Multiband Remote Sensing Image Pansharpening Based on Dual-Injection Model

Abstract

Pansharpening exploits the high-frequency component (HFC) of panchromatic (PAN) images to restore the spatialresolution of the corresponding multispectral (MS) image. In this article, a dual-injection model-based multiband remote sensing image pansharpening method is presented that focuses on how to correctly use the HFC to improve the MS image for obtaining a high-spatial resolution and MS image. The model is based on a two-step HFC injection algorithm with two different injection gains. In the first step, an HFC is reconstructed with sparse theory, and an injection gain based on the relationship between PAN and MS images is developed. Employing the previous injection gain and the reconstructed HFC on an upsampling MS image, an improved LRMS (ILRMS) image is then produced. In the second step, another injection gain based on the differences and similarities between the PAN and MS images is designed. With the help of this injection gain, the fusion image is achieved via the adaptive integration of the ILRMS image and the HFC from the PAN image. Experiments confirm that the proposed method is more effective than some popular widely used pansharpening methods.

Pansharpening Based on Spectral-Spatial Dependence for Multibands Remote Sensing Images

“…With reference image [30] No referenceimage [32] Correlation The peak signal-to-noise ratio (PSNR ) S D : the spectral distortion index Q2n-index (Q4 ) Remark：The symbol ↑ denotes that a higher value implies better performance. The symbol↓ denotes that a lower value implies lower performance.…”

“…Most researchers improve the DI model by innovating its three decision variables. For example, Yang et al [31] suggested compensation detail injection based on sparse fusion, and Yang et al [32] developed an intermediate image to take the place of the LRMS image to receive the injected details with the help of an improved injection gain. These methods can effectively enhance the spatial resolution of an MS image, but various degrees of spectral distortion were produced because the methods ignore the influence of the spatial enhancement in one pixel on the spectral of its neighbourhood pixels.…”

Remote Sensing Pansharpening by Full-Depth Feature Fusion

“…Recently, with the rapid development of deep learning and accessibility of highperformance computing hardware equipment, convolutional neural networks (CNNs) have shown outstanding performance in image processing fields, e.g., image resolution reconstruction [45][46][47][48][49], image segmentation [50][51][52], image fusion [53][54][55][56][57], image classification [58], image denoising [59], etc. Therefore, many methods [34][35][36][37][38]41,42,[58][59][60][61][62][63][64][65][66][67][68][69][70][71][72][73][74][75] based on deep learning have also been applied to solve the pansharpening problem. Benefiting from the powerful nonlinear fitting and feature extraction capabilities of CNNs and the availability of big data, these DL-based methods could perform better than the above three methods to a certain degree, i.e., CS-, MRA-, and VO-based methods.…”

Pansharpening Based on Joint-Guided Detail Extraction

“…Methods based on variational optimization (VO) make up an important category of pansharpening techniques, and can balance the performance and efficiency of this process [16]. Such methods are generally based on or transformed into a variational optimization problem, which includes two processes: (1) the construction of the energy function and (2) minimization of the energy function [17], [18]. To build a reasonable model, researchers have presented two hypotheses: The first hypothesis assumes that the spatial structure of an ideal fusion image is roughly the same as that of a PAN image, which is usually represented by gradient features or wavelet coefficients [1], [19].…”