To address the limitations of hyperspectral imaging systems, super-resolution (SR) techniques that fuse low-resolution hyperspectral image (HSI) with high-resolution multispectral image (MSI) are applied. Due to the significant modal difference between HSI and MSI, and the insufficient consideration of HSI band correlation in previous works, issues arise such as spectral distortions and loss of fine texture and boundaries. In this article, an unsupervised spectral correlation-based fusion network (SCFN) is proposed to address the above challenges. A new dense spectral convolution module (DSCM) is proposed to capture the intrinsic similarity dependence between spectral bands in HSI to effectively extract spectral domain features and mitigate spectral aberrations. To preserve the rich texture details in MSI, a global-local aware block (GAB) is designed for joint global contextual information and emphasize critical regions. To address the cross-modal disparity problem, new joint losses are constructed to improve the preservation of high-frequency information during image reconstruction and effectively minimize spectral disparity for more precise and accurate image reconstruction. The experimental results on three hyperspectral remote sensing datasets demonstrate that SCFN outperforms other methods in both qualitative and quantitative comparisons. Results from the fusion of real hyperspectral and multispectral remote sensing data further confirm the applicability and effectiveness of the proposed network.

High-resolution remote sensing images (HRRSIs) play an important role in large area and real-time earth observation tasks. However, HRRSIs typically comprise heterogeneous objects of various sizes and complex boundary lines, which pose challenges to HRRSI segmentation. Despite the fact that deep convolutional neural networks dramatically boosted the accuracy, several limitations exist in standard models. Existing methods, mainly concatenate multiscale information to extract the various sizes of objects. However, these methods ignore differentiating information, making it difficult to take advantage of them and completely extract small objects. In addition, there have remained some difficulties in extracting boundary information with positions of uncertainty in previous works. In this article, we propose a novel multiscale feature weighted-aggregating and boundary enhancement network (MFBE-Net) for the segmentation of HRRSIs. ResNet-50, possessing a strong ability to extract features, is employed as the backbone. To fully utilize the information that was extracted, we propose a multiscale feature weighted-aggregating module, which aims to weight-integrate deep features, shallow features, and global information. The boundary enhancement module is designed to solve the blurry boundary information problems and locate its positions. Coordinate attention is also applied in the framework to coherently label size-varied ground objects from different categories and reduce information redundancy. Meanwhile, a mixed loss function is used to supervise the network training process. Finally, MFBE-Net was verified on two public HRRSI datasets, and the experimental results show that the proposed framework outperformed other existing mainstream deep learning methods and could further improve the accuracy of HRRSI segmentation.

Tailings ponds are a significant source of environmental pollution and present potential danger, making it a top priority to obtain accurate location information. Traditional object-based remote sensing techniques suffer from low efficiency and lack of automation. Furthermore, deep learning research on tailings ponds lacks practical models and datasets. To address these gaps, this letter proposes a novel approach - Multi-scale Feature Fusion and Threshold-based Attentional YOLO (MFTA-YOLO) for detecting tailings ponds in remote sensing images. Specifically, CSPDarknet53 is used as the feature extractor in MFTA-YOLO, and it combines the Multi-scale Feature Fusion Module (MF) and a new attention mechanism Threshold-based Attention (TA). MF effectively integrates multi-scale semantic features to detect varying sizes of objects. TA recalibrates input contributions based on the threshold gap, allowing better focus on regions and channels of interest. Additionally, a large-scale tailings ponds dataset, consisting of 3619 high-resolution (1.07m) maps sourced from Google Earth, has been constructed. Extensive experiments on this dataset have demonstrated that MFTA-YOLO outperforms most existing methods for tailings pond detection in remote sensing images, achieving an F1-score of 0.799 and AP@.5 of 0.851.