Classification of Hyperspectral Imagery Based on Ant Colony Compositely Optimizing SVM in Spatial and Spectral Features
CHEN Shan-jing1,2,3, HU Yi-hua1,2*, SHI Liang1,2, WANG Lei1,2, SUN Du-juan1,2, XU Shi-long1,2
1. Electronic Engineering Institute,State Key Laboratory of Pulsed Power Laser Technology , Hefei 230037, China 2. Anhui Province Key Laboratory of Electronic Restriction, Hefei 230037, China 3. Department of Astronautics, Electronic Engineering Institute, Hefei 230037, China
Abstract:A novel classification algorithm of hyperspectral imagery based on ant colony compositely optimizing support vector machine in spatial and spectral features was proposed. Two types of virtual ants searched for the bands combination with the maximum class separation distance and heterogeneous samples in spatial and spectral features alternately. The optimal characteristic bands were extracted, and bands redundancy of hyperspectral imagery decreased. The heterogeneous samples were eliminated form the training samples, and the distribution of samples was optimized in feature space. The hyperspectral imagery and training samples which had been optimized were used in classification algorithm of support vector machine, so that the class separation distance was extended and the accuracy of classification was improved. Experimental results demonstrate that the proposed algorithm, which acquires an overall accuracy 95.45% and Kappa coefficient 0.925 2, can obtain greater accuracy than traditional hyperspectral image classification algorithms.
陈善静1,2,3,胡以华1,2*,石 亮1,2,王 磊1,2,孙杜娟1,2,徐世龙1,2 . 空-谱二维蚁群组合优化SVM的高光谱图像分类 [J]. 光谱学与光谱分析, 2013, 33(08): 2192-2197.
CHEN Shan-jing1,2,3, HU Yi-hua1,2*, SHI Liang1,2, WANG Lei1,2, SUN Du-juan1,2, XU Shi-long1,2 . Classification of Hyperspectral Imagery Based on Ant Colony Compositely Optimizing SVM in Spatial and Spectral Features . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(08): 2192-2197.
[1] Chang C I, Safavi H. Pattern Recognition, 2011, 44: 2760. [2] Ritter G X, Urcid G. Information Sciences, 2011, 181: 1787. [3] Wang, L G, Deng L Q. 2009 WRI World Congress on Computer Science and Information Engineering, CSIE, 2009, 7: 144. [4] Demir B, Ertürk S. IEEE Geoscience and Remote Sensing Letters, 2009, 6(4): 840. [5] Sakla W, Chan A, Sakla A. IEEE Geoscience and Remote Sensing Letters, 2011, 8(2): 384. [6] Mathieu F, Benediktsson J A, Chanussot J, et al. IEEE Transactions Geoscience Remote Sensing, 2008, 46(11): 3804. [7] Dorigo M, Birattari M, Stützle T. IEEE Computational Intelligence Magazine, 2006, 11: 28. [8] Dorigo M, Maniezzo V, Colorni A. IEEE Transactions on Systems, Man, and Cybernetics- Part B, 1996, 26(1): 29. [9] Dorigo M, Gambardella L M. IEEE Transactions Evolutionary Computation, 1997, 1(1): 53. [10] Zhang B, Sun X, Gao L R, et al. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(7): 2635. [11] Melgani F, Bruzzone L. IEEE Transactions Geoscience Remote Sensing, 2004, 42(8): 1778. [12] Tarabalka Y, Benediksson J A, Chanussot J. IEEE Transactions Geoscience Remote Sensing, 2009, 47(8): 2973. [13] Pal M, Foody G M. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(5): 2297. [14] Joshua B, Tenenbaum et al. Science, 2000, 290: 2319.