Pansharpening using total variation regularization

He, Xiyan; Condat, Laurent; Chanussot, Jocelyn; Xia, Junshi

doi:10.1109/igarss.2012.6351611

Cited by 12 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two proposed pansharpening methods LR-TV and PCP-TV, are compared with seven state-of-theart methods, including two recent component substitution methods with spectral adjustment: FIHS-SA 3 [18] and GSA 4 [20]; two multiresolution-analysis methods, which are joint winners of the 2006 IEEE Data Fusion Contest 5 [13]: AWLP [23] and GLP-CBD [22], [49]; and three variational methods 6 : P+XS [28] and the two TV based methods presented in Sect. II (respectively referred to as TV_1 for the method in [30] and TV_2 for the method in [35]). …”

Section: Resultsmentioning

confidence: 99%

“…where the data fidelity term (1/2) Rv−u 2 2 measures the data misfit with respect to u and the regularizer φ(v, p) promotes a solution v with desired properties, which depend on the Pan image p. In this vein, the authors of [30] proposed to add the gradient of the Pan image into the total variation functional, in order to inject important geometric and structural information of the Pan image into the fused image. The optimization problem is defined in [30] as…”

Section: Formulation Of the Pansharpening Inferencementioning

confidence: 99%

See 1 more Smart Citation

A New Pansharpening Method Based on Spatial and Spectral Sparsity Priors

Condat

Bioucas-Dias

et al. 2014

IEEE Trans. on Image Process.

Self Cite

155

View full text Add to dashboard Cite

Abstract-The development of multisensor systems in recent years has led to great increase in the amount of available remote sensing data. Image fusion techniques aim at inferring high quality images of a given area from degraded versions of the same area obtained by multiple sensors. This paper focuses on pansharpening, which is the inference of a high spatial resolution multispectral image from two degraded versions with complementary spectral and spatial resolution characteristics: 1) a low spatial resolution multispectral image and 2) a high spatial resolution panchromatic image. We introduce a new variational model based on spatial and spectral sparsity priors for the fusion. In the spectral domain, we encourage low-rank structure, whereas in the spatial domain, we promote sparsity on the local differences. Given the fact that both panchromatic and multispectral images are integrations of the underlying continuous spectra using different channel responses, we propose to exploit appropriate regularizations based on both spatial and spectral links between panchromatic and fused multispectral images. A weighted version of the vector total variation norm of the data matrix is employed to align the spatial information of the fused image with that of the panchromatic image. With regard to spectral information, two different types of regularization are proposed to promote a soft constraint on the linear dependence between the panchromatic and fused multispectral images. The first one estimates directly the linear coefficients from the observed panchromatic and low-resolution multispectral images by linear regression while the second one employs the principal component pursuit to obtain a robust recovery of the underlying low-rank structure. We also show that the two regularizers are strongly related. The basic idea of both regularizers is that the J. Chanussot is with the GIPSA-Laboratory, University of Grenoble, Grenoble F-38402, France, and also with the Faculty of Electrical and Computer Engineering, University of Iceland, Reykjavik 101, Iceland (e-mail: jocelyn.chanussot@gipsa-lab.grenoble-inp.fr).This paper has supplementary downloadable material available at http://ieeexplore.ieee.org., provided by the author. The supplementary material contains the details of the parameter selection and the algorithm performance of the two proposed methods. It can also be downloaded at http://www.gipsalab.fr/∼jocelyn.chanussot/SupplementaryMaterial.pdf. The total size of the file is 82.5 kB. Contact greenhxy@gmail.com for further questions about this work.Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee. Index Terms-Image fusion, pansharpening, remote sensing, principal component pursuit, total variation, low rank recovery, convex optimization, proximal splitting method, split augmented Lagrangian shrinkage (SALSA).

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Formulation Of the Pansharpening Inferencementioning

confidence: 99%

A New Pansharpening Method Based on Spatial and Spectral Sparsity Priors

Condat

Bioucas-Dias

et al. 2014

IEEE Trans. on Image Process.

Self Cite

155

View full text Add to dashboard Cite

show abstract

“…He et al [30] proposed to add the gradient of the panchromatic image into the total variation functional. Instead of penalizing the oscillations of each spectral band independently, the proposed term couples the regularization of the spectral and panchromatic components as follows:…”

Section: Classical Regularization Strategiesmentioning

confidence: 99%

A survey of pansharpening methods with a new band-decoupled variational model

Duran

Buades

Coll

et al. 2017

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Most satellites decouple the acquisition of a panchromatic image at high spatial resolution from the acquisition of a multispectral image at lower spatial resolution. Pansharpening is a fusion technique used to increase the spatial resolution of the multispectral data while simultaneously preserving its spectral information. In this paper, we consider pansharpening as an optimization problem minimizing a cost function with a nonlocal regularization term. The energy functional which is to be minimized decouples for each band, thus permitting the application to misregistered spectral components. This requirement is achieved by dropping the, commonly used, assumption that relates the spectral and panchromatic modalities by a linear transformation. Instead, a new constraint that preserves the radiometric ratio between the panchromatic and each spectral component is introduced. An exhaustive performance comparison of the proposed fusion method with several classical and state-of-the-art pansharpening techniques illustrates its superiority in preserving spatial details, reducing color distortions, and avoiding the creation of aliasing artifacts.

show abstract

“…Besides, in order to reduce the time complexity, an alternate variational wavelet pan-sharpening (AVWP) model was suggested by Moeller (2009). On the other hand, by considering the fusion problem as the colourization of the panchromatic image, He et al (2012) introduced a variant of the total variation (TV) to generate a high-resolution pan-sharpened image. In this setting, Palsson, Sveinsson, and Ulfarsson (2014) presented afterwards a simple explicit image formation model with Tikhonov and TV regularization.…”

Section: Introductionmentioning

confidence: 99%

Pan-sharpening of multi-spectral images using a new variational model

Zhang

Fang

Zhou

et al. 2015

International Journal of Remote Sensing

View full text Add to dashboard Cite

In the field of multi-spectral and panchromatic images fusion (Pan-sharpening), the impressive effectiveness of deep neural networks has been recently employed to overcome the drawbacks of traditional linear models and boost the fusing accuracy. However, to the best of our knowledge, existing research works are mainly based on simple and flat networks with relatively shallow architecture, which severely limited their performances. In this paper, the concept of residual learning has been introduced to form a very deep convolutional neural network to make a full use of the high non-linearity of deep learning models. By both quantitative and visual assessments on a large number of high quality multi-spectral images from various sources, it has been supported that our proposed model is superior to all mainstream algorithms included in the comparison, and achieved the highest spatial-spectral unified accuracy.

show abstract

Pansharpening using total variation regularization

Cited by 12 publications

References 16 publications

A New Pansharpening Method Based on Spatial and Spectral Sparsity Priors

A New Pansharpening Method Based on Spatial and Spectral Sparsity Priors

A survey of pansharpening methods with a new band-decoupled variational model

Pan-sharpening of multi-spectral images using a new variational model

Contact Info

Product

Resources

About