A nonlinear spectral mixture model for hyperspectral imagery based on secondary scattering
YU Xianchuan1, LI Jianguang1,2, XU Jindong1, ZHANG Libao1, HU Dan1
1. Beijing Normal University, College of Information Science and Technology, Beijing 100875, China;
2. Communication University of China, Information Enginering School, Beijing 100024, China
As the linear mixture model cannot well characterize the resultant mixed spectra due to the complicated relations between different ground objects and the effect of atmospheric scattering, a nonlinear spectral mixture model-secondary scattering model is proposed in this paper. Computer simulated images and AVIRIS hyperspectral images of Cuprite district in America were tested, and the experimental results show that the decompostion result of the proposed model are much more precise than that of the traditional linear spectral mixture model.
余先川, 李建广, 徐金东, 张立保, 胡丹. 基于二次散射的高光谱遥感图像光谱非线性混合模型[J]. 国土资源遥感, 2013, 25(1): 18-25.
YU Xianchuan, LI Jianguang, XU Jindong, ZHANG Libao, HU Dan. A nonlinear spectral mixture model for hyperspectral imagery based on secondary scattering. REMOTE SENSING FOR LAND & RESOURCES, 2013, 25(1): 18-25.
[1] Schweizer S M,Moura J M F.Hyperspectral imagery:Clutter adaptation in anomaly detection[J].IEEE Tran on Information Theory,2000,46(5):1855-1871.[2] 童庆禧,张兵,郑兰芬.高光谱遥感——原理、技术与应用[M].北京:高等教育出版社,2006:166-169. Tong Q X,Zhang B,Zheng L F.Hyperspectral remote sensing[M].Beijing:Higher Education Press,2006:166-169.[3] Keshava N,Mustard J.Spectral unmixing[J].IEEE Signal Processing Mag,2002,19(1):44-57.[4] Craig M.Minimum volume transforms for remotely sensed data[J].IEEE Trans Geosci and Remote Sensing,1994,32(3):542-552.[5] Nascimento J M P,Bioucas-Dias J M.Does independent component analysis play a role in unmixing hyperspectral data?[J].IEEE Trans Geosci and Remote Sensing,2005,43(1):175-187.[6] Jia S,Qian Y.Constrained nonnegative matrix factorization for hyperspectral unmixing[J].IEEE Trans Geosci and Remote Sensing,2009,47(1):161-173.[7] Zortea M,Plaza A.Spatial preprocessing for endmember extraction[J].IEEE Trans Geosci and Remote Sensing,2009,47(8):2679-2693.[8] Ghosh G,Kumar S,Saha S K.Hyperspectral satellite data in mapping salt-affected soils using linear spectral unmixing analysis[J].Journal of the Indian Society of Remote Sensing,2012,40(1):129-136.[9] Liu K H,Wong E,Du E Y,et al.Kernel-based linear spectral mixture analysis [J].IEEE Trans Geosci and Remote Sensing,2012,9(1):129-133.[10] Deng Y B,Fan F L,Chen R R.Extraction and analysis of impervious surfaces based on a spectral unmixing method using Pearl River Delta of China landsat TM/ETM+ imagery from 1998 to 2008[J].Sensors,2012,12(2):1846-1862.[11] Iordache M D,Bioucas-Dias J M.Sparse unmixing of hyperspectral data[J].IEEE Trans Geosci and Remote Sensing,2011,49(6):2014-2039.[12] RSI(Research Systems Inc.).ENVI user's guide version 4.0[S].Boulder,CO 80301 USA,2003.[13] Heinz D C,Chang C I.Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery[J].IEEE Tran GRS,2001,39(3):529-545.[14] Plaza J,Plaza A,Martinez P,et al.Nonlinear mixture models for analyzing laboratory simulated-forest hyperspectral data[J].Proc SPIE Image and Signal Processing for Remote Sensing IX,2004,52(38):480-487.[15] AVIRIS data of Cuprite distuict,America.http://aviris.jpl.nasa.gov/html/aviris.freedata.html.[16] Vane G,Green R,Chrien T G,et al.The airborne visible/infrared imaging spectrometer(AVIRIS)[J].Remote Sensing of the Environment,1993,44(2/3):127-143.[17] Nascimento J,Dias J B.Vertex component analysis:A fast algorithm to unmix hyperspectral data[J].IEEE Trans Geosci and Remote Sens,2005,43(4):175-187.