Performance evaluation of pan-sharpening and dictionary learning methods for sparse representation of hyperspectral super-resolution

Şimşek, Murat; Polat, Ediz

doi:10.1007/s11760-020-01836-8

Cited by 7 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first VO method treats the PAN image as the linear combination of diverse bands of HRMS image, thus the LRMS image is the blurred version of HRMS image [28]. Afterward, various VO methods are developed to address pansharpening problem, such as Bayesian methods [29,30,31], variational approaches [32,33,34], compressed-sensing and sparse representation-based techniques [35,36,37,38,39,40] and so on. Despite these methods can achieve a good balance between the spectral information and spatial details by optimizing the loss function, they inevitably introduce more tunable parameters and higher computational burden.…”

Section: Introductionmentioning

confidence: 99%

CGSNet: Channel Group Shuffling Network for Remote Sensing Image Fusion

Jiang,

Peng,

Zhang

2023

IEEE Access

View full text Add to dashboard Cite

High-resolution multi-spectral (HRMS) images have been widely used in various fields, however, they can not be directly obtained due to the physical hardware limits of existing remote sensing satellites. Therefore, pansharpening technique has been widely explored as an effective tool to generate HRMS images by fusing the complementary information of low-resolution multi-spectral (LRMS) images and high-resolution panchromatic (PAN) images. Existing deep learning-based pansharpening methods mainly focus on enhancing the spatial representation ability of the network, while paying little attention to modeling spectral dependencies in spite of its significance for remote sensing data. In this paper, we propose a simple yet effective channel group shuffling (CGS) module to explore the implicit relationships with regard to the adjacent and cross-channels while considering spatial information. To be specific, the proposed CGS module consists of two components: channel group module and feature shuffle fusion module. The former enhances the diversity of spectral information and cross-channel information communications while ensuring the spectral order of the input feature. The latter integrates the cross-group feature maps with rich spatial-spectral information. Equipped with the proposed functional module, our image fusion network, dubbed CGSNet, produces favorable results against existing state-of-the-art counterparts over various satellite datasets. Ablation studies further verify the flexibility and effectiveness of our core design. INDEX TERMSPansharpening, Deep learning, Channel group, Feature shuffle fusion.

show abstract

Section: Introductionmentioning

confidence: 99%

CGSNet: Channel Group Shuffling Network for Remote Sensing Image Fusion

Jiang,

Peng,

Zhang

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the first category, it is tried that with fusing a hyperspectral image with a high spatial resolution image (panchromatic, RGB or multispectral), the spatial resolution of the hyperspectral image is increased [3]- [4]. Different fusion methods such as tensor factorization [5], sparse representation and dictionary learning [6], component substitution [7] and multi-resolution analysis approaches [8] belong to the first category. In the second category, there is no auxiliary image for hyperspectral super resolution.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Super Resolution Using Anomaly Weighted Gabor Based CNN

Farajzadeh,

Imani,

Mohammadi

2023

itrc

View full text Add to dashboard Cite

Hyperspectral images have high spectral resolution. But, due to the tradeoff between spectral and spatial resolution and various hardware constraints, imaging a hyperspectral image with high spatial resolution is not practical. Hyperspectral super resolution is a soft approach to solve this challenge. Recently, deep learning based methods such as convolutional neural network (CNN) show great success in this field. But, the contextual details in object boundaries and anomalies present in the scene are not well addressed. To this end, a new CNN based framework is proposed for hyperspectral image super resolution in this work. To improve ability of the convolutional blocks in simultaneous extraction of spectral and spatial characteristics, the weighted Gabor features are concatenated in output of the defined convolutional blocks. To extract more details containing anomalous targets present in the scene, the anomaly scores of pixels are calculated and used for weighting the Gabor features. The experiments on three real hyperspectral images acquired by AVIRIS and ROSIS sensors show superior performance of the proposed framework compared to several state-of-the-art methods based on CNN and residual networks. In addition to common super resolution metrics such as SAM and ERGAS, the efficiency of different methods are evaluated according to the classification accuracy metrics such as overall accuracy and kappa coefficient. The overall classification accuracy is increased from 70.39 to 88.23 in Indian dataset, from 86.07 to 96.20 in Pavia University dataset, and from 95.82 to 99.12 in Pavia center dataset.

show abstract

“…VO-based [12] methods are an important class of pan-sharpening methods. Since the main fusion processes of regularization-based methods [13][14][15][16][17], Bayesian-based methods [18][19][20], model-based optimization (MBO) [21][22][23] methods and sparse reconstruction (SR) [24][25][26] based methods are all based on or transformed into an optimization of a variational model, they can be generalized to variational optimization (VO) based methods. In other words, the main process of such pan-sharpening methods is usually based on or transformed into an optimization of a variational model.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Super-Resolution Via Joint Regularization of Low-Rank Tensor Decomposition

Cao

Bao

2021

Remote Sensing

View full text Add to dashboard Cite

The hyperspectral image super-resolution (HSI-SR) problem aims at reconstructing the high resolution spatial–spectral information of the scene by fusing low-resolution hyperspectral images (LR-HSI) and the corresponding high-resolution multispectral image (HR-MSI). In order to effectively preserve the spatial and spectral structure of hyperspectral images, a new joint regularized low-rank tensor decomposition method (JRLTD) is proposed for HSI-SR. This model alleviates the problem that the traditional HSI-SR method, based on tensor decomposition, fails to adequately take into account the manifold structure of high-dimensional HR-HSI and is sensitive to outliers and noise. The model first operates on the hyperspectral data using the classical Tucker decomposition to transform the hyperspectral data into the form of a three-mode dictionary multiplied by the core tensor, after which the graph regularization and unidirectional total variational (TV) regularization are introduced to constrain the three-mode dictionary. In addition, we impose the l1-norm on core tensor to characterize the sparsity. While effectively preserving the spatial and spectral structures in the fused hyperspectral images, the presence of anomalous noise values in the images is reduced. In this paper, the hyperspectral image super-resolution problem is transformed into a joint regularization optimization problem based on tensor decomposition and solved by a hybrid framework between the alternating direction multiplier method (ADMM) and the proximal alternate optimization (PAO) algorithm. Experimental results conducted on two benchmark datasets and one real dataset show that JRLTD shows superior performance over state-of-the-art hyperspectral super-resolution algorithms.

show abstract

Performance evaluation of pan-sharpening and dictionary learning methods for sparse representation of hyperspectral super-resolution

Cited by 7 publications

References 17 publications

CGSNet: Channel Group Shuffling Network for Remote Sensing Image Fusion

CGSNet: Channel Group Shuffling Network for Remote Sensing Image Fusion

Hyperspectral Image Super Resolution Using Anomaly Weighted Gabor Based CNN

Hyperspectral Super-Resolution Via Joint Regularization of Low-Rank Tensor Decomposition

Contact Info

Product

Resources

About