataset, ADMTR Dataset), wherein the factors of jamming position, jamming-to-signal ratio (JSR), and the modulated parameter are considered to enhance the generalization. Second, a Multi-Input Multi-Output Fusion Wavelet Neural Network (MIMOFWTNN) is established, which not only uses the amplitude information of the scene but also adequately makes use of the phase and high-frequency information. This empowers us to detect the AMT in a higher dimensional feature space such that the type recognition can be implemented with more certainty. Analysis and discussions conducted on comparison experiments and ablation experiments demonstrate that the proposed network can achieve an average accuracy of 96.96% on the cross-validation set and a correct rate of 99.0% on the completely independent test set, which outperforms the compared methods.