A new IHS and wavelet based pansharpening algorithm for high spatial resolution satellite imagery

Wady, S. M. A.; Bentoutou, Y.; Bengermikh, A.; Bounoua, Abdennacer; Taleb, Nasreddine

doi:10.1016/j.asr.2020.06.001

Cited by 19 publications

(9 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where N represents the number of channels, M i represents the selected multispectral Image channels, F i represents pansharpened image, P H represents the histogram-matched highspatial-resolution PAN data, P represents PAN data, I represents up-sampled intensity component, σ represents deviation, and μ represents mean. However, some authors noticed that the resulting image contains several spectral distortions despite excellent efficiency and high spatial resolution [61]- [63]. These findings inspired numerous modifications to the algorithm.…”

Section: B Pansharpeningmentioning

confidence: 99%

Using Super-Resolution Algorithms for Small Satellite Imagery: A Systematic Review

Karwowska

Wierzbicki

2022

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

View full text Add to dashboard Cite

show abstract

Section: B Pansharpeningmentioning

confidence: 99%

Using Super-Resolution Algorithms for Small Satellite Imagery: A Systematic Review

Karwowska

Wierzbicki

2022

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

View full text Add to dashboard Cite

show abstract

“…Regression coefficients between MS bands and PAN image are then used to generate better clarity fused image. Hybrid pansharpening method, based on IHS and à-trous wavelet decomposition, injects spatial information in MS bands while preserving spectral details [10]. However, its computational complexity is higher as compared to other CS methods.…”

Section: Introductionmentioning

confidence: 99%

Siamese Networks Based Deep Fusion Framework for Multi-Source Satellite Imagery

et al. 2022

View full text Add to dashboard Cite

A critical aim of pansharpening is to fuse coherent spatial and spectral features from panchromatic and multispectral images respectively. This study proposes deep siamese network based pansharpening model as a two-stage framework in a multiscale setting. In the first stage, a siamese network learns a common feature space between panchromatic and multispectral bands. The second stage follows by fusing the output feature maps of the siamese network. The parameters of these two stages are shared across scales in order to add spatial information consistently (across scales). The spectral information is preserved by adding appropriate skip connections from input multispectral image. Multi-level network parameters sharing mechanism in pyramidal reconstruction of pansharpened image, better preserves spatial and spectral details simultaneously. Experimental work carried out using deep siamese network in multi-scale setting (to obtain inter-band similarity among different sensor data) outperforms several latest pansharpening methods.INDEX TERMS Pansharpening, image fusion, deep-learning, siamese networks, remote sensing, depth-of-field.

show abstract

“…Image fusion or pan-sharpening proposes enhancing the low spatial quality MS image by adding the details of the high spatial quality PAN image [4]. Recently, the fusion of PAN and MS images has become an important requirement for many remote sensing applications.…”

Section: Introductionmentioning

confidence: 99%

A Novel Fusion Technique for GeoEye-1 Satellite Imagery

Elshora

2022

Preprint

View full text Add to dashboard Cite

Color distortion is the main weakness of the current fusion techniques, which occurs because of radiometric differences between panchromatic (PAN) and multispectral (MS) images. In this study, a novel fusion technique was developed to merge the PAN and MS images of the GeoEye-1 satellite and produce superior fused images without color distortion. This technique proposes reducing the difference in radiometry between the PAN band and the MS bands by using only the parts of the MS bands inside the area of the PAN band. Therefore, modification coefficients were used for the MS bands in the definition of the intensity (I) equation based on their overlapping areas with the PAN band. As the reflectance of vegetation is high in the NIR band and low in the RGB bands, this technique suggests using an additional coefficient for the NIR band in the definition of the I equation to add the correct effect of vegetation. This coefficient is variable for all types of land cover based on the percentage of the agricultural areas within the image, which leads to significant and stable performance for all types of land cover. This study aims to evaluate the performance of this technique by a comparison with five standard fusion techniques: fast-intensity-hue-saturation, principal component analysis, Gram Schmidt fusion, hyper-spherical color space, and Ehlers fusion. Three datasets of GeoEye-1 satellite PAN and MS images in Tanta City, Egypt, with different land cover classes (agricultural, urban, and mixed areas), were used in this study. The output fused images were compared with the original PAN and MS images by statistical analysis and visual inspection. The proposed fusion technique demonstrated great efficiency in producing fused images of superior spatial and spectral quality for all types of land cover.

show abstract

A new IHS and wavelet based pansharpening algorithm for high spatial resolution satellite imagery

Cited by 19 publications

References 44 publications

Using Super-Resolution Algorithms for Small Satellite Imagery: A Systematic Review

Using Super-Resolution Algorithms for Small Satellite Imagery: A Systematic Review

Siamese Networks Based Deep Fusion Framework for Multi-Source Satellite Imagery

A Novel Fusion Technique for GeoEye-1 Satellite Imagery

Contact Info

Product

Resources

About