Sparse Representation Based Pansharpening Using Trained Dictionary

Cheng, Ming; Wang, Cheng; Li, Jonathan

doi:10.1109/lgrs.2013.2256875

Cited by 72 publications

(24 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main directions investigate techniques to select the dictionary, improve the sparse codes, and reduce its dimensionality. In order to solve the problem of learning the dictionary for the high-resolution multispectral images, which is unknown, a recent work [94] proposes to train the dictionary using both the high-and low-resolution multispectral images and to constrain the learning of the K-SVD method to improve the representation. The work in [95] also introduces a compressed sensing method that significantly minimizes the spectral distortion in the pan-sharpened multispectral bands with respect to the original ones.…”

Section: B Sparse Dictionary Learningmentioning

confidence: 99%

Multimodal Classification of Remote Sensing Images: A Review and Future Directions

Gómez-Chova¹,

et al. 2015

View full text Add to dashboard Cite

| Earth observation through remote sensing images allows the accurate characterization and identification of materials on the surface from space and airborne platforms. Multiple and heterogeneous image sources can be available for the same geographical region: multispectral, hyperspectral, radar, multitemporal, and multiangular images can today be acquired over a given scene. These sources can be combined/fused to improve classification of the materials on the surface. Even if this type of systems is generally accurate, the field is about to face new challenges: the upcoming constellations of satellite sensors will acquire large amounts of images of different spatial, spectral, angular, and temporal resolutions. In this scenario, multimodal image fusion stands out as the appropriate framework to address these problems. In this paper, we provide a taxonomical view of the field and review the current methodologies for multimodal classification of remote sensing images.We also highlight the most recent advances, which exploit synergies with machine learning and signal processing: sparse methods, kernel-based fusion, Markov modeling, and manifold alignment. Then, we illustrate the different approaches in seven challenging remote sensing applications: 1) multiresolution fusion for multispectral image classification; 2) image downscaling as a form of multitemporal image fusion and multidimensional interpolation among sensors of different spatial, spectral, and temporal resolutions; 3) multiangular image clas, sification; 4) multisensor image fusion exploiting physicallybased feature extractions; 5) multitemporal image classification of land covers in incomplete, inconsistent, and vague image sources; 6) spatiospectral multisensor fusion of optical and radar images for change detection; and 7) cross-sensor adaptation of classifiers. The adoption of these techniques in operational settings will help to monitor our planet from space in the very near future.

show abstract

Section: B Sparse Dictionary Learningmentioning

confidence: 99%

Multimodal Classification of Remote Sensing Images: A Review and Future Directions

Gómez-Chova¹,

et al. 2015

View full text Add to dashboard Cite

show abstract

“…In [29] a method based on compressive sensing with sparsity-inducing prior information has been proposed, where sparsity is enforced by building a dictionary of image patches randomly sampled from high-resolution MS images. Further developments have been proposed in [30][31][32] with the goal to avoid the cost of dictionary construction. As of today, instead, there has been limited interest on deep learning, with some exception like in [33], where a modified sparse denoising autoencoder algorithm is proposed.…”

Section: Introductionmentioning

confidence: 99%

Pansharpening by Convolutional Neural Networks

et al. 2016

View full text Add to dashboard Cite

Abstract:A new pansharpening method is proposed, based on convolutional neural networks. We adapt a simple and effective three-layer architecture recently proposed for super-resolution to the pansharpening problem. Moreover, to improve performance without increasing complexity, we augment the input by including several maps of nonlinear radiometric indices typical of remote sensing. Experiments on three representative datasets show the proposed method to provide very promising results, largely competitive with the current state of the art in terms of both full-reference and no-reference metrics, and also at a visual inspection.

show abstract

“…Since the method includes both classical (in this case AWLP) and sparse representation-based strategies, it can be categorized as a hybrid SR-based approach. While better quality score indexes are obtained with respect to the boosting pan-sharpening method AWLP, no remarkable improvements are introduced by this method with respect to fast and robust classical component substitution methods, such as Gram-Schmidt Adaptive -Context Adaptive (GSA-CA) [8], as reported in Cheng, Wang and Li [39].…”

Section: Hybrid Sr-based Approaches For Pan-sharpeningmentioning

confidence: 92%

“…Recently, some image fusion methods based on the compressed sensing paradigm and sparse representations have appeared, either applied to pan-sharpening [36][37][38][39] or to spatio-temporal fusion of multispectral images [40][41][42].…”

Section: Sparse Representationmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Image Fusion Algorithms Based on the Super-Resolution Paradigm

Garzelli

2016

Remote Sensing

View full text Add to dashboard Cite

A critical analysis of remote sensing image fusion methods based on the super-resolution (SR) paradigm is presented in this paper. Very recent algorithms have been selected among the pioneering studies adopting a new methodology and the most promising solutions. After introducing the concept of super-resolution and modeling the approach as a constrained optimization problem, different SR solutions for spatio-temporal fusion and pan-sharpening are reviewed and critically discussed. Concerning pan-sharpening, the well-known, simple, yet effective, proportional additive wavelet in the luminance component (AWLP) is adopted as a benchmark to assess the performance of the new SR-based pan-sharpening methods. The widespread quality indexes computed at degraded resolution, with the original multispectral image used as the reference, i.e., SAM (Spectral Angle Mapper) and ERGAS (Erreur Relative Globale Adimensionnelle de Synthèse), are finally presented. Considering these results, sparse representation and Bayesian approaches seem far from being mature to be adopted in operational pan-sharpening scenarios.

show abstract

Sparse Representation Based Pansharpening Using Trained Dictionary

Cited by 72 publications

References 16 publications

Multimodal Classification of Remote Sensing Images: A Review and Future Directions

Multimodal Classification of Remote Sensing Images: A Review and Future Directions

Pansharpening by Convolutional Neural Networks

A Review of Image Fusion Algorithms Based on the Super-Resolution Paradigm

Contact Info

Product

Resources

About