Image registration is the basis for the joint interpretation of synthetic aperture radar (SAR) and optical images. However, the significant nonlinear radiation difference (NRD) and the geometric imaging model difference render the registration quite challenging. To solve this problem, both traditional and deep learning methods are used to extract structural information with dense descriptions of the images, but they ignore that structural information of the image pair is coupled and often process images separately. In this paper, a deep learning-based registration method with a co-attention matching module (CAMM) for SAR and optical images is proposed, which integrates structural feature maps of the image pair to extract keypoints of a single image. First, joint feature detection and description are carried out densely in both images, for which the features are robust to radiation and geometric variation. Then, a CAMM is used to integrate both images’ structural features and generate the final keypoint feature maps so that the extracted keypoints are more distinctive and repeatable, which is beneficial to global registration. Finally, considering the difference in the imaging mechanism between SAR and optical images, this paper proposes a new sampling strategy that selects positive samples from the ground-truth position’s neighborhood and augments negative samples by randomly sampling distractors in the corresponding image, which makes positive samples more accurate and negative samples more abundant. The experimental results show that the proposed method can significantly improve the accuracy of SAR–optical image registration. Compared to the existing conventional and deep learning methods, the proposed method yields a detector with better repeatability and a descriptor with stronger modality-invariant feature representation.

Due to the limitations of the horizontal bounding boxes for locating the oriented ship targets in synthetic aperture radar (SAR) images, the rotated bounding box (RBB) has received wider attention in recent years. First, the existing RBB encodings suffer from boundary discontinuity problems, which interfere with the convergence of the model, and then lead to some problems, such as the inaccurate location of the ship targets in the boundary state. Thus, from the perspective that the long-edge features of the ships are more representative of their orientation, the long-edge decomposition RBB encoding has been proposed in this paper, which can avoid the boundary discontinuity problem. Second, the problem of the positive and negative samples imbalance is serious for the SAR ship images because only a few ship targets exist in the vast background of these images. Since the ship targets of different sizes are subject to varying degrees of interference caused by this problem, a multiscale elliptical Gaussian sample balancing strategy has been proposed in this paper, which can mitigate the impact of this problem by labeling the loss weights of the negative samples within the target foreground area with multiscale elliptical Gaussian kernels. Finally, experiments based on the CenterNet model were implemented on the benchmark SAR image dataset SSDD (SAR ship detection dataset). The experimental results demonstrate that our proposed long-edge decomposition RBB encoding outperforms other conventional RBB encodings in the task of oriented ship detection in SAR images. In addition, our proposed multiscale elliptical Gaussian sample balancing strategy is effective and can improve the model performance.

P-band ultra-wideband bistatic synthetic aperture radar (UWB BSAR) has the well capability of the foliage penetrating, high-resolution imaging and adding the scattered information, which is potential of detecting the concealed target. However, the P-band UWB BSAR raw data is of the huge amount, big spatial-variance, significant range azimuth coupling and complicated motion error, which increases the difficulty of the efficient and precise reconstruction. In this paper, we propose a reconstruction strategy for the P-band UWB BSAR raw data including the motion errors, which can solve the above problems with the high-efficiency and high-precision. This method requires the local beamforming from the raw data as an intermediate processing in the slant range plane instead of ground plane, which can be exactly referenced to the tracks of the transmitter and receiver considering platform altitudes. And, it derives the requirement for selecting the subapertures and subimages by analyzing the bistatic range error considering the motion errors, as well as sampling requirement of the beam for the subimages, which offers a near-optimum tradeoff between the precision and efficiency. Simulated and measured results show that the proposed strategy is effective, and can achieve the near optimal performance with the low computational complexity.

The video synthetic aperture radar (VideoSAR) has the high frame-rate imaging capability, which can perform the ground moving target detection. The moving target often leaves the shadow in the sequence of the VideoSAR images, which can indirectly detect the moving target by detecting its shadow. In view of the high false alarm rate and high missed detection rate of existing algorithms, this paper proposes a moving target shadow detection method based on the improved ViBe in the VideoSAR images. Firstly, the shadow information and local contrast information of the VideoSAR image are extracted by using the super-pixel segmentation technology, which can achieve the background reconstruction. Besides, the ViBe algorithm is improved by modifying the definition of the distance in the image pixel classification, adding the image pixel screening, and performing the morphological filtering, which is more suitable for the moving target shadow detection in VideoSAR images. Finally, by jointly extracting the regions of interest from multiple frames' detection results, most of the false alarms are suppressed, which can obtain the excellent performance in detecting the moving target shadow. The experimental results tested on the VideoSAR data released by the Sandia National Laboratories are shown to validate the correctness and effectiveness of the proposed algorithm, for which the detection rate of moving target shadows reached 97.66%, with only 8 false alarms.

Due to the inherent characteristics of synthetic aperture radar (SAR) imaging, SAR ship features are not obvious and the category distribution is unbalanced, which makes the task of ship recognition in SAR images quite challenging. To address the above problems, a two-level feature-fusion ship recognition strategy combining the histogram of oriented gradients (HOG) features with the dual-polarized data in the SAR images is proposed. The proposed strategy comprehensively utilizes the features extracted by the HOG operator and the shallow and deep features extracted by the Siamese network in the dual-polarized SAR ship images, which can increase the amount of information for the model learning. First, the Siamese network is used to extract the shallow and deep features from the dual-polarized SAR images, and then the HOG feature of the dual-polarized SAR images is also extracted. Furthermore, the bilinear transformation layer is used for fusing the HOG features from dual-polarized SAR images, and the grouping bilinear pooling process is used for fusing the dual-polarized shallow feature and deep feature extracted by the Siamese network, respectively. Finally, the catenation operation is used for fusing the dual-polarized HOG features and dual-polarized shallow feature and deep feature, respectively, which are used for the recognition of the SAR ship targets. Experimental results tested on the OpenSARShip2.0 dataset demonstrate the correctness and effectiveness of the proposed strategy, which can effectively improve the recognition performance of the ship targets by fusing the different level features of the dual-polarized SAR images.