Recently, many researchers have been dedicated to using convolutional neural networks (CNNs) to extract global-context features (GCFs) for remote-sensing scene classification. Commonly, accurate classification of scenes requires knowledge about both the global context and local objects. However, unlike the natural images in which the objects cover most of the image, objects in remote-sensing images are generally small and decentralized. Thus, it is hard for vanilla CNNs to focus on both global context and small local objects. To address this issue, this paper proposes a novel end-to-end CNN by integrating the GCFs and local-object-level features (LOFs). The proposed network includes two branches, the local object branch (LOB) and global semantic branch (GSB), which are used to generate the LOFs and GCFs, respectively. Then, the concatenation of features extracted from the two branches allows our method to be more discriminative in scene classification. Three challenging benchmark remote-sensing datasets were extensively experimented on; the proposed approach outperformed the existing scene classification methods and achieved state-of-the-art results for all three datasets.

Advanced Geostationary Radiation Imager (AGRI) is one of the main payloads of the 2nd generation geostationary orbit meteorological satellite FengYun-4A. Typically, the existence of variable stripe noise in the water vapor band remote sensing images of the AGRI greatly affects many applications such as cloud detection, especially as one full disk image is separated into 10 sub-images for transforming as soon as possible, so the denoising algorithm which can reduce variable stripe noise and is adaptive to process using sub-images must be built. In this paper, we propose an adaptive wavelet filter for image denoising. This approach introduces a new parameter termed Weight Sum Variance of Digital Number Probability (WSVODP), which is used to indicate the appropriate wavelet filter coefficients. WSVODP is only sensitive to the difference of observation targets of different sensors. Thus, our approach can learn appropriate wavelet filter coefficients fast and exactly. We built a real-world remote sensing image dataset from AGRI on FengYun-4A and the experimental results on this dataset show that the proposed approach could effectively reduce the variable stripe noise from different observation targets. At the same time, an edge compensation method which is fitted to the scanning model of AGRI is suggested to avoid ringing artifacts. Many applications, such as cloud detection with denoised images, show very good results. The proposed approach reduces the stripe noise adaptation, so the result is very steady even if the stripe noise varies with different targets, and edge compensation ensures that there are no obvious ringing artifacts in the full disk image joined by the 10 sub-images.

For geostationary meteorological satellite (GSMS) remote sensing image registration, high computational cost and matching error are the two main challenging problems. To address these issues, this paper proposes a novel algorithm named slope-restricted multi-scale feature matching. In multi-scale feature matching, images are subsampled to different scales. From a small scale to a large scale, the offsets between the matched pairs are used to narrow the searching area of feature matching for the next larger scale. Thus, the feature matching is accomplished from coarse to fine, which will make the matching process more accurate and reduce errors. To enhance the matching performance, the outliers in the matched pairs are rectified by using slope-restricted rectification, which is based on local geometric similarity. Compared with other algorithms, the experimental results show that our proposed method is more accurate and efficient.

Radiometric Calibration (RC) is a critical process in aerospace infrared remote sensing that establishes the relationship between the radiation energy of observed objects and the Digital Number (DN) output from sensors, which is fundamental for ensuring high-precision applications of infrared remote sensing data. At present, Source-Based RC (SBRC) is the predominant method, relying on a variety of Radiometric Sources (RS) including in-orbit blackbodies, or natural targets such as lakes, oceans. This approach, while effective, imposes constraints on remote sensing systems such as space & weight allocation for RS and additional observation time for RC. Moreover, the reliance on physical calibration sources can introduce uncertainties due to factors such as imperfect emissivity of in-orbit blackbodies, lack of data consistency due to varied RS types, and variations in environmental conditions. In this paper, we propose a novel RC method named Artificial Intelligence Radiometric Calibration (AIRC), which directly generates RC coefficients for the in-orbit remote sensing satellites using the physical and environmental parameters of the sensor. We first theoretically prove that RC coefficients can be derived as functions of the sensor states. Next, we propose our Neural Networks for infrared Radiometric Calibration (RCNN), to learn this relationship based on historical high-accuracy calibration data, enabling a shift from Reference Traceability (RT) to States Traceability (ST). Then, to verify the feasibility of the proposed scheme, we train and test an Multi-layered Perceptron (MLP) as a simple implementation of RCNN based on our long-term well-curated RC data from our FengYun-4A Avanced Geosynchronous Radiation Imager (FY-4A AGRI), and the experiments show that the proposed method achieves high-accuracy RC comparable with the official RC method applied on FY-4A AGRI that uses an in-orbit blackbody. Our study showcases how to conduct RC using the “reason (the states of sensor) - results (calibration coefficient)” logic, as supplement to the existing “result (observation to RS) - reason (calibration coefficient)” logic, which promotes constituting a uniform observing system for cross-platform infrared satellites.

In magnetic resonance imaging (MRI), low-resolution (LR) images often hamper clinical diagnosis and research due to constraints in imaging conditions and technology limitations. Recent studies in super-resolution (SR) reconstruction of multi-contrast MRI have shown promise by leveraging the complementary information from different MRI contrasts. However, existing multi-contrast MRI SR techniques face several challenges: 1) a lack of pre-alignment precision can result in distorted reconstructions; 2) prevailing transformer network structures, with their smaller windows (e.g., 8×8), struggle to effectively capture long-range dependencies and lack the ability to interact between different windows; and 3) current methods are limited to fixed integer scaling (e.g., 2×, 3×, 4×), which limits flexibility and increases complexity in training and storage. To address these challenges, we propose a novel arbitrary-scale SR network for multi-contrast MRI. Specifically, our approach compensates for spatial misalignment between modalities through deformable registration module and employs permuted cross-attention transformer in MR images. In addition, we introduce a ref-scale ensemble implicit attention module that better integrates high-frequency information from reference images and enables arbitrary-scale upsampling. Extensive experiments on two publicly available MRI datasets validate the superiority of our method in multi-contrast MRI SR, demonstrating its significant potential in clinical applications. Our code is available at https://github.com/fangxiaojia0/An-Arbitrary-Scale-Super-Resolution-Network-for-Multi-Contrast-MRI-With-Permuted-Cross-Attention.