Two-Step Sparse Coding for the Pan-Sharpening of Remote Sensing Images

Jiang, Cheng; Zhang, Hongyan; Shen, Huanfeng; Zhang, Liangpei

doi:10.1109/jstars.2013.2283236

Cited by 127 publications

(44 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the real data experiments, since there is no reference HR MS image, the "quality with no reference" (QNR) measurement is used to evaluate different pansharpened results objectively. 35 The proposed method is compared with five popular fusion algorithms: AIHS, 7 Wavelet, 11 PN-TSSC, 19 SparseFI, 20 and J-SparseFI. 21 The results of AIHS method are gotten from the software developed by Rahmani et.al.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…[13][14][15][16][17] Recently, inspired by sparse representation techniques, some researchers have achieved great success in data fusion. [18][19][20][21] The initial work is proposed by Li and Yang. 18 Then, Jiang et al 19 proposed a two-step sparse coding method with patch normalization (PN-TSSC).…”

Section: Introductionmentioning

confidence: 99%

“…[18][19][20][21] The initial work is proposed by Li and Yang. 18 Then, Jiang et al 19 proposed a two-step sparse coding method with patch normalization (PN-TSSC). Zhu and Bamler 20 proposed a new pansharpening method named sparse fusion of images (SparseFI), which explores the sparse representation of MS image patches in a dictionary trained only from the PAN image.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pansharpening via sparse regression

Tang

2017

Opt. Eng

View full text Add to dashboard Cite

Abstract. Pansharpening is an effective way to enhance the spatial resolution of a multispectral (MS) image by fusing it with a provided panchromatic image. Instead of restricting the coding coefficients of low-resolution (LR) and high-resolution (HR) images to be equal, we propose a pansharpening approach via sparse regression in which the relationship between sparse coefficients of HR and LR MS images is modeled by ridge regression and elastic-net regression simultaneously learning the corresponding dictionaries. The compact dictionaries are learned based on the sampled patch pairs from the high-and low-resolution images, which can greatly characterize the structural information of the LR MS and HR MS images. Later, taking the complex relationship between the coding coefficients of LR MS and HR MS images into account, the ridge regression is used to characterize the relationship of intrapatches. The elastic-net regression is employed to describe the relationship of interpatches. Thus, the HR MS image can be almost identically reconstructed by multiplying the HR dictionary and the calculated sparse coefficient vector with the learned regression relationship. The simulated and real experimental results illustrate that the proposed method outperforms several well-known methods, both quantitatively and perceptually.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pansharpening via sparse regression

Tang

2017

Opt. Eng

View full text Add to dashboard Cite

show abstract

“…Traditional pan-sharpening algorithms can be divided into three major branches: Component Substitution (CS) [1][2], Detail Injection (DI) [3] [4], and regularization constraint model based methods [5] [6]. In the former two branches, the fusing process is usually split into discrete steps, instead of end-to-end mapping.…”

Section: Introductionmentioning

confidence: 99%

“…Four metrics: Q, ERGAS, SAM, and SCC are employed to quantify its accuracy in spatial and spectral domains, with the original MS image as ground truth. The performances of DRPNN are compared with five algorithms from different branches for comparisons with the proposed network, including Component Substitution: GS [1], Detail Injection: MTF-GLP [3], SFIM [4], regularization constraint models: ISTS [5] based on total variation and TSSC [6] based on sparse representation. Besides these traditional algorithms, PNN [10], a shallow CNN without recidual learning and skip connection has also been included for comparison.…”

Section: Introductionmentioning

confidence: 99%

Boosting the Accuracy of Multispectral Image Pansharpening by Learning a Deep Residual Network

Wei

Yuan

Shen

et al. 2017

IEEE Geosci. Remote Sensing Lett.

Self Cite

414

198

View full text Add to dashboard Cite

Abstract-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