In remote sensing image classification, open-set recognition (OSR) poses a significant challenge, aiming to accurately classify known categories while effectively rejecting unknown class samples or identifying potential novel categories. Although existing methods have made strides in recognizing known classes, they exhibit notable limitations in handling unknown class samples. This letter introduces an OSR model for ship detection, termed masked autoencoder (MAE)-based OSR (MOSR), which leverages the robust representation learning capabilities of the MAE. MOSR not only sustains high accuracy in the recognition of known classes but also markedly enhances the performance in the identification of unknown class samples. Comprehensive experiments on the custom RSHIP-137 remote sensing dataset validate the efficacy and superiority of the MOSR model. Compared with the state-of-the-art (SOTA) adversarial reciprocal point learning (ARPL) method, MOSR shows substantial improvements in both known class recognition accuracy and the area under the receiver operating characteristic curve (AUROC) for unknown class recognition for ship detection. This study presents a novel solution for OSR in remote sensing ship detection and offers valuable insights for future research.

A challenging issue in the field of marine remote sensing is the application of polarimetric synthetic aperture radar (PolSAR) to small ship detection in complicated environments. Several outstanding polarimetric detectors (such as the optimal polarimetric detector, polarimetric whitening filter, and polarimetric notch filter, etc.), have been effectively implemented in practical applications. A linear combination model based on quadratic optimization is summarized to establish a general framework for polarimetric detectors, transitioning the PolSAR ship target detection from a model driven approach to a hybrid (model/data)-driven approach. However, the dimension of the covariance matrix may be high, and the computation cost will be large. The higher dimension of the covariance matrix requires a bigger the data demand. As a result, when the sample size is small, the model performance will degrade. In this paper, to decrease the computational complexity and improve the robustness, we propose a novel method called the simultaneous diagonalization transform (SDT). The proposed method enables an almost simplest representation of information from the covariance matrix providing a rapid detection algorithm. The simulation experiments demonstrate that polarimetric detectors based on SDT consistently outperform those based on other methods in terms of accuracy, efficiency, and sample size requirements across various complex backgrounds. Furthermore, the effectiveness, robust, and fastness of the polarimetric detector based on SDT is validated using real data collected by RadarSAT-2, GaoFen-3, and Sentinel-1A.

Ship detection using polarimetric synthetic radar (PolSAR) imagery attracts a lot of attention in recent years. Most notably, the detector polarimetric notch filter (PNF) has been demonstrated to be effective for ship detection in PolSAR imagery, which gives excellent performances. In this work, a mathematical form of one new PNF (NPNF) based on physical mechanisms of targets and clutter is further developed for partial targets. The different mechanisms have been revealed based on the projection matrix. The experimental results including simulated and measured data demonstrate that the NPNF exhibits a better performance than the original PNF.

Ship detection is an important task in civil or military applications and we can use polarimetric synthetic aperture radar (PolSAR). Many polarimetric detectors were proposed and achieved good performances in particular environments, such as optimal polarimetric detector (OPD), polarimetric whitening filter (PWF), polarimetric notch filter (PNF), polarimetric detection optimization filter (PDOF) and diagonal loading detector (DLD) etc. Up to know, the analytical links among different polarimetric detectors have not been found. In this work, the above polarimetric detectors are unified in mathematical forms and a general framework of polarimetric detectors based on quadratic optimization is presented. The mathematical forms are summarized as a trace of two matrices’ product. One is a detection transformation matrix and the other is the polarimetric covariance matrix of the pixel to be detected. We find that all these polarimetric detectors can be regarded as the optimization of such detection matrix, which is the key point of the general framework, and the difficulty turns to be a linear inseparable problem. Pocket Perceptron Linear Algorithm (PPLA) is used to solve the linear inseparable problem. In the case of low resolution, target detection is almost an indivisible problem, and multilayer perceptron (MLP) cannot provide better detection results than PPLA. In the case of high resolution, target detection becomes a nonlinear separable problem, and MLP is gradually superior to PPLA. Additionally, the optimal weights of the recent DLD are obtained to compare with other detectors in the general framework and the DLD is developed to a more general case (GDLD). The experiments validate the general framework of polarimetric detectors. Different detectors in the general framework are utilized and compared in both simulated and measured PolSAR data. The results show the optimal solution in the general framework can always reach the best performance, and the GDLD is the closest one to the optimal detector of the general framework.

Polarimetric synthetic aperture radar (PolSAR) is widely used in remote sensing and has important applications in the detection of ships. Although many polarimetric detectors have been proposed, they are not well combined. Recently, a polarimetric detection optimization filter (PDOF) was proposed, which performs well in most environments. In this study, a novel subspace form of the PDOF [strict PDOF (SPDOF)] was further developed based on the Cauchy inequality and matrix decomposition theories, enhancing detection performance. Furthermore, a simple method to determine the optimal dimension of the subspace detector based on the trace ratio form was proposed by calculating the area under the receiver operating characteristic (ROC) curve, reaching the best detection performance among the subspaces of the detector. Moreover, to combine different subspace detectors, a modified linear discriminant analysis was proposed and developed for the diagonal loading detector (DLD) based on polarimetric subspaces. The experimental results demonstrate the superiority of these joint polarimetric subspace detectors. Most importantly, DLD solves for previous limitations due to the complex clutter background and achieves a performance comparable to that of the Wishart (Gaussian) distribution, particularly in the low target-to-clutter ratio (TCR) case.

The detection of small ships in polarimetric synthetic aperture radar (PolSAR) images is still a topic for further investigation. Recently, patch detection techniques, such as superpixel-level detection, have stimulated wide interest because they can use the information contained in similarities among neighboring pixels. In this article, we propose a novel neighborhood polarimetric covariance matrix (NPCM) to detect the small ships in PolSAR images, leading to a significant improvement in the separability between ship targets and sea clutter. The NPCM utilizes the spatial correlation between neighborhood pixels and maps the representation for a given pixel into a high-dimensional covariance matrix by embedding spatial and polarization information. Using the NPCM formalism, we apply a standard whitening filter, similar to the polarimetric whitening filter (PWF). We show how the inclusion of neighborhood information improves the performance compared with the traditional polarimetric covariance matrix. However, this is at the expense of a higher computation cost. The theory is validated via the simulated and measured data under different sea states and using different radar platforms.

Constant false alarm rate (CFAR) algorithms using a local training window are widely used for ship detection with synthetic aperture radar (SAR) imagery. However, when the density of the targets is high, such as in busy shipping lines and crowded harbors, the background statistics may be contaminated by the presence of nearby targets in the training window. Recently, a robust CFAR detector based on truncated statistics (TS) was proposed. However, the truncation of data in the format of polarimetric covariance matrices is much more complicated with respect to the truncation of intensity (single polarization) data. In this article, a polarimetric whitening filter TS CFAR (PWF-TS-CFAR) is proposed to estimate the background parameters accurately in the contaminated sea clutter for PolSAR imagery. The CFAR detector uses a polarimetric whitening filter (PWF) to turn the multidimensional problem to a 1-D case. It uses truncation to exclude possible statistically interfering outliers and uses TS to model the remaining background samples. The algorithm does not require prior knowledge of the interfering targets, and it is performed iteratively and adaptively to derive better estimates of the polarimetric covariance matrix (although this is computationally expensive). The PWF-TS-CFAR detector provides accurate background clutter modeling, a stable false alarm property, and improves the detection performance in high-target-density situations. RadarSat2 data are used to verify our derivations, and the results are in line with the theory.