Synthetic aperture radar (SAR) images suffer from speckle noise due to their imaging mechanism, which deteriorates image interpretability and hinders subsequent tasks like target detection and recognition. Traditional denoising methods fall short of the demands for high-quality SAR image processing, and deep learning approaches trained on synthetic datasets exhibit poor generalization because noise-free real SAR images are unattainable. To solve this problem and improve the quality of SAR images, a speckle noise suppression method based on subaperture decomposition and non-local low-rank tensor approximation is proposed. Subaperture decomposition yields azimuth-frame subimages with high global structural similarity, which are modeled as low-rank and formed into a 3D tensor. The tensor is decomposed to derive a low-dimensional orthogonal basis and low-rank representation, followed by non-local denoising and iterative regularization in the low-rank subspace for data reconstruction. Experiments on simulated and real SAR images demonstrate that the proposed method outperforms state-of-the-art techniques in speckle suppression, significantly improving SAR image quality.

The ScanSAR mode can change the antenna angle during operation and obtain a wide swath by scanning multiple strips at one time. However, due to discontinuous working in azimuth, the scalloping effect in ScanSAR will degrade the image quality. In this paper, a novel adaptive scalloping suppression method is proposed by analyzing the complex scene as well as the scalloping distribution. First, the images of the various types of scenes are pre-processed so that the distribution of sub-images satisfies the Kalman filter conditions. Then, the problem of space-variant property is solved by performing adaptive blocking in the range direction. Finally, the Kalman filtering algorithm is introduced to process the scalloping in each sub-block separately, and the processed sub-blocks are fused to obtain the final result. The proposed method is verified by the real ScanSAR images of GF-3. Experimental results show that the proposed method is more efficient for scalloping suppression than the existing ones for both general and complex scenes, and has clear improvement for large-scale images with strong scalloping, which fully verifies the robustness and adaptability of the proposed method.

High-resolution space-borne synthetic aperture radar (SAR) images are important sources of information for marine monitoring and target recognition. For inshore port scenes, there is a wide variety of ship targets; moreover, as the scattering intensity of the land background is much higher than that of the sea surface, similar structures on land in SAR images can cause significant interference to the identification of ship targets, resulting in a high false alarm rate and false recognition rate. Therefore, the classification of ship targets in SAR images still requires professional interpretation and correction to eliminate possible false alarms and recognitions. In this paper, by imitating the basic structural requirements for manual discrimination of target categories, a space-borne SAR high-resolution inshore ship classification and correction method of “Pre-recognition – Fine Recognition – Matching Correction” is designed based on the YOLO recognition network. Taking three types of typical ship targets as examples, a high-resolution SAR inshore ship target dataset and a high-resolution SAR ship component architecture dataset are constructed to train the pre-recognition network and the fine recognition network respectively. The latter is based on the former to recognize the component composition of possible targets, and forms a component arrangement architecture vector. The final recognition results are obtained by matching and correcting the similarity distance with the three types of targets. This method can reduce the false alarm rate in ship target recognition in complex inshore port scenes to less than 10% and correct some false recognition results, thereby improving the accuracy of ship target identification and reducing the cost for manual correction.

Due to a wide swath at the order of hundreds of kilometres, inter-scan banding (ISB) may occur in both ScanSAR and TOPS modes of a Synthetic Aperture Radar (SAR), leading to degraded image quality. In this paper, the causes of ISB are analyzed and an ISB suppression method based on Retinex theory and global weighting is proposed. Firstly, the image with ISB is considered as an image with uneven lighting, and ISB is considered as a lighting component. The ISB component is calculated using a global weighting method. Based on previous studies, the coupling relationship between ISB and scalloping (another issue commonly found in ScanSAR) is identified, and a joint procedure for suppressing ISB and scalloping is established. The proposed method is a post-processing technique that does not require any other additional information such as the noise equivalent sigma zero (NESZ). Experimental results based on real SAR images from Gaofen-3 (GF-3) and Sentinel-1 indicate that the proposed method can significantly reduce the effect of ISB and improve the image quality, and it is more efficient and robust compared to existing methods.

Synthetic aperture radar (SAR) products are mostly presented as grayscale images, where the scattering characteristics of ground objects lack intuitive visualization, limiting the performance of downstream interpretation tasks. To address this issue, this paper proposes AnisoColSAR, a physics-informed SAR image colorization method. Based on the physical scattering mechanism of ground objects, AnisoColSAR takes the scattering anisotropy index (SAI) as a proxy for physical anisotropy. By quantifying and encoding the SAI into color features, it generates pseudo-color images with explicit physical significance without full-polarization or multi-source auxiliary data. Experiments on the AIR-PolSAR-Seg-2.0 dataset demonstrate that the proposed pseudo-color images stably improve semantic segmentation performance across all polarization modes (HH, VV, HV, VH), with particularly significant gains in cross-polarization modes. This study provides a novel physics-guided approach for SAR image interpretation, and the generated pseudo-color images are promising for various remote sensing tasks such as classification and detection, showing strong practical value.

One-bit quantization technology effectively simplifies the hardware architecture of synthetic aperture radar (SAR) and significantly reduces the volume of echo data, making it a pivotal research direction in spaceborne SAR systems. However, the high computational cost and latency associated with one-bit SAR signal reconstruction have limited the efficiency of downstream target detection applications. To address the demand for efficient ship target detection in one-bit SAR imagery, a label self-supervised ship detection training method on one-bit non-reconstructed SAR images is proposed in this paper, which enables generic deep learning models to perform detection directly in one-bit SAR images based on the chirp scaling algorithm (CSA) without signal recovery during inference. First, a training framework based on curriculum learning is designed, aiming to discriminate between real ship targets and false targets. Second, a one-bit reconstruction and training label self-supervised correction branch is incorporated into the training framework to autonomously generate false target labels and progressively guide the model to learn false target features. Third, a one-bit non-reconstructed image dataset is proposed to validate the trained model, which maps only reliable ship target annotations from full-precision echo imaging results. Finally, experiments conducted on real SAR data demonstrate that the detection model derived from the proposed training method can directly detect ship targets in the non-reconstructed images. Compared with the classic “reconstruction-and-detection” workflow, the trained model runs inference, bypassing the reconstruction process, and achieves a 20-fold improvement in efficiency without compromising detection accuracy. This method provides a practical solution for the rapid acquisition of target information in large-scale ship monitoring using one-bit SAR.