Data, in deep learning (DL), are crucial to detect ships in synthetic aperture radar (SAR) images. However, SAR image annotation limitations hinder DL-based SAR ship detection. A novel data-selection method and teacher–student model are proposed in this paper to effectively leverage sparse labeled data and improve SAR ship detection performance, based on the semi-supervised oriented object-detection (SOOD) framework. More specifically, we firstly propose a SAR data-scoring method based on fuzzy comprehensive evaluation (FCE), and discuss the relationship between the score distribution of labeled data and detection performance. A refined data selector (RDS) is then designed to adaptively obtain reasonable data for model training without any labeling information. Lastly, a Gaussian Wasserstein distance (GWD) and an orientation-angle deviation weighting (ODW) loss are introduced to mitigate the impact of strong scattering points on bounding box regression and dynamically adjusting the consistency of pseudo-label prediction pairs during the model training process, respectively. The experiments results on four open datasets have demonstrated that our proposed method can achieve better SAR ship detection performances on low-proportion labeled datasets, compared to some existing methods. Therefore, our proposed method can effectively and efficiently reduce the burden of SAR ship data labeling and improve detection capacities as much as possible.

Since the heavy clutter seriously restricts the ability of radar to detect target, it is significant to build the target detector under heavy clutter. For practical situations without the secondary data or prior knowledge of target and clutter, this paper proposes a polarization-space-time detector. First, a general radar model is constructed for multiple pulses, multiple arrays, and multiple polarizations. Based on the theory of ternary hypothesis, the secondary data free (SDF) GLRT detector is proposed, which can maintain the constant false alarm probability (CFAR) in inhomogeneous clutter. Then, this paper proposes a matrix transform operator and an adaptive detection method using sliding window respectively, which do not need to know the steering vector of radar and the noncentral parameter of clutter in advance, so that the SDF-GLRT detector can adapt to different application scenarios. In addition, this paper optimizes the polarization waveform of the radar system by constructing a projection matrix, which can give the closed-form solutions of the optimal polarization and worst polarization, instead of relying on numerical solution. Finally, the performances of SDF-GLRT detector and other three detectors are compared by simulated and real data, which verifies that SDF-GLRT detector in this paper can still maintain superior performance in various clutter environments without secondary data.

Since heavy clutter seriously restricts the ability of radar to detect targets, it is significant to build the target detector under heavy clutter. For practical situations without the secondary data or prior knowledge of target and clutter, this paper proposes a polarization-space-time detector. First, a general radar model is constructed for multiple pulses, multiple arrays, and multiple polarizations. Based on the theory of ternary hypothesis, the secondary data free (SDF) GLRT detector is proposed, which can maintain the constant false alarm probability (CFAR) in inhomogeneous clutter. Then, this paper proposes a matrix transform operator and an adaptive detection method using sliding window. These two approaches do not need to know the steering vector of radar and the noncentral parameter of clutter in advance, so the SDF-GLRT detector can adapt to different application scenarios. In addition, this paper optimizes the polarization waveform of the radar system by constructing a projection matrix. This method yields closed-form solutions of the optimal polarization and worst polarization, rather than relying on numerical solution. Finally, the performances of the SDF-GLRT detector and three other detectors are compared by simulated and real data. The proposed SDF-GLRT maintains $P_{\mathrm{FA}}$ of $5.4\times {10}^{-3}$ and $2.6\times {10}^{-3}$ on two IPIX datasets (#54 and #310) at a design $P_{\mathrm{FA}}={10}^{-3}$, whereas the other detectors deviate to $0.0249$–$0.7405$. The optimal polarization yields a detection-probability gain of more than $0.22$ over the worst polarization at $\mathrm{SCR}=0$ dB.