Hyperspectral Remote Sensing Image Classification Based on SVM Optimized by Clonal Selection
LIU Qing-jie1, 2, JING Lin-hai1, 2, WANG Meng-fei3, LIN Qi-zhong1, 2
1. Center for Earth Observation and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China 2. Key Laboratory of Digital Earth, Chinese Academy of Sciences, Beijing 100094, China 3. China Aero Geophysical Survey and Remote Sensing Center for Land and Resources, Beijing 100083, China
Abstract:Model selection for support vector machine (SVM) involving kernel and the margin parameter values selection is usually time-consuming, impacts training efficiency of SVM model and final classification accuracies of SVM hyperspectral remote sensing image classifier greatly. Firstly, based on combinatorial optimization theory and cross-validation method, artificial immune clonal selection algorithm is introduced to the optimal selection of SVM (CSSVM) kernel parameter σ and margin parameter C to improve the training efficiency of SVM model. Then an experiment of classifying AVIRIS in India Pine site of USA was performed for testing the novel CSSVM, as well as a traditional SVM classifier with general Grid Searching cross-validation method (GSSVM) for comparison. And then, evaluation indexes including SVM model training time, classification overall accuracy (OA) and Kappa index of both CSSVM and GSSVM were all analyzed quantitatively. It is demonstrated that OA of CSSVM on test samples and whole image are 85.1% and 81.58, the differences from that of GSSVM are both within 0.08% respectively; And Kappa indexes reach 0.821 3 and 0.772 8, the differences from that of GSSVM are both within 0.001; While the ratio of model training time of CSSVM and GSSVM is between 1/6 and 1/10. Therefore, CSSVM is fast and accurate algorithm for hyperspectral image classification and is superior to GSSVM.
[1] YANG Guo-peng, YU Xu-chu, CHEN Wei, et al(杨国鹏, 余旭初, 陈 伟, 等). Journal of Remote Sensing(遥感学报), 2008, 12(4): 579. [2] Maheshn Pal, Giles M. Foody IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(5): 2297. [3] Giorgos Mountrakis, Jungho I M, Caesar Ogole. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66: 247. [4] TAN Kun, DU Pei-jun(谭 琨, 杜培军). J. Infrared Millim. Waves(红外与毫米波学报), 2008, 27(2): 123. [5] ZHAO Shu-he, FENG Xue-zhi, DU Jin-kang, et al(赵书河, 冯学智, 都金康, 等). Journal of Remote Sensing(遥感学报), 2003, 7(5): 407. [6] Pabitra Mitra, B Uma Shankar, Sanka K Pal. Pattern Recognition Letters, 2004, 25: 1067. [7] Zhang Hongsheng, Zhang Yuanzhi, Lin Hui. International Journal of Applied Earth Observation and Geoinformation, 2012, 18: 148. [8] Shigeo Abe. Support Vector Machines for Pattern Classification (Advances in Pattern Recognition) (Second Edition). Springer, 2010. [9] YAO Quan-zhu, TIAN Yuan(姚全珠, 田 元). Computer Engineering(计算机工程), 2008, 34(15): 223. [10] Friedrichs F, Igel C. Evolutionary Tuning of Multiple SVM Parameters[C]. Proceedings of the Twelfth European Symposium on Artificial Neural Networks (ESANN2004), 2004. 519. [11] De Castro L N, Von Zuben F J. The Clonal Selection Algorithm with Engineering Application. Proceedings of Genetic and Evolutionary Computation Conference, Las Vegas, Nevada, USA, 2000. 36. [12] HE Ling-min, SHEN Zhang-quan, KONG Fan-sheng, et al(何灵敏, 沈掌泉, 孔繁胜, 等). Journal of Image and Graphics(中国图象图形学报), 2007, 12(4): 648. [13] Landgrebe D. Signal Theory Method in Multispectral Remote Sensing[M].Hoboken, NJ: Wiley, 2003. [14] Li Cheng Hsuan, Kuo Bor-Chen, Lin Chin Teng, et al. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(3): 784.