Hyperspectral Image Resolution Enhancement Based on Spectral Unmixing and Information Fusion

Bieniarz, Jakub; Cerra, Daniele; Avbelj, Janja; Reinartz, Peter; Müller, Rupert

doi:10.5194/isprsarchives-xxxviii-4-w19-33-2011

Cited by 21 publications

(20 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…PAN sensors capture image in wavelength range of 0.4 to 0.7 um. Therefore in this paper panchromatic image is simulated by resampling hyperspectral data on bands between 400 to 700 nm (Bieniarz et al, 2011).…”

Section: Panchromatic Datamentioning

confidence: 99%

“…Another method named coupled non negative matrix factorization (CNMF) has been introduced by Yokoya et al (2011) (Yokoya et al, 2012). Bieniarz et al (2011) (Bieniarz et al, 2011) proposed an algorithm to fuse multispectral and hyperspectral data based on linear mixing model. A fusion method based on Indusion approach was proposed by Licciardi et al (2012) (Licciardi et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fusion of Hyperspectral and Panchromatic Images Using Spectral Unmixing Results

Rajabi

Ghassemian

2013

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Hyperspectral imaging, due to providing high spectral resolution images, is one of the most important tools in the remote sensing field. Because of technological restrictions hyperspectral sensors has a limited spatial resolution. On the other hand panchromatic image has a better spatial resolution. Combining this information together can provide a better understanding of the target scene. Spectral unmixing of mixed pixels in hyperspectral images results in spectral signature and abundance fractions of endmembers but gives no information about their location in a mixed pixel. In this paper we have used spectral unmixing results of hyperspectral images and segmentation results of panchromatic image for data fusion. The proposed method has been applied on simulated data using AVRIS Indian Pines datasets. Results show that this method can effectively combine information in hyperspectral and panchromatic images.

show abstract

Section: Panchromatic Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fusion of Hyperspectral and Panchromatic Images Using Spectral Unmixing Results

Rajabi

Ghassemian

2013

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Based on this model, a non-negative matrix factorization pansharpening of HS image has been proposed in [21]. Similar works have been developed independently in [16], [23], [24]. Later, Yokoya et al have proposed to use a coupled nonnegative matrix factorization (CNMF) unmixing for the fusion of low-spatial-resolution HS and high-spatial-resolution MS data, where both HS and MS data are alternately unmixed into endmember and abundance matrices by the CNMF algorithm [15].…”

Section: Introductionmentioning

confidence: 99%

Multiband Image Fusion Based on Spectral Unmixing

Wei

Bioucas-Dias

Dobigeon

et al. 2016

IEEE Trans. Geosci. Remote Sensing

141

View full text Add to dashboard Cite

This paper presents a multi-band image fusion algorithm based on unsupervised spectral unmixing for combining a high-spatial low-spectral resolution image and a low-spatial high-spectral resolution image. The widely used linear observation model (with additive Gaussian noise) is combined with the linear spectral mixture model to form the likelihoods of the observations. The non-negativity and sum-to-one constraints resulting from the intrinsic physical properties of the abundances are introduced as prior information to regularize this ill-posed problem. The joint fusion and unmixing problem is then formulated as maximizing the joint posterior distribution with respect to the endmember signatures and abundance maps, This optimization problem is attacked with an alternating optimization strategy. The two resulting sub-problems are convex and are solved efficiently using the alternating direction method of multipliers. Experiments are conducted for both synthetic and semi-real data. Simulation results show that the proposed unmixing based fusion scheme improves both the abundance and endmember estimation comparing with the state-of-the-art joint fusion and unmixing algorithms.

show abstract

“…Katışım temelli yöntemlerin pan keskinleştirilmiş yöntemler üzerinde en temel avantajı, hiperspektral imgeye yüksek çözünürlüklü imgeyle sadece örtüştüğü bantlar için değil tüm bantları için yüksek çözünürlük etkisinin aktarılabilmesidir [5,6].…”

Section: Introductionunclassified

Unmixing-based fusion of hyperspectral images with high spatial resolution images

Gerçek

Çeşmeci

Güllü

et al. 2013

2013 21st Signal Processing and Communications Applications Conference (SIU)

View full text Add to dashboard Cite

Özetçe-Hiperspektral görüntüler çok yüksek spektral çözünürlükte veri sağlamakla birlikte teknik kısıtlardan dolayı düşük uzamsal çözünürlüğe sahiptir. Bu görüntülerin yüksek uzamsal çözünürlüklü görüntülerle kaynaştırılması hem spektral hem de uzamsal çözünürlüğü yüksek zengin içerikli veriler elde edilmesini sağlar. Bu çalışmada düşük uzamsal çözünürlüğe sahip hiperspektral görüntülerin çözünürlüklerinin artırımı amacıyla yüksek uzamsal çözünürlüğe sahip çok bantlı (multispektral) görüntülerle kaynaştırılmasında spektral katışım temelli kaynaştırma yöntemleri önerilmektedir. Buna göre, hiperspektral görüntüden çıkartılan son elemanlar, yüksek çözünürlüklü görüntüye adapte edilmekte ve elde edilen yüksek çözünürlüklü katışım oranları kaynaştırılmış görüntüyü elde etmekte kullanılmaktadır. Yöntem sentetik ve gerçek olmak üzere hiperspektral ve çok bantlı bileşenlerin girdi olarak kullanıldığı iki veri setinde test edilmiştir. Yöntem, görüntü kaynaştırmada kullanılan klasik yöntemlere göre daha fazla başarım sağlamıştır. Anahtar kelimeler -Hiperspektral; çok bantlı; kaynaştırma; çözünürlük; spektral katışım; son eleman.Abstract-Hyperspectral images having very high spectral resolution are subject to low spatial resolution due to technical constraints. Fusion of hyperspectral images with high resolution multispectral images produces high information-content, high spectral and spatial resolution images. In this study for spatial resolution enhancement of hyperspectral images we propose unmixing-based approaches of fusion with high spatial resolution images. Accordingly; end members extracted out of hyperspectral images are adjusted to multispectral images and they are used to derive high resolution abundances to end up with a fused image. Method is applied on two datasets with hyperspectral and multispectral components as input one being a synthetic and other a real dataset. Method produced better accuracy over conventional methods used in image fusion. Bu çalışma TÜBİTAK tarafından 111E052 no'lu proje kapsamında desteklenmiştir. 978-1-4673-5563-6/13/$31.00 ©2013 IEEE a b c d e f Şekil 3: Kaynaştırma sonucunda oluşan bantların RGB (31-20-13. bantlar) gösterimi a) orijinal Hyperion, b) orijinal IKONOS c) SFIM, d) SSCN, e) FCLS temelli kaynaştırma f) bulanık temelli kaynaştırma

show abstract

Hyperspectral Image Resolution Enhancement Based on Spectral Unmixing and Information Fusion

Cited by 21 publications

References 9 publications

Fusion of Hyperspectral and Panchromatic Images Using Spectral Unmixing Results

Fusion of Hyperspectral and Panchromatic Images Using Spectral Unmixing Results

Multiband Image Fusion Based on Spectral Unmixing

Unmixing-based fusion of hyperspectral images with high spatial resolution images

Contact Info

Product

Resources

About