Search

Thick clouds reduce the useful information in visible remote sensing and restrict the usefulness of remote sensing images. Many scholars have proposed time-based strategies to solve these restrictions. However, these approaches still suffered from difficulties, such as requiring paired cloud mask pictures as additional auxiliary images, having artefacts or image distortions, and model training difffculties. For thick clouds in multitemporal remote sensing, this research offers an implicit multitemporal remote sensing thick cloud removal network (IRNet). As the name suggests, IRNet does not need cloud masks as external auxiliary data inputs to the network. To attenuate the temporal difference problem between multitemporal remote sensing images with model training difffculties, multiscale feature extraction block (MFEB) is designed in IRNet. In addition, the designed upsampling and convolution blocks are utilized in the designed high-fidelity reconstruction block (HFRB) to reconstruct the missing information under the cloud to generate highly preserved cloud-free images. By utilizing two readily datasets for removing multitemporal thick clouds, we have evaluated our method against the most effective existing techniques. Our findings consistently demonstrate that our method improves the restoration of texture detail and spatial information. [ABSTRACT FROM AUTHOR] more...

To address the challenge of image matching posed by significant modal differences in remote sensing images influenced by snow cover, this paper proposes an innovative image transformation-based matching method. Initially, the Pix2Pix-GAN conversion network is employed to transform remote sensing images with snow cover into images without snow cover, reducing the feature disparity between the images. This conversion facilitates the extraction of more discernible features for matching by transforming the problem from snow-covered to snow-free images. Subsequently, a multi-level feature extraction network is utilized to extract multi-level feature descriptors from the transformed images. Keypoints are derived from these descriptors, enabling effective feature matching. Finally, the matching results are mapped back onto the original snow-covered remote sensing images. The proposed method was compared to well-established techniques such as SIFT, RIFT2, R2D2, and ReDFeat and demonstrated outstanding performance. In terms of NCM, MP, Rep, Recall, and F1-measure, our method outperformed the state of the art by 177, 0.29, 0.22, 0.21, and 0.25, respectively. In addition, the algorithm shows robustness over a range of image rotation angles from −40° to 40°. This innovative approach offers a new perspective on the task of matching multi-temporal snow-covered remote sensing images. [ABSTRACT FROM AUTHOR] more...

Spatial injection-based pansharpening methods are prone to spatial or spectral distortions in pansharpening images due to insufficient extraction of spatial details and a mismatch between the amount of spatial detail information injected and the required amount. To this end, this paper proposes a pansharpening method that optimizes spatial detail extraction and injection. Firstly, a method to optimize the amount of spatial detail injection is proposed, that is, to extract the high-frequency information of the image through iterative filtering and determine the optimal number of iterations based on the global analysis of the method. Then, to fully extract and combine the spatial detail information of the source image, the detailed high-frequency image extracted corresponding to the optimal iterative filtering times is decomposed by non-subsampled shearlet transform (NSST), and a new multi-scale sum-modified-Laplacian (NSML) as an external stimulus to a parameter-adaptive pulse-coupled neural network model (PAPCNN). A fusion rule based on multi-scale morphological gradients is designed to extract a small amount of detailed information for the low-frequency subband. The fused spatial detail image can be obtained by combining the fused low-frequency and high-frequency subbands and inverse NSST transformation. Finally, pansharpening can be realized by combining spatial detail image, injection coefficient, and MS image. In this paper, many experiments are carried out on the QuickBird, GeoEye-1, and WorldView-4 datasets, and quantitative and qualitative comparisons are made with eight advanced methods. Experimental results show that the method proposed in this paper can achieve better fusion results. [ABSTRACT FROM AUTHOR] more...

The pansharpening method based on spatial injection is prone to spectral distortion due to the spatial detail injection amount mismatch. For this reason, this paper proposes a method that combines adaptive intensity component extraction and spatial detail injection optimisation. Firstly, a new method for extracting the I component of multispectral (MS) image is proposed, which decomposes each band of MS image and panchromatic (PAN) image according to the structure-energy mechanism through the joint bilateral filter and then determines the weight coefficient of each band of MS image to extract the I component by solving the minimum optimisation problem of the structure layer of PAN image and the energy layer of MS image. Secondly, a spatial detail extraction method combining local spatial frequency and local energy is proposed, and the method can fully extract the fine detail features of PAN images and MS images. In this paper, many experiments are conducted on QuickBird, GeoEye-1 and WorldView-4 datasets, and quantitative and qualitative comparisons are made with eight advanced methods, and qualitative and quantitative analyses of the experimental results show that the proposed method has certain superiority. [ABSTRACT FROM AUTHOR] more...