Introduction of sensor spectral response into image fusion methods. Application to wavelet-based methods

By Xavier Otazu, María González-Audicana, Octavi Fors, Jorge Núñez. IEEE Transactions on Geoscience and Remote Sensing, 2005

850 citations recorded by the source corpus.

Usual image fusion methods inject features from a high spatial resolution panchromatic sensor into every low spatial resolution multispectral band trying to preserve spectral signatures and improve spatial resolution to that of the panchromatic sensor. The objective is to obtain the image that would be observed by a sensor with the same spectral response (i.e., spectral sensitivity and quantum efficiency) as the multispectral sensors and the spatial resolution of the panchromatic sensor. But in these methods, features from electromagnetic spectrum regions not covered by multispectral sensors are injected into them, and physical spectral responses of the sensors are not considered during this process. This produces some undesirable effects, such as resolution overinjection images and slightly modified spectral signatures in some features. The authors present a technique which takes into account the physical electromagnetic spectrum responses of sensors during the fusion process, which produces images closer to the image obtained by the ideal sensor than those obtained by usual wavelet-based image fusion methods. This technique is used to define a new wavelet-based image fusion method.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/042e510b3b55c37756b7e851077508f6dbda648f

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

A New Pan-Sharpening Method Using a Compressed Sensing Technique (2011, methodology): “An ATWTbased method with the additive wavelet luminance proportional (AWLP) model was proposed in [17].”
Target-Adaptive CNN-Based Pansharpening (2017, methodology): “Besides our CNN-based methods, we consider a number of well-known conventional techniques selected because of their good performance, and specifically, PRACS [8], Gram–Schmidt adaptive (GSA) [7], Indusion [13], additive wavelet luminance proportional (AWLP) [12], a Trous wavelet transform using the ”
A Multiscale and Multidepth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening (2017, methodology): “3) Compared Algorithms: For the numeric and visual assessment, seven traditional and state-of-the-art algorithms were used, representing different branches of pan-sharpening methods: GS [4] and partial replacement adaptive component substitution (PRACS) [5] belonging to CS; the MTF-based generalized”
Pansharpening by Convolutional Neural Networks (2016, methodology): “• PRACS: Partial Replacement Adaptive Component Substitution [10]; • Indusion: Decimated Wavelet Transform using an additive injection model [18]; • AWLP: Additive Wavelet Luminance Proportional [20], a generalization of AWL [19]; • ATWT-M3: A Trous Wavelet Transform with the injection Model 3 propo”
A survey of classical methods and new trends in pansharpening of multispectral images (2011, methodology): “The WiSpeR [102] method can be considered as a generalization of different wavelet-based image fusion methods.”
Multisource and Multitemporal Data Fusion in Remote Sensing: A Comprehensive Review of the State of the Art (2019, methodology): “Representative MRA-based fusion methods are founded on box filtering [54], Gaussian filtering [56], bilateral filtering [73], wavelet transform [53], [55], and curvelet transform [57].”
PanNet: A Deep Network Architecture for Pan-Sharpening (2017, methodology): “In multiresolution approaches [19, 22], the PAN image and LRMS images are decomposed, e.”
Remote Sensing Image Fusion Based on Two-Stream Fusion Network (2017, methodology): “(a)Referenced Image; (b) APCA [25]; (c) AWLP [18]; (d) AIHS [21]; (e) PNN [16] and (f) the proposed TFNet.”
Optimal MMSE Pan Sharpening of Very High Resolution Multispectral Images (2008, methodology): “…methods—the SSD and BDSD models with both global mmse (gmmse) and local mmse (lmmse) estimations—and the following two MRA-based Pan-sharpening methods being awarded as the two most distinguished algorithms at the IEEE 2006 Data Fusion Contest: the CBD [9] and the AWLP method [28].”
Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art (2017, methodology): “Representative MRA pan-sharpening algorithms include the smoothing filtered-based intensity modulation (SFIM) method [207], the additive wavelet luminance proportional method [211], and the generalized Laplacian pyramid (GLP) method [208].”
Comparison of Pansharpening Algorithms: Outcome of the 2006 GRS-S Data-Fusion Contest (2007, methodology): “The WiSpeR algorithm developed at the Computer Vision Center, Barcelona, as well, is a generalization of AWLP [23].”
Detail Injection-Based Deep Convolutional Neural Networks for Pansharpening (2021, methodology): “(AWLP) [14], the “à-trous” wavelet transform [15], the Laplacian pyramid (LP) [16], the generalized Laplacian pyramid (GLP) [17], [18], the GLP with robust regression [19], and the GLP with full-scale regression (GLP-Reg) [20].”
A Sparse Image Fusion Algorithm With Application to Pan-Sharpening (2013, methodology): “Among the existing hundreds of various pan-sharpening methods, the most popular ones are intensity–hue–saturation technique (IHS) [2], principal component analysis (PCA) [3], Brovey transform [4], and wavelet-based fusion [5], [6].”
Multi-source remote sensing data fusion: status and trends (2010, methodology): “Otazu et al. (2005) introduced sensors’ spectral responses and ground spectral features into fusion technology on the basis of MRA.”
Boosting the Accuracy of Multispectral Image Pansharpening by Learning a Deep Residual Network (2017, methodology): “proportion (AWLP) method [18], and the two-step sparse coding model (TSSC) [6].”
A New Benchmark Based on Recent Advances in Multispectral Pansharpening: Revisiting Pansharpening With Classical and Emerging Pansharpening Methods (2021, methodology): “The AWLP, originally proposed by [61], exploits the “à trous” wavelet for details of extraction from the PAN image using the fusion rule in (8) and injection coefficients estimated as .”