The Study on Blind Unmixing for Hyperspectral Imagery

Abstract:

Hyperspectral is the frontiers of Remote Sensingdevelopment, which plays a more andmore important role in many fields. themixed pixels become an main obstacle to the in depth development forquantification imageryanalysis,This paper presented a novel approach based on independentcomponent analysis for hyperspectralunmixing,it introducing the constraints of abundance nonnegative and abundancesum-to-one，the purpose of our algorithm was not to findindependent components as decomposition results anymore．It developed an abundance modeling technique todescribe the statistical distribution of the data．Themodeling approach is capable of self-adaptation，andcan be applied to hyperspectral images with different characteristics．Experimental results demonstrated that the proposedapproach can obtain more accurate results than the other state-of-the-artapproaches．

• Periodical: Advanced Materials Research (Volumes 779-780)
• Pages: 1770-1773
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.779-780.1770
• Online since: September 2013
• Authors: Zuo Wei Huang, Yuan Jiang Huang
• Keywords: Endmember, Hyperspectral Imagery, Independent Component Analysis (ICA), Mixed Pixel

References

[1] F. Bovolo,L. Bruzzone and L. Carlin. A Novel Techinique for Sub pixel Image Classification based on Support vector Machine[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2983 2999.

DOI: 10.1109/tip.2010.2051632

[2] Chein I Chang, Baohong Ji. Weighted Abundance Constrained Linear Spectral Mixture Analysis[J]. IEEE Transaction on Geoscience and Remote Sensing, 2006, 44(2): 378- 388.

DOI: 10.1109/tgrs.2005.861408

[3] Penn B.S. Using Simulated Annealing to Obtain Optimal Linear Endmember Mixtures of Hyperspectral Data[J]. Computers&Geosciences, 2002, 28(7): 809 817.

DOI: 10.1016/s0098-3004(01)00114-5

[4] Theiler J, Scovel C, Wohlberg B and Foy B R. 2010. Elliptically contoured distributions for anomalous change detection in hyperspectral imagery. Geoscience and Remote Sensing Letters, IEEE, 7(2): 271–275.

DOI: 10.1109/lgrs.2009.2032565

[5] TUngar S G, Pearlman J S, Mendenhall J A and Reuter D. 2003. Overview of the earth observing one(EO-1)mission. Geoscience and Remote Sensing, IEEE Transactions on, 41(6): 1149–1159.

DOI: 10.1109/tgrs.2003.815999

[6] Antonio Plaza and Chein I Chang. Impact of Initialization on Design of Endmember Extraction Algorithms[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(11): 3397 3407.

DOI: 10.1109/tgrs.2006.879538