Novel Super Resolution Restoration of Remote Sensing Images Based on Compressive Sensing and Example Patches-Aided Dictionary Learning

In this paper, a sensing image super-resolution (SR) reconstruction method is proposed. Sparse dictionary dealing with remote sensing image SR problem is introduced in this work. The sparse dictionary is based on a sparsity model where the dictionary atoms have sparse representation over a basic dictionary. The sparse dictionary consists of two parts: basic dictionary and atom representation matrix. The sparse dictionary leads to compact representation and it is both adaptive and efficient. Furthermore, compared with conventional SR methods, two dictionary pairs, i.e. primitive sparse dictionary pair and residual sparse dictionary pair, are proposed. The primitive sparse dictionary pair is learned to reconstruct initial high-resolution (HR) remote sensing image from a single low-resolution (LR) input. However, the initial HR remote sensing image loses some details compare with the corresponding original HR image completely. Therefore, residual sparse dictionary pair is learned to reconstruct residual information. The proposed method is tested on remote sensing images, and the experimental results indicate that the proposed algorithm can provide substantial improvement in resolution of remote sensing images, and the results are superior in quality to the results produced by other methods.

show abstract

“…The conventional dictionaries [16,17,18,22] are unstructured [23]. In this work, we introduce the sparse dictionary.…”

Section: A the Basics Of Sparse Dictionarymentioning

confidence: 99%

“…However the trained dictionary is a nonstructured dictionary; consequently the approach may produce ringing effect in certain resultant images. In [17], K-SVD method was used to obtain a suitable dictionary. The authors of [18] applied optimized K-SVD algorithm to obtain an appropriate dictionary.…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Images Super-resolution Based on Sparse Dictionaries and Residual Dictionaries

Zhang

Dai

et al. 2013

2013 IEEE 11th International Conference on Dependable, Autonomic and Secure Computing

View full text Add to dashboard Cite

show abstract

“…Example-based SR approaches break the limitations existing in the traditional reconstruction-based algorithms. They learn the mapping relationship between the corresponding pre-processed low and high resolution training samples to recover the missed HF details, mainly including learningbased approach [4], neighborhood embedding approach [5] and sparse representation methods [6][7][8][9][10][11][12][13][14][15][16][17][18], etc.…”

Section: Introductionmentioning

confidence: 99%

“…Yang [14] made some improvements combined with sparse representation theory on the basis of Glasner's work, which improves the reconstruction efficiency and quality. The reconstruction method in [17] modified the algorithm of Yang [6][7][8] with the CS theory, reducing the number of training dictionary but still using external several training images. Pan in [15][16] and Zhu in [18] modified the method in [17] not relying on any external images, assuming that the low resolution patches can be considered as the compressed sensing version of high resolution patches under the framework of CS theory.…”

Section: Introductionmentioning

confidence: 99%

Image Super-resolution Reconstruction Algorithm Based on Self-Similarity and Compressive Sensing

Yao¹,

Xie²

2017

IJSIP

View full text Add to dashboard Cite

show abstract

“…However, the performance of this method relies heavily on the number of atoms. In [4] and [5], the authors only establish one HR dictionary, which needs a few of atoms to resolve the SR problem well. But they fix the linear measurement matrix which limits only to a scale factor of two.…”

Section: Introductionmentioning

confidence: 99%

Spatial-spectral compressive sensing for hyperspectral images super-resolution over learned dictionary

Huang

Liu

et al. 2014

2014 IEEE Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

This paper proposes a new hyperspectral images superresolution (HSI-SR) method based on compressive sensing (CS) theory, spatial sparsity and spectral similarity prior. First, according to sparsity and incoherence of CS theory, we propose a new dictionary learning method, ensuring that the learned dictionary not only has less dimensionality to speed up the sparse decomposition, but also satisfies sparsity well. Then, we introduce the spatial sparsity and spectral similarity regularizations into HSI-SR model, which can recover the spatial information effectively and preserve the spectral information well. The experimental results show the proposed method outperforms other well-known methods in terms of both objective measurements and visual evaluation.

show abstract

Novel Super Resolution Restoration of Remote Sensing Images Based on Compressive Sensing and Example Patches-Aided Dictionary Learning

Cited by 31 publications

References 17 publications

Remote Sensing Images Super-resolution Based on Sparse Dictionaries and Residual Dictionaries

Remote Sensing Images Super-resolution Based on Sparse Dictionaries and Residual Dictionaries

Image Super-resolution Reconstruction Algorithm Based on Self-Similarity and Compressive Sensing

Spatial-spectral compressive sensing for hyperspectral images super-resolution over learned dictionary

Contact Info

Product

Resources

About