Data Fusion. Definitions and Architectures - Fusion of Images of Different Spatial Resolutions

By Lucien Wald. 2002

676 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/51b2b81e5124b3bb7ec53517a5dd64d8e348cadf

How researchers see this paper

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

Citations in the corpus

Detail Injection-Based Deep Convolutional Neural Networks for Pansharpening (2021, methodology): “The former is performed using the spectral angle mapper (SAM) [61], the relative dimensionless global error in synthesis (ERGAS) [62], the spatial correlation coef-ﬁcient (SCC) [63], and the universal image quality index for four-band images (Q4) and eight-band images (Q8) [64].”
A comparison of STARFM and an unmixing-based algorithm for Landsat and MODIS data fusion (2015, methodology): “resolution image (Wald, 2002) and spatially similar to the highresolution image (Lillo-Saavedra, Gonzalo, Arquero, & Martinez, 2005), and is calculated as follows:”
A New Pansharpening Algorithm Based on Total Variation (2014, methodology): “When there is no reference image available it is difficult to make objective comparisons, however, a possible solution is to make use of Wald’s consistency property [5] which states that the pansharpened image degraded to the resolution of the MS image should be very similar to the original MS image”
Pansharpening by Convolutional Neural Networks (2016, background): “SAM Spectral Angle Mapper [45] ERGAS Erreur Relative Globale Adimensionnelle de Synthèse [46] full reference SCC Spatial Correlation Coefficient [47] Q Universal Image Quality index [48] averaged over the bands Qx x-band extension of Q [49] QNR Quality with no-Reference index [44] no reference Dλ Sp”
Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising (2014, methodology): “Evaluation measures: To comprehensively assess the performance of all competing algorithms, we employ five quantitative picture quality indices (PQI) for performance evaluation, including peak signal-to-noise ratio (PSNR), structure similarity (SSIM [26]), feature similarity (FSIM [30]), erreur rela”
A Critical Comparison Among Pansharpening Algorithms (2015, unknown): “A more credited global index is the Erreur Relative Globale Adimensionnelle de Synthèse (ERGAS) that was properly proposed for pansharpening in [73] and is defined as follows: where the RMSE is defined as in (22), and μ represents the mean (average on pixels) of the image.”
Image fusion—the ARSIS concept and some successful implementation schemes (2003, methodology): “From several published and unpublished experiments, Wald (2002) reports that an error ERGAS larger than 3 corresponds to fused products of low quality, while an ERGAS less than 3 denotes a product of satisfactory quality or better.”
Synthesis of Multispectral Images to High Spatial Resolution: A Critical Review of Fusion Methods Based on Remote Sensing Physics (2008, methodology): “Nowadays, no published fusion method actually fulfills the totality of these requirements.”
Multi-source remote sensing data fusion: status and trends (2010, methodology): “Wald (2002) and Ranchin et al. (2003) introduce the ‘Ame´lioration de la Re´solution Spatiale par Injection de Structures’ (ARSIS, improving spatial resolution by structure injection) concept based on the assumption that the missing information is linked to the high frequencies of the data sets to…”
PanNet: A Deep Network Architecture for Pan-Sharpening (2017, methodology): “We use five widely used quantitative performance measures to evaluate performance: relative dimensionless global error in synthesis (ERGAS) [23], spectral angle mapper (SAM) [26], universal image quality index [25] averaged over the bands (QAVE) and x-band extension of Q8 (for 8 bands) [2], and the ”
A survey of classical methods and new trends in pansharpening of multispectral images (2011, background): “However, we cannot predict the quality at higher resolution from the quality of lower resolution [106].”
A comparative analysis of image fusion methods (2005, background): “the original resolution level is close to the quality of the synthesized images at the inferior level [37], so properties 2) and 3) can still be used to compare the behavior of the various methods.”
A Multiscale and Multidepth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening (2017, background): “Five numeric metrics were applied to quantify the qualities of the pan-sharpened images from the simulated experiments: the peak signal-to-noise ratio (PSNR) [44], the universal image quality metric (Q) [45], the Erreur Relative Globale Adimensionnelle de Synthèse (ERGAS) [46], the spectral angle m”
Hyperspectral Pansharpening: A Review (2015, methodology): “4) Erreur relative globale adimensionnelle de synthèse: ERGAS offers a global indication of the quality of a fused image.”
Kronecker-Basis-Representation Based Tensor Sparsity and Its Applications to Tensor Recovery (2018, unknown): “:3) e se (ERGAS [65]).”
A New Benchmark Based on Recent Advances in Multispectral Pansharpening: Revisiting Pansharpening With Classical and Emerging Pansharpening Methods (2021, background): “ERREUR RELATIVE GLOBALE ADIMENSIONNELLE DE SYNTHÉSE The ERGAS index, whose French acronym stands for relative dimensionless global error in synthesis [139], is a normalized dissimilarity index that offers a global indication of the distortion toward the reference of a test multiband image:”