The utilization of polarimetric synthetic aperture radar (PolSAR) enables the preservation of more comprehensive target scattering characteristics compared to conventional SAR. Despite the significant advancements in deep learning (DL) technology for single polarimetric SAR ship detection, there remains a scarcity of DL research specifically focused on PolSAR ship detection. This article proposed a lightweight theory-driven network (LT-Net) for combining domain knowledge and DL techniques, which is suitable to detect small targets and reduce the computational complexity. The LT-Net incorporates convolutional block attention module, and employs differential downsampling during the process of high-dimensional feature extraction. The integration of domain knowledge lends each convolution step a distinct physical significance. Due to the limited availability of public datasets, this article presents a public fully polarized ship detection (FPSD) dataset for the first time, which contains 853 Pauli pseudocolor maps (in JPG format) and multilook complex data (in TIF format), with a total of 1714 ship targets from AIRSAR, UAVSAR, and RadarSAT-2. The FPSD encompasses a range of scenarios, with the majority of ship targets being small targets. Validation on FPSD shows that LT-Net exhibits significantly lower time complexity and space complexity compared to four popular target detection networks, Meanwhile, LT-Net achieves the best detection performance in the Pauli pseudocolor maps.

Azimuth ambiguity is a common issue in polarimetric synthetic aperture radar (PolSAR) imagery, particularly on calm and windless maritime surfaces, which causes numerous false alarms in ship detection. Numerous methods have been applied in Single Look Complex (SLC) PolSAR imagery to suppress ambiguities. Nevertheless, identifying and removing azimuth ambiguities in Multilook Complex (MLC) PolSAR imagery remains an open problem. This paper proposes an azimuth ambiguity identification method for ship detection in multilook PolSAR imagery. The process is divided into two steps: potential target detection and ambiguity identification. Firstly, the four-component scattering model (Y4O) proposed by Yamaguchi is utilized to decompose the multilook PolSAR image into four dominant scattering categories. Then, the constant false alarm rate (CFAR) detection is conducted based on the total scattering power to detect all potential targets. Azimuth ambiguities are identified according to the correlation coefficient between the measured and standard scattering power vectors. Eventually, the detection map is formed by removing azimuth ambiguities from the CFAR detection result. The proposed method is validated on RadarSAT-2 and AIRSAR images.

Constant false alarm rate (CFAR) detector is a common method for ship detection in polarimetric synthetic aperture radar (PolSAR) image. CFAR detectors greatly depend on the clutter modeling which can be easily affected by the contamination caused by both lower- and higher-intensity outliers such as spilled oil, intensive targets and so on. Traditional CFAR detectors perform detection in a pixel-by-pixel manner which ignores the spatial information. Both the bias in clutter modeling and the absence of spatial information can degrade the ship target detection performance. In this study, a superpixel-level polarimetric bilateral truncated statistics (BTS) CFAR detector is proposed to promote the ship target detection performance in complex ocean scenarios. As the preprocessing of the PolSAR image, the superpixel segmentation is conducted based on the multilook polarimetric whitening filter (MPWF) result to select candidate ship target superpixels for bilateral truncation and background clutter modeling. The elliptical truncation is expanded to complex situation and the relationship between the second moments before and after truncation is derived. The maximum likelihood estimation (MLE) estimator of the equivalent number of looks (ENL) based on the bilateral truncation distribution is derived and compared with other parameter estimators. The influence of the truncation depth on estimator performance is analyzed, according to which the adaptive bilateral truncation method is determined. The Gaussian mixture model (GMM) and the Parzen window kernel method are compared with the model-based method and utilized for data fitting. The proposed method performs bilateral truncation based on the superpixel segmentation result to provide the pure clutter samples for the accurate parameter estimation and clutter distribution modeling, reducing time consumption and false alarm. The method is validated efficient on both simulated and measured data from RADARSAT-2.

With the expanding application of synthetic aperture radar (SAR) in ocean monitoring and port regulation, nearshore ship detection based on SAR image faces notable challenges arising from strong background scattering, dense target occlusion, and large pose variations. Therefore, this paper proposes a two-stage oriented detection network named EARS-Net to improve the accuracy of ship detection in complex nearshore environments. Specifically, a lightweight convolutional block attention module (CBAM) is embedded into the high-level semantic stages of ResNet50 to enhance discriminative ship features while suppressing interference from port infrastructures and shoreline structures. Then, the dynamic angle regression loss (DAL) is proposed, and the angle weight function is designed according to the ship direction distribution characteristics, which allocates higher regression weight to the ship target with larger tilt angle, improving the defect of insufficient positioning accuracy for large angle ships. Moreover, a training strategy that combines focal loss, multi-scale training, and rotated online hard example mining (ROHEM) is employed to alleviate sample imbalance and improve generalization in dense scenes. Experimental results on the nearshore subset of the SSDD show that EARS-Net achieves an average precision (AP) of 0.903 on the test set, demonstrating reliable detection capability under complex backgrounds and dense target distributions. These results validate the effectiveness of our method and highlight its potential as a practical engineering solution for enhancing port situational awareness and coastal security monitoring.