Detail Information Prior Net for Remote Sensing Image Pansharpening

Abstract

Pansharpening, which fuses the panchromatic (PAN) band with multispectral (MS) bands to obtain an MS image with spatial resolution of the PAN images, has been a popular topic in remote sensing applications in recent years. Although the deep-learning-based pansharpening algorithm has achieved better performance than traditional methods, the fusion extracts insufficient spatial information from a PAN image, producing low-quality pansharpened images. To address this problem, this paper proposes a novel progressive PAN-injected fusion method based on superresolution (SR). The network extracts the detail features of a PAN image by using two-stream PAN input; uses a feature fusion unit (FFU) to gradually inject low-frequency PAN features, with high-frequency PAN features added after subpixel convolution; uses a plain autoencoder to inject the extracted PAN features; and applies a structural similarity index measure (SSIM) loss to focus on the structural quality. Experiments performed on different datasets indicate that the proposed method outperforms several state-of-the-art pansharpening methods in both visual appearance and objective indexes, and the SSIM loss can help improve the pansharpened quality on the original dataset.

Deep Learning Hyperspectral Pansharpening on Large-Scale PRISMA Dataset

“…net/wp-content/uploads/2022/11/Mini-Toolbox-PRISMA.zip, (accessed on 26 May 2024)). Regarding the deep learning methods, we selected PNN [52], PanNet [53], MSDCNN [54], TFNet [55], SRPPNN [56], DIPNet [57], FPF-GAN [34], and PGCU-PanNet [36].…”

“…The rest of the original architecture was not changed. • DIPNet [57]: This model is composed of 3 main components. The first two are feature extraction branches, respectively, for the low-frequency and high-frequency details of the panchromatic image; here, we changed the stride value of the second convolutional layer used to reduce the features' spatial resolution, from 2 to 3, in order to bring the extracted features to the same dimension of the input bands to perform feature concatenation.…”

Target feature matching method of remote sensing image of power tower supported by grid coding

“…Combining the above described grid model of remote sensing image target recognition, we can use the GCNN convolution neural network to carry out feature matching from the perspective of image signal processing [20]. That is, each remote sensing image is regarded as a special data format, different pixels represent different nodes, and each channel center node has an image arrangement mean.…”