Two Endmember Extraction Algorithms with Combined Spatial and Spectral Domain TM Image
WANG Jie1,2, YANG Liao1*, SHEN Jin-xiang1,2, WU Xiao-bo1,2，GUO Peng-cheng1,2
1. Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi 830011, China 2. Graduate University of Chinese Academy of Sciences, Beijing 100049, China
Abstract：Based on a few bands and unabundant spectral information of TM remote sensing image, two endmember extraction algorithms are put forward. First, spatial split endmember extraction algorithm, which firstly browses the image, based on the complexity of objects, divides the image into different blocks, then uses hourglass algorithm to extract endmembers. Second, region continuity algorithm, also based on dividing-into-blocks idea, which uses extraction and classification of homogenous object algorithm and spectral correlation energy level matching algorithm to extract endmembers. Finally, comparing the two algorithms, spatial split endmember extraction algorithm runs fast, with little prior knowledge, however, the probability of error extraction endmembers exists; and region continuity algorithm’s precision is higher, needs for prior knowledge, and the segment process is slow. Experimental results show that both spatial-and-spectral combined endmember extraction algorithms can effectively solve the large regional scale, multispectral endmember extraction problem, and have broad application prospects.
[1] GENG Xiu-rui(耿修瑞). Target Detection and Classification for Hyperspectral Image(高光谱影像目标探测与分类). Beijing: Institute of Remote Sensing Applications Chinese Academy of Sciences(中国科学院遥感应用研究所), 2005. [2] Green A A, Berman M, Switzer P, et al. IEEE Transaction on Geoscience and Remote Sensing, 1988, 26(1): 65. [3] Chang Chein-I, Cheng Chao, Liu Weimin, et al. IEEE Transaction on Geoscience and Remote Sensing, 1988, 44(10): 2804. [4] Ketting R L, Iandgrebe D A. IEEE Transactions on Geosciences and Remote Sensing, 1976, 14(1): 19. [5] TONG Qing-xi, ZHANG Bing, ZHENG Lan-fen(童庆禧，张 兵，郑兰芬). The Principles and Applications of Hyperspectral Remote Sensing(高光谱遥感原理与应用), Beijing: Higher Education Press(北京：高等教育出版社), 2006. 6. [6] WANG Qin-jun(王钦军). Target Detection Algorithms in Hyperion/Multispectral Remote Sensing and Their Application in Rock Types Detection(高/多光谱遥感目标识别算法及其在岩性目标提取中的应用). Beijing: Institute of Remote Sensing Applications Chinese Academy of Sciences(北京：中国科学院遥感应用研究所), 2006. [7] GENG Xiu-rui(耿修瑞). Several Mathematical Principles on Information Extraction for Hyperspectral Imagery(高光谱遥感信息提取若干数学原理). Beijing: Beijing Normal University Press(北京：北京师范大学出版社), 2007. [8] Chen Fang, Tang Jun-Mei. International Journal of Remote Sensing, 2009, 30(22): 6061. [9] Chang Chein-I. Hyperspectral Imaging: Techniques for Spectral Detection and Classification. New York: Kluwer Academic/Plenum Publishers, 2003. 41 [10] Mark Berman, Harri Kiiveri, Ryan Lagerstrom, et al. IEEE on Transactions on Geosciences and Remote Sensing, 2004, 42(10): 2085. [11] Alina Zare, Paul Gader. IEEE Transactions on Geosciences and Remote Sensing Letters, 2007, 4(3): 446. [12] Bateson C Ann, Gregory P Asner, Carol A Wessman. IEEE Transactions on Geosciences and Remote Sensing, 2000, 38(2): 1083.
