Context-driven fusion of high spatial and spectral resolution images based on oversampled multiresolution analysis

By Bruno Aiazzi, Luciano Alparone, Stefano Baronti, Andrea Garzelli. IEEE Transactions on Geoscience and Remote Sensing, 2002

903 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/89b716e6dfb3a6124b69fbbbd2baaa7930e0f40e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Comparison of Pansharpening Algorithms: Outcome of the 2006 GRS-S Data-Fusion Contest (2007, methodology): “Such impairments, which may be as much annoying as spectral distortions, are emphasized by mis-registration between MS and Pan data, particularly if the MRA underlying detail injection is not shift-invariant [19], [21].”
Fusion of multispectral and panchromatic images using improved IHS and PCA mergers based on wavelet decomposition (2004, methodology): “As expected [16], [38], those artifacts are missing when the undecimated algorithm is applied, as can be observed in Fig.”
Optimizing the High-Pass Filter Addition Technique for Image Fusion (2007, background): “Within the spatial domain techniques, the wavelet-based image fusion technique, with its large number of sub-varieties, has been most intensely investigated (e.g., Pradhan, 2005; Pradhan et al., 2006; Aiazzi et al., 2002; King et al., 2001).”
Improving Component Substitution Pansharpening Through Multivariate Regression of MS $+$Pan Data (2007, background): “These drawbacks, which may be as annoying as spectral distortions, are emphasized by a misregistration between MS and Pan data, especially if the MRA underlying detail injection is not shift-invariant [15], [18].”
Detail Injection-Based Deep Convolutional Neural Networks for Pansharpening (2021, methodology): “Classical MRA approaches differ from each other in the way to extract PAN details and how to estimate the injection coefﬁcient g in (3) (see [14], [15], [17]).”
Target-Adaptive CNN-Based Pansharpening (2017, methodology): “Spatial details can be extracted in different ways, using, for example, decimated or undecimated wavelet transforms [10]–[13], the Laplacian pyramids [14]–[18], or other nonseparable transforms, such as the contourlet [19].”
A Multiscale and Multidepth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening (2017, methodology): “Examples of this type of method are the fusion methods based on wavelet transform [6] or curvelet transform”
Multi-source remote sensing data fusion: status and trends (2010, methodology): “…fusion techniques (Amolins et al. 2007) adopt multi-scale decomposition methods such as multi-scale wavelets (Nu´n˜ez et al. 1999), Laplacian pyramids (Aiazzi et al. 2002) or bi-dimensional empirical mode decomposition (BEMD; Liu et al. 2007) to decompose MS and PAN images with different levels.”
A Critical Comparison Among Pansharpening Algorithms (2015, background): “The corresponding differential representation, achieved by calculating the differences between the Gaussian pyramid levels, is named LP and has later been proven to be very valuable for pansharpening purposes [64].”
An Efficient Pan-Sharpening Method via a Combined Adaptive PCA Approach and Contourlets (2008, methodology): “pan-sharpening methods using multiresolution approaches of discrete wavelet transform [7], [8], Laplacian pyramid [9], and”
A Variational Model for P+XS Image Fusion (2006, background): “, 1997), or improvements based on multiresolution analysis of P+XS images (Aiazzi et al., 2002).”
Coupled Nonnegative Matrix Factorization Unmixing for Hyperspectral and Multispectral Data Fusion (2012, methodology): “The multiresolution methods based on an undecimated discrete wavelet transform or Laplacian pyramid [6] showed the best results.”
Image fusion—the ARSIS concept and some successful implementation schemes (2003, background): “The 2D low-pass reduction filter is generally zero-phase (Aiazzi et al. , 2002).”
Automatic radiometric normalization of multitemporal satellite imagery with the iteratively re-weighted MAD transformation (2008, neutral): “with a wavelet fusion technique (Aiazzi et al., 2002).”
Forest Types Classification Based on Multi-Source Data Fusion (2017, methodology): “It could be classified into 4 categories: substitution based on Principal Component Analysis (PCA) [30] or Intensity Hue Saturation (IHS) [31]; fusion based on the analysis of multi-resolution [32]; fusion based on model optimization [33]; and fusion based on sparse representation [34].”
Synthesis of Multispectral Images to High Spatial Resolution: A Critical Review of Fusion Methods Based on Remote Sensing Physics (2008, background): “In all these formalisms, the fused MS product is a function of this linear combination and of the Pan image as well.”
Pansharpening by Convolutional Neural Networks (2016, methodology): “These last methods rely on redundant representations, characterized by the shift-invariance property, like the á Trous Wavelet transform (ATWT) or the Laplacian pyramid (LP) [13].”
Optimal MMSE Pan Sharpening of Very High Resolution Multispectral Images (2008, methodology): “…(IHS) transformation or principal component analysis [20], the spectral distortion minimization (SDM) with respect to the resam-pled MS data [21], or the spatially adaptive injection as in the context-based-decision (CBD) algorithm [6] and in the method by Ranchin, Wald, and Mangolini (RWM) [22].”