Incorporating an Adaptive Image Prior Model Into Bayesian Fusion of Multispectral and Panchromatic Images

Khademi, Ghassem; Ghassemian, Hassan

doi:10.1109/lgrs.2018.2817561

Cited by 32 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many variations of the multiscale transform-based techniques exist, such as discrete wavelet transform (DWT), stationary wavelet transform (SWT), curvelet transform (CVT), contourlet transform (CT), and Non-subsampled contourlet transform (NSCT) [4]. The next subsections give a descriptive overview and methodology of MST-based pan-sharpening techniques which are selected for this study.…”

Section: Multiscale Transform-based Pan-sharpening Techniquesmentioning

confidence: 99%

“…Wavelet transform brings a multiresolution framework. With this setting, the signal can be decomposed into components that collect the information at a specified scale, i.e., different frequencies are analyzed with different resolutions [2][3][4][5][6]. The WT has numerous applications in remote sensing such as image registration, spatial and spectral fusion, feature extraction, speckle reduction, texture classification, and crop phenology detection [7].…”

Section: Discrete Wavelet Transform (Dwt)mentioning

confidence: 99%

See 1 more Smart Citation

Pan-sharpening Using Spatial-frequency Method

Kumar¹

2019

Satellite Information Classification and Interpretation

View full text Add to dashboard Cite

Over the years, researchers have formulated various techniques for pan sharpening that attempt to minimize the spectral distortion, i.e., retain the maximum spectral fidelity of the MS images. On the other hand, if the use of the PAN-sharpened image is just to produce maps for better visual interpretation, then the spectral distortion is not of much concern, as the goal is to produce images with high contrast. To solve the color distortion problem, methods based on spatial frequency domain have been introduced and have demonstrated superior performance in terms of producing high spectral fidelity pan-sharpened images over spatial-scale methods.

show abstract

Section: Multiscale Transform-based Pan-sharpening Techniquesmentioning

confidence: 99%

Section: Discrete Wavelet Transform (Dwt)mentioning

confidence: 99%

Pan-sharpening Using Spatial-frequency Method

Kumar¹

2019

Satellite Information Classification and Interpretation

View full text Add to dashboard Cite

show abstract

“…The second hypothesis assumes that an up-sampled MS (UPMS) image can be considered a blurred version of an HRMS image; in other words, the HRMS image can be filtered by a blur function with a Gaussian shape to obtain an UPMS image [20]. To improve the reliability of the model, Deng et al [21] proposed a Laplacian prior to constrain the fused image, Khademi et al [22] put forward a total variation prior to reduce the number of artifacts, and Wang et al [23] designed a Markov prior to reconstruct the image based on the maximum posterior probability. After the construction of the VO-based model, iterative optimization algorithms are usually employed to solve the model, including conjugate gradient [17], gradient descent [21], and split Bregman iterative algorithm s [24].…”

Section: Introductionmentioning

confidence: 99%

Pansharpening Based on Joint-Guided Detail Extraction

Yang

Huang

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Pansharpening is the process of fusing low spatial resolution multispectral (MS) images with high spatial resolution panchromatic (PAN) images, so as to obtain high spatial resolution multispectral (HRMS) images. In this study, a new pansharpening method based on a joint-guided detail extraction is proposed to maintain the spectral and spatial fidelity of a pansharpened image. First, to obtain details that are highly correlated with an MS image, a new PAN image is constructed and guided by the intensity component of the MS image through a variational model. The construction of the new PAN image improves the correlation between the PAN and MS images, and thus reduces the spectral distortion. The variational model is rapidly solved using the least-squares method. Second, to obtain accurate details from the new PAN image, the extraction of the details is guided by each band of the MS image through a regression model, which can further reduce the spatial distortion. The regression model is effectively solved using the gradient descend method. Finally, the details are injected into the up-sampled MS image to obtain a fused image. Numerous experiments on the proposed approach were conducted and the results were compared with previous state-of-the-art pansharpening methods. The experimental results verify that the proposed method can efficiently achieve high-quality HRMS images.

show abstract

“…As an ill-posed problem, these methods simulate the process with prior constraints and the modeling can be conceptually seen as an optimization problem. The representative methods used for sharpening include Bayesian model [24,25] and sparse representation [26]. To address the problem of Sentinel-2 sharpening, several methods are presented by taking this task as a convex optimization problem.…”

Section: Introductionmentioning

confidence: 99%

Sentinel-2 Sharpening via Parallel Residual Network

2020

Remote Sensing

View full text Add to dashboard Cite

Sentinel-2 data is of great utility for a wide range of remote sensing applications due to its free access and fine spatial-temporal coverage. However, restricted by the hardware, only four bands of Sentinel-2 images are provided at 10 m resolution, while others are recorded at reduced resolution (i.e., 20 m or 60 m). In this paper, we propose a parallel residual network for Sentinel-2 sharpening termed SPRNet, to obtain the complete data at 10 m resolution. The proposed network aims to learn the mapping between the low-resolution (LR) bands and ideal high-resolution (HR) bands by three steps, including parallel spatial residual learning, spatial feature fusing and spectral feature mapping. First, rather than using the single branch network, the parallel residual learning structure is proposed to extract the spatial features from different resolution bands separately. Second, the spatial feature fusing is aimed to fully fuse the extracted features from each branch and produce the residual image with spatial information. Third, to keep spectral fidelity, the spectral feature mapping is utilized to directly propagate the spectral characteristics of LR bands to target HR bands. Without using extra training data, the proposed network is trained with the lower scale data synthesized from the observed Sentinel-2 data and applied to the original ones. The data at 10 m spatial resolution can be finally obtained by feeding the original 10 m, 20 m and 60 m bands to the trained SPRNet. Extensive experiments conducted on two datasets indicate that the proposed SPRNet obtains good results in the spatial fidelity and the spectral preservation. Compared with the competing approaches, the SPRNet increases the SRE by at least 1.538 dB on 20 m bands and 3.188 dB on 60 m bands while reduces the SAM by at least 0.282 on 20 m bands and 0.162 on 60 m bands.

show abstract

Incorporating an Adaptive Image Prior Model Into Bayesian Fusion of Multispectral and Panchromatic Images

Cited by 32 publications

References 23 publications

Pan-sharpening Using Spatial-frequency Method

Pan-sharpening Using Spatial-frequency Method

Pansharpening Based on Joint-Guided Detail Extraction

Sentinel-2 Sharpening via Parallel Residual Network

Contact Info

Product

Resources

About