Spectral Unmixing for the Classification of Hyperspectral Images at a Finer Spatial Resolution

被引:142
作者
Villa, Alberto [1 ,2 ]
Chanussot, Jocelyn [1 ]
Benediktsson, Jon Atli [2 ]
Jutten, Christian [1 ]
机构
[1] Grenoble Inst Technol INP, Signal & Image Dept, GIPSA Lab, F-38031 Grenoble 1, France
[2] Univ Iceland, Fac Elect & Comp Engn, IS-101 Reykjavik, Iceland
关键词
Hyperspectral data; simulated annealing; source separation; spatial regularization; spatial resolution improvement; EXTRACTION;
D O I
10.1109/JSTSP.2010.2096798
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The problem of classification of hyperspectral images containing mixed pixels is addressed. Hyperspectral imaging is a continuously growing area of remote sensing applications. The wide spectral range of such imagery, providing a very high spectral resolution, allows to detect and classify surfaces and chemical elements of the observed image. The main problem of hyperspectral data is the (relatively) low spatial resolution, which can vary from a few to tens of meters. Many factors make the spatial resolution one of the most expensive and hardest to improve in imaging systems. For classification, the major problem caused by low spatial resolution are the mixed pixels, i.e., parts of the image where more than one land cover map lie in the same pixel. In this paper, we propose a method to address the problem of mixed pixels and to obtain a finer spatial resolution of the land cover classification maps. The method exploits the advantages of both soft classification techniques and spectral unmixing algorithms, in order to determine the fractional abundances of the classes at a sub-pixel scale. Spatial regularization by simulated annealing is finally performed to spatially locate the obtained classes. Experiments carried out on synthetic real data sets show excellent results both from a qualitative and quantitative point of view.
引用
收藏
页码:521 / 533
页数:13
相关论文
共 34 条
[1]  
[Anonymous], 2009, Kernel methods for remote sensing data analysis
[2]  
[Anonymous], P SUMM 8 JPL AIRB EA
[3]  
ARONSZAJN N, 1950, THEORY REPRODUSING K
[4]  
Atkinson P.M., 1997, INNOVATIONS GIS 4, P166, DOI 10.1201/9781482272956-25/mapping-sub-pixelboundaries-remotely-sensed-images-peter-atkinson
[5]   Fuzzy rule-based classification of remotely sensed imagery [J].
Bárdossy, A ;
Samaniego, L .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2002, 40 (02) :362-374
[6]   LIBSVM: A Library for Support Vector Machines [J].
Chang, Chih-Chung ;
Lin, Chih-Jen .
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)
[7]  
Clark R. N., 2007, USGS DIGITAL SPECTRA, V231
[8]   A COEFFICIENT OF AGREEMENT FOR NOMINAL SCALES [J].
COHEN, J .
EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 1960, 20 (01) :37-46
[9]   Synergy in remote sensing - what's in a pixel? [J].
Cracknell, AP .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1998, 19 (11) :2025-2047
[10]   Abundance estimation of spectrally similar minerals by using derivative spectra in simulated annealing [J].
Debba, Pravesh ;
Carranza, Emmanuel J. M. ;
van der Meer, Freek D. ;
Stein, Alfred .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2006, 44 (12) :3649-3658