The varying Polarimetric Orientation Angles (POAs) result in scattering diversity, leading to ambiguity in the interpretation of Polarimetric Synthetic Aperture Radar (PolSAR) images. Exploring the scattering characteristics in the Polarimetric Rotation Domain (PRD) and the complementary features can help overcome the ambiguity. To address this, we propose a novel PolSAR image classification algorithm called Learning Scattering similarity and Texture-based attention with Convolutional Neural Networks (LSTCNN). Three strategies are included in the proposed method. Firstly, a pixel-level Scattering Similarity Learning (SSL) module is proposed to analyze the scattering components of radar targets by learning the mapping from PolSAR data in the PRD to typical scattering models, with rotation angles as learnable parameters to utilize scattering diversity and avoid ambiguity. Secondly, a neighborhood-level Texture-based Attention (TA) module is proposed to learn the spatially enhanced features of PolSAR images, with the attention module design guided by the physical meaning of texture and consideration of channel and position importance. Finally, the proposed LSTCNN, which includes the SSL module, TA module, and classification module, combines pixel-level scattering features in the PRD and neighborhood-level texture features to increase the discriminability of features. The experimental results on three PolSAR images acquired by AIRSAR and E-SAR demonstrate the robustness and excellence of LSTCNN.

Thanks to the availability of large-scale data, deep Convolutional Neural Networks (CNNs) have witnessed success in various applications of computer vision. However, the performance of CNNs on Synthetic Aperture Radar (SAR) image classification is unsatisfactory due to the lack of well-labeled SAR data, as well as the differences in imaging mechanisms between SAR images and optical images. Therefore, this paper addresses the problem of SAR image classification by employing the Generative Adversarial Network (GAN) to produce more labeled SAR data. We propose special GANs for generating SAR images to be used in the training process. First, we incorporate the quadratic operation into the GAN, extending the convolution to make the discriminator better represent the SAR data; second, the statistical characteristics of SAR images are integrated into the GAN to make its value function more reasonable; finally, two types of parallel connected GANs are designed, one of which we call PWGAN, combining the Deep Convolutional GAN (DCGAN) and Wasserstein GAN with Gradient Penalty (WGAN-GP) together in the structure, and the other, which we call CNN-PGAN, applying a pre-trained CNN as a discriminator to the parallel GAN. Both PWGAN and CNN-PGAN consist of a number of discriminators and generators according to the number of target categories. Experimental results on the TerraSAR-X single polarization dataset demonstrate the effectiveness of the proposed method.

Recently, object detection in natural images has made a breakthrough, but it is still challenging in oriented ship detection for remote sensing imagery. Considering some limitations in this task, such as uncertain ship orientation, unspecific features for locating and classification in the complex optical environment, and multiplicative speckle interference of synthetic aperture radar (SAR), we propose an oriented ship detector based on the pairwise branch detection head and adaptive SAR feature enhancement. The details are as follows: (1) Firstly, the ships with arbitrary directions are described with a rotated ground truth, and an oriented region proposal network (ORPN) is designed to study the transformation from the horizontal region of interest to the rotated region of interest. The ORPN effectively improved the quality of the candidate area while only introducing a few parameters. (2) In view of the existing algorithms that tend to perform classification and regression prediction on the same output feature, this paper proposes a pairwise detection head (PBH) to design parallel branches to decouple classification and locating tasks, so that each branch can learn more task-specific features. (3) Inspired by the ratio-of-average detector in traditional SAR image processing, the SAR edge enhancement (SEE) module is proposed, which adaptively enhances edge pixels, and the threshold of the edge is learned by the channel-shared adaptive thresholds block. Experiments were carried out on both optical and SAR datasets. In the optical dataset, PBH combined with ORPN improved recall by 5.03%, and in the SAR dataset, the overall method achieved a maximum F1 score improvement of 6.07%; these results imply the validity of our method.

With the swift advancement of deep learning, significant strides have been made in Polarimetric Synthetic Aperture Radar (PolSAR) image classification, particularly with the advent of diffusion models that allow for explicit class probability modeling. However, existing diffusion models have yet to fully leverage the rich polarimetric characteristics of PolSAR images. To address this, we propose the Multi-level Conditional Diffusion (MCDiff) model for PolSAR image classification, incorporating three key strategies. Firstly, a Prior Learning (PL) module is constructed to capture scattering characteristics across all three polarization basis parameter spaces, providing conditional guidance for the diffusion model. Secondly, a Multi-scale and Multi-dimensional noise Prediction (MMP) module is designed to reduce the information loss when noisy labels and image features of different dimensions are fused to predict noise. Finally, a Multi-level high-order Statistical feature Learning (MSL) module is introduced to aid in the additive Gaussian noise prediction of noisy labels while mitigating the impact of PolSAR images' multiplicative speckle noise on the prediction. Experimental results on three benchmark datasets confirm MCDiff's ability to achieve high-performance explicit class probability modeling for PolSAR images among the compared methods

Recently, deep-learning methods have yielded rapid progress for object detection in synthetic aperture radar (SAR) imagery. It is still a great challenge to detect ships in SAR imagery due to ships’ small size and confusable detail feature. This article proposes a novel anchor-free detection method composed of two modules to deal with these problems. First, for the lack of detailed information on small ships, we suggest an adaptive feature-encoding module (AFE), which gradually fuses deep semantic features into shallow layers and realizes the adaptive learning of the spatial fusion weights. Thus, it can effectively enhance the external semantics and improve the representation ability of small targets. Next, for the foreground–background imbalance, the Gaussian-guided detection head (GDH) is introduced according to the idea of soft sampling and exploits Gaussian prior to assigning different weights to the detected bounding boxes at different locations in the training optimization. Moreover, the proposed Gauss-ness can down-weight the predicted scores of bounding boxes far from the object center. Finally, the effect of the detector composed of the two modules is verified on the two SAR ship datasets. The results demonstrate that our method can effectively improve the detection performance of small ships in datasets.

The sensitivity and dependence of polarization and scattering on target orientation and radar incident angle pose a significant challenge in interpreting PolSAR images. Previous studies have emphasized the potential advantages of compensating for target orientation and acquiring diverse scattering information by rotating the polarimetric matrix. To fully exploit inter-pixel polarization information and achieve consistency in the targets' polarization orientation angle (POA), we propose a transformer-based framework that combines POA align with cyclic channel attention for PolSAR image classification. First, we select relevant features and introduce an implicit layer to facilitate unsupervised learning of POA, guiding the alignment of target orientation. Second, considering the inherent correlation between input POA channels and the necessity for more rational and efficient utilization of channel information, we devise a lightweight channel attention module with local cross-channel interaction and a cyclic padding strategy. Finally, this article is devoted to presenting a unified global modeling framework based on transformer. The primary objective is to overcome the limitations of local modeling capability in CNNs and comprehensively capture distinctions between polarization channels and intricate relationships among polarimetric information across pixels. Extensive experiments and analyses have demonstrated the robustness and effectiveness of the proposed method.