Cloud removal is essential for improving the quality of optical remote sensing images in various downstream applications. Leveraging auxiliary synthetic aperture radar (SAR) data with cloud penetrating ability can accurately reconstruct details obscured by thick cloud cover. However, the presence of complex cloud types in optical images hampers the effective use of the similar geometrical characteristics shared with SAR images, resulting in spectral distortion and fuzzy textures. In this paper, we propose a similarity-guided fusion SAR-assisted cloud removal network. The unidirectional multimodal fusion module effectively utilizes similarity to recover structures and fill in spectral information. Additionally, the bidirectional multiscale reconstruction module refines and aggregates these multiscale intermediate reconstruction results in terms of semantic guidance and detail preservation. The experimental results on the SEN12MS-CR and GF23-CR datasets demonstrate that our method achieves superior quantitative and visual reconstruction. The source code is available at https://github.com/phaeton2017/SGFCR.

In recent years, the fusion-based classification of hyperspectral image (HSI) and light detection and ranging (LiDAR) data has garnered increasing attention from researchers. However, significant image disparities exist between HSI and LiDAR data because of their distinct imaging mechanisms, which limits the fusion of HSI and LiDAR data. Therefore, establishing effective interaction (INTER) and fusion between HSI and LiDAR data is crucial. Moreover, the classification of multimodal data with limited labeled instances is another challenging task. To address these issues, we propose a contrastive learning enhanced adaptive multimodal fusion network (CAMFNet) for the joint classification of HSI and LiDAR data. CAMFNet introduces a novel semantic similarity contrastive (SSC) loss that fully utilizes a large amount of unlabeled data to learn potential complementary information between different modalities. In addition, a hierarchical fusion strategy is adopted to fuse multimodal features. At the shallow feature fusion stage, a cross-modal feature interaction fusion (CMFIF) module is proposed to guide the extraction of multimodal features and enhance the complementary information through cross-modal interaction. At the same time, adaptive feature fusion is also used to dynamically assign corresponding weights to different modal features, achieving finer fusion. At the deep feature fusion stage, a channel split and integration (CSI) block is constructed to further optimize the fused spectral-spatial and elevation features via a negative feedback mechanism. The effectiveness of CAMFNet is validated through experiments on three standard datasets, which demonstrates that CAMFNet outperforms state-of-the-art methods.

Leveraging synthetic aperture radar (SAR) data to assist in cloud removal demonstrates promising potential and has achieved satisfactory results in restoring clear contours of images. However, there are three critical challenges: inherent geometric discrepancies between SAR and optical images complicate cross-modal correlation modeling; modality-specific noises lead to radiometric inconsistency and texture loss in cross-modal information aggregation; diverse clouds and complex scenes impede the attainment of both detailed inpainting and global consistency. Therefore, we propose a novel network integrating supervised alignment perception strategy (SAPS) and modality difference selection module (MDSM) to enhance SAR-optical fusion for cloud removal. Specifically, the SAPS consists of supervised training and an alignment perception module to address spatial misalignments and enhance the stability of deviation perception. Then, the MDSM dynamically focuses on different regions and eliminates modality-specific noise through mutual dynamic guidance. Furthermore, the locality-enhanced Mamba module in reconstruction optimization enhances the consistency of the overall reconstruction results and the expressiveness of local details. Experiments conducted on the SEN12MS-CR, LuojiaSET-OSFCR, and simulated WHU-OPT-SAR datasets assess reconstruction performance from multiple perspectives. The proposed method not only achieves superiority in basic quantitative and qualitative validation, but also demonstrates advantages in reconstruction under different cloud coverage levels and across various terrains.

Multisource unsupervised domain adaptation (MUDA) has demonstrated its effectiveness in improving model performance for remote sensing (RS) scene classification, particularly in cases where the target-domain lacks labeled data. However, most current methods based on convolutional neural networks (CNNs) or Transformers fail to fully exploit the features within each source domain, which benefits classification accuracy. Additionally, these methods frequently overlook the varying levels of similarity between domains, limiting the potential of MUDA. To alleviate this limitation, we propose Hy-MSDA, a hybrid CNN-Transformer with consistent learning and dynamic weighting for MUDA, which fully explores and utilizes valuable information from multiple sources at both the feature and decision levels. To achieve a better alignment of categories among domains, the consistency learning module aims to learn domain-invariant features, maintaining consistency in global high-level features and rich semantic information at the feature level. At the decision level, the dynamic weighting strategy balances the contribution of each source domain by considering their varying importance levels. These two components are closely interconnected and mutually reinforce each other, resulting in improved cross-domain collaboration of Hy-MSDA for domain adaptation. Experimental results on the RS classification datasets clearly demonstrate that Hy-MSDA outperforms the state-of-the-art methods, achieving a significant enhancement of 2%–7% in classification accuracy. Moreover, experiments on RS segmentation datasets reveal that Hy-MSDA performs comparably to supervised methods, further validating the effectiveness of Hy-MSDA in segmentation tasks. The source code is available athttps://github.com/phaeton2017/Hy-MSDA.

Significant progress has been achieved in cloud detection using deep convolutional neural networks, leading to a substantial increase in detection accuracy. However, discriminating between actual clouds and cloud-like objects, as well as accurately identifying thin clouds and cloud boundaries, have been persistent challenges in the cloud detection. To address these issues, an Integration Transformer with gradient-aware feature aggregation (TransGA-Net) is proposed in this paper. This framework employs Transformers as encoders, significantly enhancing the modeling capabilities for global features and long-term dependencies. Additionally, a novel Gradient-Aware Feature Aggregation Module is proposed, focused on gradient variations within cloud boundary regions and utilizing gradient information to guide feature aggregation. The performance of TransGA-Net is validated on Landsat-8, GF-2, and Sentinel-2 datasets. In general, experiments show TransGA-Net surpasses the highest performance achieved by the other methods by 0.6%, 1.3%, and 0.7% in OA on the three datasets respectively, demonstrating that proposed method are particularly effective in identifying areas with thin cloud cover and distinguishing between clouds and cloud-like objects. The source code is available at https://github.com/phaeton2017/transga-net.

Synthetic aperture radar (SAR) has evolved into an essential Earth observation technique. Geometric quality is one of its most fundamental elements to ensure subsequent applications. Excellent localization accuracy requires comprehensive error compensation and calibration. While traditional calibration work is time-consuming and depends on the test sites. Besides, the available calibration test sites are scarce and unevenly distributed for certain SAR satellites. It is, hence, necessary to research how to make geometric calibration without ground control points (GCPs) for SAR. This study proposes a method utilizing the constraints of symmetric geometry that could cancel out plane error symmetrically, and then calculates calibration constants combined with external DEM. Experiments demonstrate the calibration accuracy of the proposed way is approximately 0.3 m along range direction when all constraints are met, and the discrepancy between the proposed method and that using GCPs are analyzed. Generally, the method can achieve fast, labor-saving, and normalized calibration work for SAR images in the absence of available control data.

High-resolution synthetic aperture radar (SAR) satellites have become an important way to observe the earth. However, the geometric positioning accuracy of SAR satellite images across different times and spaces is an important factor affecting the realization of global remote sensing applications. In this study, a multimode hybrid geometric calibration method that incorporates an atmospheric propagation delay correction and that can be used to detect systematic errors affecting the geometric positioning accuracy of SAR satellites is described. The spatiotemporal variation reasons of geometric positioning error sources for spaceborne SAR are then analyzed. Finally, the stability of geometric positioning accuracy is evaluated using the described method on data extracted from Yaogan-13 (YG-13) SAR satellite images with long time series and multiple test areas in China. The results reveal that during the study period (2015–2017), the geometric positioning accuracy of the YG-13 SAR system was relatively stable and is better than 3 m regardless of the spatial distribution, after removal of systematic pulse-dependent slant range errors and atmospheric correction. Furthermore, the validation results provide a reference for the design of SAR satellite systems, the establishment of calibration periods, and quantitative remote sensing application.

The high-precision geometric positioning of satellite images is the basis for the geometric processing of remote-sensing images and acquisition of various geospatial information. It is an important premise for the wide application of high-resolution remote-sensing satellite images. To correct systematic biases in rational function models (RFMs), many compensation methods for system errors inherent of RFMs have been proposed. Thus far, the bias compensation model (BCM) is the most widely accepted method under rigorous conditions, namely narrow camera field, small off-nadir angle, and small attitude error. However, research studies on the compensation effect of the BCM under weak conditions (wide camera field, large off-nadir angle, or large attitude error) are still lacking, and some researchers commented that the BCM is inapplicable under weak conditions in the absence of experiments. This letter analyzes the effect of position and attitude errors on orientation accuracy in the image space. An experiment was conducted using data from the Gaofen-1 (GF-1) wide-field-view-4 (WFV-4) sensor to compare the proposed analysis with the traditional analysis, and the results obtained using the BCM under weak conditions were found to be consistent with our analysis rather than the traditional analysis. This confirms that the BCM can also be used under weak conditions.

This article proposes a novel fusing filter algorithm based on a surface variation anisotropic diffusion (SVAD) filter and a ratio image filter to achieve good speckle reduction and edge preservation. The proposed algorithm can be divided into three steps. First, the proposed SVAD filter effectively calculates the diffusion coefficient of each pixel to obtain filtering results on different scales. Second, the proposed ratio image filter obtains a new denoising result that can effectively recover some details lost with the SVAD filter. Then, the two filtering results are fused to obtain the final despeckling result. Furthermore, the effects of the weighting coefficients of the fusion processing and the number of iterations of the ratio image filter on the final filtering results are analyzed. The proposed algorithm is effectively evaluated by conducting some experiments on the added noise image and real synthetic aperture radar (SAR) images. The experimental results confirm that the proposed method can not only significantly reduce speckle but also effectively preserve the edge information of images.