Integration of Spatial-Spectral Information Based Endmember Extraction for Hyperspectral Image
KONG Xiang-bing1, 2, SHU Ning1, GONG Yan1, WANG Kai1
1. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China 2. Key Laboratory of the Loess Plateau Soil Erosion and Water Loss Process and Control, Ministry of Water Resources, Yellow River Institute of Hydraulic Research, Zhengzhou 450003, China
摘要: 端元光谱提取是高光谱影像混合像元分解的关键。现有的端元提取方法多是仅利用了影像的光谱信息,忽略了像元间的空间相关性。现有研究基础上,提出了一种结合影像空间和光谱信息的高光谱影像端元光谱自动提取方法(integration of spatial-spectral information based endmember extraction,ISEE)。该方法首先进行影像子空间划分以增强影像局部的光谱信息特征,然后通过特征空间投影分析获得影像候选端元,最后依次在影像空间信息约束下和端元光谱信息约束下进行优化,得到最终的影像端元光谱集。仿真高光谱影像和真实高光谱影像的实验结果表明,结合影像空间和光谱信息的ISEE方法是有效的,且比一些常用方法提取的端元光谱更为准确。
关键词:高光谱影像;端元提取;正交子空间投影;空间信息
Abstract:In the present paper, a novel algorithm is proposed to integrate both spatial and spectral information for automatic EE (Integration of spatial-spectral information based endmember extraction, ISEE). At first, the image is divided into some subspaces for improvement of spectral contrast. Then, the subset of the image is projected to the feature space related to the image endmembers, and the candidate endmember spectra are extracted through orthogonal subspace projection analysis. At last, the endmember spectra are refined under the constraint of image spatial context and spectral information. The performances of different endmember extraction methods are compared using both synthetic hyperspectral image and real hyperspectral image. The experimental results demonstrate that ISEE incorporated with spatial information is effective, and the endmember spectra extracted by ISEE are more accurate than by some common EE methods.
Key words:Hyperspectral remote sensing;Endmember extraction;Orthogonal subspace projection;Spatial information
孔祥兵1, 2,舒 宁1,龚 龑1,王 凯1 . 结合空间和光谱信息的高光谱影像端元光谱自动提取 [J]. 光谱学与光谱分析, 2013, 33(06): 1647-1652.
KONG Xiang-bing1, 2, SHU Ning1, GONG Yan1, WANG Kai1 . Integration of Spatial-Spectral Information Based Endmember Extraction for Hyperspectral Image . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(06): 1647-1652.
[1] Boardman W, Kruse F A, Green R O. Mapping Target Signatures Via Partial Unmixing of AVIRIS Data, 1995. 23. [2] Neville R A, Staenz K, Szeredi T, et al. Automatic Endmember Extraction from Hyperspectral Data for Mineral Exploration, 1999. 21. [3] Nascimento José M P, José M Bioucas Dias. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(4): 898: 910. [4] Harsanyi J C, Chang C I. IEEE Trans. Geosci. Remote Sens., 1994, 32(4): 779. [5] Berman M, Kiiveri H, Lagerstrom R, et al. IEEE Trans. Geosci. Remote Sens., Oct., 2004, 42(10): 2085. [6] Chang C I, Wu C C, Liu W, et al. IEEE Trans. Geosci. Remote Sens., Oct., 2006, 44(10): 2804. [7] Plaza A, Martinez P, Perez R M, et al. IEEE Transactions on Geoscience and Remote Sensing, September, 2002, 40(9): 2025. [8] Rogge D M, Rivard B, Zhang J, et al. Remote Sens. Environ., 2007, 110(3): 287. [9] Zortea M, Plaza A. IEEE T. Geoscience and Remote Sensing, 2009, 48(8): 2679. [10] Mei S H, He M Y, Wang Z Y, et al. Ieee Transactions on Geoscience and Remote Sensing, 2010, 48(9): 3434. [11] GONG Yan, SHU Ning(龚 龑, 舒 宁). Geomatics and Information Science of Wuhan University(武汉大学学报·信息科学版), 2008, 33(3): 310. [12] Bateson C A, Asner G P, and Wessman C A. IEEE Trans. Geosci. Remote Sens., Mar., 2000, 38(2): 1083. [13] Swayze G, Clark R, Sutley S, et al. Nevada, 1992, (1): 47. [14] Chang C I, Du Q. Ieee Transactions on Geoscience and Remote Sensing, 2004, 42(3): 608. [15] KONG Xiang-bing, SHU Ning, TAO Jian-bin, et al(孔祥兵,舒 宁,陶建斌,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2011, 31(8): 2166. [16] Sohn Youngsinn,Rebello N. Sanjay. Photogrammetric Engineering and Remote Sensing, 2002, 68(12): 1271. [17] Heinz D, Chang C I. IEEE Trans. on Geoscience and Remote Sensing, 2001, 39(3): 529.