High-resolution (HR) remote sensing images have important applications in many scenarios, and improving the resolution of remote sensing images via algorithms is one of the key research fields. However, current super-resolution (SR) algorithms, which are trained on synthetic datasets, tend to have poor performance in real-world low-resolution (LR) images. Moreover, due to the inherent complexity of real-world remote sensing images, current models are prone to color distortion, blurred edges, and unrealistic artifacts. To address these issues, real-SR datasets using the Gao Fen (GF) satellite images at different spatial resolutions have been established to simulate real degradation situations; moreover, a second-order attention generator adversarial attention network (SA-GAN) model based on real-world remote sensing images is proposed to implement the SR task. In the generator network, a second-order channel attention mechanism and a region-level non-local module are used to fully utilize the a priori information in low-resolution (LR) images, as well as adopting region-aware loss to suppress artifact generation. Experiments on test data demonstrate that the model delivers good performance for quantitative metrics, and the visual quality outperforms that of previous approaches. The Frechet inception distance score (FID) and the learned perceptual image patch similarity (LPIPS) value using the proposed method are improved by 17.67% and 6.61%, respectively. Migration experiments in real scenarios also demonstrate the effectiveness and robustness of the method.
Researchers have explored various methods to fully exploit the all-weather characteristics of Synthetic aperture radar (SAR) images to achieve high-precision, real-time, computationally efficient, and easily deployable ship target detection models. These methods include Constant False Alarm Rate (CFAR) algorithms and deep learning approaches such as RCNN, YOLO, and SSD, among others. While these methods outperform traditional algorithms in SAR ship detection, challenges still exist in handling the arbitrary ship distributions and small target features in SAR remote sensing images. Existing models are complex, with a large number of parameters, hindering effective deployment. This paper introduces a YOLOv7 oriented bounding box SAR ship detection model (YOLOv7oSAR). The model employs a rotation box detection mechanism, uses the KLD loss function to enhance accuracy, and introduces a Bi-former attention mechanism to improve small target detection. By redesigning the network’s width and depth and incorporating a lightweight P-ELAN structure, the model effectively reduces its size and computational requirements. The proposed model achieves high-precision detection results on the public RSDD dataset (94.8% offshore, 66.6% nearshore), and its generalization ability is validated on a custom dataset (94.2% overall detection accuracy).
As clean, renewable energy, photovoltaic (PV) energy can reduce the ozone-layer loss and climate deterioration caused by the use of traditional types of energy to generate electricity. At present, most PV energy products involve the influence of cloud cover on solar radiation. However, the resolution and precision of most cloud cover data are not fine enough to reflect the actual cloud distribution in local areas. This leads to incorrect distribution results of PV energy in areas with high-spatial-variability clouds. Using high-resolution and high-precision cloud cover data obtained by satellite remote sensing to estimate the distribution of PV energy can solve this problem. In this study, the Global Land High-Resolution Cloud Climatology (GLHCC), a 10-day cloud frequency product with a resolution of 1 km and located in China, was used to construct a cloud-based solar radiation estimation model. Using the inverse relationship between cloud cover and solar radiation, the GLHCC was converted into sunshine percentage data. Using meteorological station data in China, a Least Squares Fit (LSF) and error check were carried out on the A-P, Lqbal, Bahel and Sen Models to determine the optimal solar radiation estimation model (Sen Model). Based on the sunshine percentage data, the Sen Model and terrain shielding factors, the distribution of PV energy in China was estimated. Finally, comparing to the Global Horizontal Irradiance (GHI) of the World Bank and the yearly average global irradiance of the Photovoltaic Geographic Information System (PVGIS), PV energy data in this paper more accurately reflected the distribution of PV energy in China, especially in areas with high-spatial-variability clouds.
The sea ice cover is changing rapidly in polar regions, and sea ice products with high temporal and spatial resolution are of great importance in studying global climate change and navigation. In this paper, an ice map generation model based on Moderate-Resolution Imaging Spectroradiometer (MODIS) reflectance bands is constructed to obtain sea ice data with a high temporal and spatial resolution. By constructing a training sample library and using a multi-feature fusion machine learning algorithm for model classification, the high-accuracy recognition of ice and cloud regions is achieved. The first product provided by this algorithm is a near real-time single-scene sea ice presence map. Compared with the photo-interpreted ground truth, the verification shows that the algorithm can obtain a higher recognition accuracy for ice, clouds, and water, and the accuracy exceeds 98%. The second product is a daily and weekly clear sky map, which provides synthetic ice presence maps for one day or seven consecutive days. A filtering method based on cloud motion is used to make the product more accurate. The third product is a weekly fusion of clear sky optical images. In a comparison with the Advanced Microwave Scanning Radiometer 2 (AMSR2) sea ice concentration products performed in August 2019 and September 2020, these composite images showed spatial consistency over time, suggesting that they can be used in many scientific and practical applications in the future.
In the field of SAR-to-optical image synthesis, current methods based on conditional generative adversarial networks (CGANs) have satisfying performance under simple scenarios, but the performance drops severely under complicated scenarios. Considering that SAR images can form a robust time series due to SAR’s all-weather imaging ability, we take advantage of this and extract a temporal correlation from bi-temporal SAR images to guide the translation. To achieve this, we introduce a co-attention mechanism into the CGAN that learns the correlation between optically-available and optically-absent time points, selectively enhances the features of the former time point, and eventually guides the model to a better optical image synthesis on the latter time point. Additionally, we adopt a strategy to balance the weight of optical and SAR features to extract better features from the SAR input. With these strategies, the quality of synthesized images is notably improved in complicated scenarios. The synthesized images can increase the spatial and temporal resolution of optical imagery, greatly improving the availability of data for the applications of crop monitoring, change detection, and visual interpretation.