Ship detection in Synthetic Aperture Radar (SAR) imagery has achieved significant progress but still faces several challenges. For example, single-modal SAR provides limited ship information, and identifying small ships in complex environments is difficult, affecting detection robustness. To address these issues, this letter proposes an efficient small ship detection network based on multi-modal fusion with unpaired SAR and AIS data, named MU-Net. To address the limitations of insufficient single-modal features, it is the first attempt to integrate SAR imagery with ship distribution density information from long-term AIS. Specifically, an Asymmetric Fusion Module (AFM) is designed to incorporate AIS spatial information into SAR imagery through weighted fusion, effectively overcoming the strict data pairing requirements of traditional multi-modal fusion methods and enhancing the spatial and texture feature representation of ships. Furthermore, to boost the performance of small ship detection in challenging scenarios, MU-Net designs a Feature Dynamic Optimization Module (FDOM) and a Channel Shuffle Module (CSM). FDOM adaptively adjusts convolutional filters, and CSM performs channel reconstruction, enhancing the multi-modal feature representation of small ships and effectively reducing interference from complex backgrounds. With the integration of multi-modal information, MU-Net achieves higher detection accuracy using a single detection head. Experimental results indicate that the proposed method outperforms state-of-the-art models, achieving 89.81% Precision, 90.47% Recall, 94.82% AP0.5, and 54.75 AP0.5:0.95, with only 5.25M parameters and 55.9 GFLOPs. The dataset and code will be available at: https://github.com/DLRS09/MU-Net.

Compared to single-source to single-target (1S1T) domain adaptation, single-source to multi-target (1SmT) domain adaptation is more practical but also more challenging. In 1SmT scenarios, the significant differences in feature distributions between various target domains increase the difficulty for models to adapt to multiple domains. Moreover, 1SmT requires effective transfer to each target domain while maintaining performance in the source domain, demanding higher generalization capabilities from the model. In 1S1T scenarios, active domain adaptation methods improve generalization by incorporating a few target domain samples, but these methods are rarely applied in 1SmT due to potential sampling bias and outlier interference. To address this, we propose Progressive Prototype Refinement (PPR), an active multi-target domain adaptation method combining 1SmT with active learning to enhance cross-domain knowledge transfer. Specifically, an uncertainty assessment strategy is used to select representative samples from multiple target domains, forming a candidate set for model training. Based on the Lindeberg--Levy central limit theorem, we sample from a Gaussian distribution using corrected prototype statistics to augment the classifier's feature input, allowing the model to learn transitional information between domains. Finally, a mapping matrix is used for cross-domain alignment, addressing incomplete class coverage and outlier interference. Extensive experiments on multiple benchmark datasets demonstrate PPR's superior performance, with a 6.35% improvement on the PACS dataset and a 17.32% improvement on the Remote Sensing dataset.

Traditional synthetic aperture radar (SAR) image sea-land segmentation algorithms overlook the ship distribution priori-information provided by the automatic identification system (AIS) data, resulting in poor segmentation performance in complex environments such as ports, marine wetlands, beaches, and other sea-land boundaries. To address the above issues, this article comprehensively uses dual-polarization (VV and VH) SAR images and AIS data as the data source, and it specifically proposes a novel pyramid vision transformer (PVT) assisted by the long-time AIS data (AIS-PVT) for sea-land segmentation. AIS-PVT is the first attempt to integrate the ship distribution density priori-information, provided by the long-time AIS data, into the PVT network, thus the multiscale features of the sea and land can be better distinguished. In the decoding stage, we design a feature filter module (FFM). It aggregates features separately along two spatial directions from the skip connections, enhancing the representation of objects of interest while reducing the influence of redundant information. Furthermore, we develop a boundary-pixel-aware function to steer the model training process, allowing AIS-PVT to concentrate more on the neighborhood information of boundary pixels. Importantly, the AIS-PVT method captures global multiscale information and enhances the model’s data fusion capability. The conclusive experimental results demonstrate the superior performance of our approach in sea-land segmentation tasks, outperforming other state-of-the-art (SOTA) techniques.

In road extraction task, traditional Squeeze-and-Excitation (SE) module only calculates the mean value of each channel to represent the salient features of the roads, but it easily causes false detection due to the interference such as water, roofs, and so on. This letter specifically proposes a Multiple-Parameters-Guided Squeeze-and-Excitation (MPGSE) module for road extraction by incorporating two key parameters of the variance, and the coefficient of variation into the SE module. Further, MPGSE module adaptively adjusts the weights of different features to suppress the redundant information while enhancing the informative features, which makes the roads more separable from other disturbances. MPGSE greatly increases the between-class distance and decrease the within-class distance, thus enhancing the separation capability of the road features compared with other interference. In addition, MPGSE module is integrated into D-LinkNet to optimally fuse features, thus further improving the completeness of road feature representation. Undoubtedly, MPGSE-D-LinkNet can achieve better road extraction performance than other methods. The superiority of MPGSE-D-LinkNet is verified on the RoadNet benchmark dataset (RNBD) and Massachusetts road dataset.

Due to the specific characteristics of synthetic aperture radar (SAR), there will be ambiguity interference in SAR images, resulting in low contrast of the ship target to the clutter. This letter proposes an improved super-resolution generative adversarial network (ISRGAN) based ambiguity suppression algorithm for SAR ship target contrast enhancement. The proposed ISRGAN is the first attempt of using GAN for SAR ambiguity suppression. As a post-processing procedure, it does not need prior information of SAR systems, so it can be applied to various observation scenes and different acquisition modes. The generator of ISRGAN embeds the residual dense network (RDN) to optimally fuse the global and local features of the image, and it effectively improves the completeness of the feature information used for SAR ship target contrast enhancement. The superiority of ISRGAN on ambiguity suppression is validated on the Chinese Gaofen-3 imagery.

This letter proposes a trilateral filtering algorithm for speckle reduction in video synthetic aperture radar (video SAR). The novel filter takes traditional bilateral filter as the basic framework, so as to fully exploit the similarities of gray levels and the spatial location of neighboring pixels. Moreover, the proposed trilateral filter additionally exploits the temporal correlation information among adjacent image frames of the SAR videos and effectively reduces the interference of redundant information by using an adaptive similar frame selection technology. Comprehensively considering the three-dimensional correlation information of spatial, temporal, and gray-scale, a triple-similarity kernel is specifically developed for video-SAR de-speckling. The proposed trilateral filter can effectively smooth the speckle noise while greatly sustain the details of each image frame of the SAR videos. Experiments show that the proposed algorithm has better de-speckling performance compared with other algorithms.

It is well-known that the convolutional neural network (CNN) is an effective method for synthetic aperture radar (SAR) target classification. In the convolutional layer of CNN, convolutional kernels of different sizes can extract different feature information of the target. The small-size kernel can extract the local texture feature information, and the large-size kernel can extract the global contour feature information. Traditional CNN methods usually use fixed-size kernels for convolution, and they generally lose part of the target’s feature information, resulting in the inaccurate classification of the SAR targets. This article proposes a novel CNN model based on multikernel-size feature fusion (MKSFF-CNN) for SAR target classification. MKSFF-CNN designs a convolutional methodology with a multichannel parallel topology, it uses convolutional kernels of different sizes to extract the multikernel-size deep features of the SAR target, and then, these features are fused in an optimal way to acquire the lowest loss. Moreover, MKSFF-CNN concatenates the fused features extracted by the convolutional layers of different dimensions to achieve the finest classification. MKSFF-CNN greatly elevates the feature representation completeness of the SAR targets so that more useful feature information can be exploited for SAR target classification. Undoubtedly, MKSFF-CNN can achieve a better classification performance compared with traditional CNN models with a fixed kernel size. The superiority of MKSFF-CNN is validated on the moving and stationary target acquisition and recognition (MSTAR) dataset with the detailed objective and subjective evaluation.

In order to more efficiently mine the features of polarimetric synthetic aperture radar (PolSAR) and establish a more appropriate classification model, this article proposes an improved convolutional autoencoder (ICAE) based on texture feature fusion (TFF-ICAE) for PolSAR terrain classification. First, TFF-ICAE specifically designs a multi-indicator squeeze-and-excitation (MI-SE) block and incorporates it into the CAE network. MI-SE can enhance the essential feature information while suppressing the interference information as much as possible, and it can effectively increase the between-class distance while reducing the within-class distance. Then, TFF-ICAE uses gray level co-occurrence matrix (GLCM) to capture the texture features, and it optimally fuses these texture features and the deep features extracted by ICAE to complete the multilevel feature fusion, elevating the feature representation completeness of the terrain. That is, TFF-ICAE effectively enhances the feature separation capability of different categories while greatly elevating the feature representation completeness. Experiments on the datasets of San Francisco, Oberpfaffenhofen, and Flevoland show that the proposed TFF-ICAE, respectively, achieves overall accuracies of 93.44%, 97.61%, and 97.78%, which are at least 0.92%, 1.52%, and 0.97% higher than other algorithms. Undoubtedly, the superiority of TFF-ICAE is verified on these datasets.

This paper proposes an outliers-robust constant false-alarm rate (OR-CFAR) detector of Gaussian clutter based on the truncated-maximum-likelihood estimator (TMLE) in SAR imagery. The proposed method aims at elevating the detection performance in multiple-target environment, where the sea clutter samples are often contaminated by the interfering target pixels, the azimuth ambiguities, and the breakwater. As a consequence, the parameters used for statistical modeling are over-estimated, resulting in a degradation of the CFAR detection rate. Inspired by the traditional two-parameter CFAR (TP-CFAR) detector of Gaussian clutter, OR-CFAR designs an adaptive threshold-based clutter truncation method to eliminate the high-intensity outliers from the clutter samples in the local reference window, and the probability density function (PDF) of the sea clutter can be accurately modeled through the newly raised TMLE. Furthermore, the optimal truncation depth used for clutter truncation and PDF modeling is evaluated and selected properly to get the best detection results. The OR-CFAR greatly enhances the CFAR detection rate in multiple-target environment, and it is computationally simple and efficient, which has a great application value. The Chinese Gaofen-3 SAR data are used for experiments to show the better detection performance of OR-CFAR.

This paper proposes a multi-scale rotation-invariant haar-like (MSRI-HL) feature integrated convolutional neural network (MSRIHL-CNN)-based ship detection algorithm of the multiple-target environment in synthetic aperture radar (SAR) imagery. Usually, ship detection includes preprocessing, prescreening, discrimination, and classification. Among them, prescreening and discrimination are the most two important stages so that they catch great intention. Based on our previous work, we propose a truncated-clutter-statistics-based joint, constant false alarm rate (CFAR) detector (TCS-JCFAR) for ship target prescreening in the multiple-target environment. TCS-JCFAR greatly enhances the prescreening rate in the multiple-target environment while achieving a low observed FAR. In the discrimination stage, conventional CNN extracts the deep features (high-level features); however, it will lose the local texture and edge information (low-level features) which are of great significance for target discrimination. Hence, the MSRI-HL features are used to represent the multi-scale, rotation-invariant texture, and edge information that conventional CNN fails to capture. The extracted low-level MSRI-HL features and the high-level deep features are optimally fused to a multi-layered feature vector. Finally, the multi-layered feature vector is fed into a typical support vector machine (SVM) classifier for ship target discrimination. The proposed MSRIHL-CNN combines the low-level texture and edge features and the high-level deep features; moreover, they are optimally fused to fully represent the ship targets. Undoubtedly, MSRIHL-CNN has better discrimination performance. The superiority of the proposed TCS-JCFAR-based prescreener and MSRIHL-CNN-based discriminator is validated on the Chinese Gaofen-3 SAR imagery.

A priori-knowledge based ship CFAR detection and determination algorithm is proposed in medium and high resolution SAR images. The algorithm first runs CFAR prescreening to get the coarse detection result, then the priori knowledge of the ships such as area, length and width is used for target discrimination. A sliding window with a certain size and a bright pixel number threshold is set, the window slides on the coarse detection image with a certain step, and the bright pixels in the sliding window are determined whether targets or clutter. If the number of bright pixels in the sliding window is larger than the bright pixel number threshold, then all the bright pixels in the sliding window will be determined as targets, otherwise clutter; finally, the Probability of False Alarm (PFA) of the whole algorithm is deduced. Using the algorithm, the false alarm rate (FAR) is greatly reduced while the targets can be insured detected. The simulation results prove the algorithm's effectiveness.

This paper proposes a local CFAR detector based on gray intensity correlation in SAR imagery. The new detector comprehensively uses the local SCR and the strong gray correlation in ship targets. The detector can well adapt to the changing background by using local SCR, further, the detection performance improves greatly using the 2D CFAR detection by modelling the joint gray intensity PDF (JPDF) of neighbouring pixel pairs of the clutter in the local window. By using real clutter extraction procedure in the background cell, the actual 2D joint Log-normal distribution is precisely modelled which fits the JPDF of the clutter well. Using this detector, the false alarm rate (FAR) caused by speckle and local background non-homogeneity can be greatly reduced, and ship targets too close can also be detected. Under the same probability of false alarm (PFA), the probability of detection (PD) improves greatly compared with conventional CFAR detectors.

A novel ship wake constant false alarm rate (CFAR) detection algorithm is proposed. The algorithm first detects all the ships and replaces the pixels' gray value of the detected ship with the gray mean value. Then, with the ship target's geometric center as the center, a square image with a certain length is got, and the image is subdivided into four subimages, where the gray intensity contrast of the wake to clutter in the subimage is enhanced. Normalized Hough transform is applied on every subimage, and the probability distribution function in the Hough domain of each subimage is modeled, which can be used for CFAR detection. Finally, the detection results of the subimages are fused to get the final detection. Using our algorithm, the signal-to-clutter ratio of the wake to clutter is enhanced, the ship's navigation direction can be extracted easily, and most importantly, CFAR detection is realized.

The purpose of this letter is to show that the azimuth scanning mode of a synthetic aperture radar can be applied to deriving ocean wave spectra and determining the wave propagation direction for the first time, which reveals its enormous potential and great future in ocean observation. The improved Doppler beam sharpening imaging algorithm is used to produce a sequence of individual subimages of ocean waves in the same scan region from different aspect angles with a high revisit rate. These subimages have an inherent property that they are formed at different discretely delayed times. Therefore, wave propagation direction can be determined from a pair of wave images in different scans. Several different methods are applied to the real airborne radar wave data, including the methods of scan sum (taking the standard Fourier spectrum of the scan-summed image), spectral sum, spectral phase shift, and cross-correlation function of subimages. The processing results demonstrate the effectiveness of the algorithms.

The characteristic difference between targets and clutter is analyzed. Considering the ship target's gray intensity distribution and its shape difference compared to the clutter, in this letter, a new algorithm is presented based on correlation. The algorithm utilizes the strong gray intensity correlation in the ship target; also, the joint gray intensity distribution using 2-D joint log-normal distribution of a pixel with neighboring pixels in the clutter is modeled, which can be used for correlation-based joint constant false alarm rate detection. Using this algorithm, the false alarms caused by speckle and local background nonhomogeneity can be greatly reduced. The detection performance is much better.