[1]李士进,常纯,余宇峰,等.基于多分类器组合的高光谱图像波段选择方法[J].智能系统学报,2014,9(3):372-378.[doi:10.3969/j.issn.1673-4785.201404006]
LI Shijin,CHANG Chun,YU Yufeng,et al.Multi-classifier combination-based hyperspectral band selection[J].CAAI Transactions on Intelligent Systems,2014,9(3):372-378.[doi:10.3969/j.issn.1673-4785.201404006]
点击复制
LI Shijin,CHANG Chun,YU Yufeng,et al.Multi-classifier combination-based hyperspectral band selection[J].CAAI Transactions on Intelligent Systems,2014,9(3):372-378.[doi:10.3969/j.issn.1673-4785.201404006]
基于多分类器组合的高光谱图像波段选择方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
9
期数:
2014年第3期
页码:
372-378
栏目:
学术论文—智能系统
出版日期:
2014-06-25
- Title:
- Multi-classifier combination-based hyperspectral band selection
- Keywords:
- hyperspectral remote sensing; pattern classification; band selection; multiple classifiers combination; error diversity; dimension reduction
- 分类号:
- TP18
- 摘要:
- 由于高光谱数据具有波段多, 数据量大等特点, 对其进行降维处理成为高光谱遥感研究的一个重要问题。提出一种基于多分类器组合的高光谱波段选择方法, 该方法通过遗传算法良好的寻优能力获得若干组较优初始波段子集, 在此基础上使用这些波段子集训练若干个基分类器, 进而利用改进的基于相同错误差异性度量的分类器选择方法选出部分较优分类器, 实现波段选择的目的;最终通过局部精度分析的动态分类器选择实现多分类器组合决策。在公共测试数据集上的实验结果表明:与以往直接选择最优波段子集方法相比, 提出的算法能够选择更多具有鉴别能力的波段, 明显提高了分类正确率。
- Abstract:
- Due to the multi-waveband and massive data characteristics of hyperspectral data, dimension reduction is becoming a distinct problem in regards to hyperspectral remote sensing research. A hyperspectral band selection algorithm has been proposed based on a multi-classifier combination. This algorithm obtains several groups of sub-optimal initial waveband subsets through a genetic algorithm, which has better optimizing ability and on this basis trains several base classifiers with these waveband subsets, and further selects several member classifiers from the initial classifier pool by using an improved classifier selection method that is based on same-fault measures, realizing the purpose of the wave band selection. And finally, the multi-classifier combination decision is made through dynamic classifier selection based on the analysis of local classification accuracy (DCS-LA). The experimental results regarding the Indian Pine benchmark data set show that this new method can select these bands with more discriminative information and obviously improve the accuracy of the classification process.
- 参考文献/References:
-
[1] LANDGREBE D A. Signal theory methods in multispectral remote sensing[M]. John Wiley & Sons, 2005:5-12.
[2] SERPICO S B, BRUZZONE L. A new search algorithm for feature selection in hyperspectral remote sensing images[J].IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(7):1360-1367.
[3] BAZI Y, MELGANI F. Toward an optimal SVM classification system for hyperspectral remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(11):3374-3385.
[4] SOTOCA J M, PLA F. Hyperspectral data selection from mutual information between image bands[M]. Berlin:Springer, 2006:853-861.
[5] GUO B, DAMPER R I, GUNN S R, et al. A fast separability-based feature-selection method for high-dimensional remotely sensed image classification[J]. Pattern Recognition, 2008, 41(5):1653-1662.
[6] 戴宏亮, 戴道清.基于ETAFSVM的高光谱遥感图像自动波段选择和分类[J].计算机科学, 2009, 36(4):268-272.DAI Hongliang, DAI Daoqing. Automatic band selection and classification of hyperspectral remote sensing images based on ETAFSVM[J]. Computer Science, 2009, 36(4):268-272.
[7] 吴昊, 李士进, 林林, 等.多策略结合的高光谱图像波段选择新方法[J]. 计算机科学与探索, 2010, 4(5):464-472.WU Hao, LI Shijin, LIN Lin, et al. Multiple-strategy combination based approach to band selection for hyper-spectral image classification[J]. Journal of Frontiers of Computer Science and Technology, 2010, 4(5):464-472.
[8] YANG He, DU Qian, SU Hongjun, et al. An efficient method for supervised hyperspectral band selection[J]. IEEE Geosci Remote Sensing Lett, 2011, 8(1):138-142.
[9] 葛亮, 王斌, 张立明.基于波段聚类的高光谱图像波段选择[J].计算机辅助设计与图形学学报, 2012, 24(11):1447-1454.GE Liang, WANG Bing, ZHANG Liming. Band selection based on band clustering for hyperspectral imagery[J]. Journal of Computer-Aided Design & Computer Graphics, 2012, 24(11):1447-1454.
[10] 王立国, 魏芳洁.结合遗传算法和蚁群算法的高光谱图像波段选择[J].中国图象图形学报, 2013, 18(2):235-242.WANG Liguo, WEI Fangjie.Band selection for hyperspectral imagery based on combination of genetic algorithm and ant colony algorithm[J].Journal of Image and Graphics, 2013, 18(2):235-242.
[11] LI Shijin, ZHU Yuelong, WAN Dingsheng, et al.Spectral similarity-preserving hyperspectral band selection[J]. Remote Sensing Letters, 2013, 4(10):969-978.
[12] SERPICO S B, MOSER G. Extraction of spectral channels from hyperspectral images for classification purposes[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(2):484-495.
[13] ZHOU Z H. Ensemble Methods:Foundations and algorithms[M]. Boca Raton:CRC Press, 2012.
[14] KUNCHEVA L I. Switching between selection and fusion in combining classifiers:an experiment[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B:Cybernetics, 2002, 32(2):146-156.
[15] KUNCHEVA L I, WHITAKER C J. Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy[J]. Machine Learning, 2003, 51(2):181-207.
[16] WOODS K, KEGELMEYER JR W P, BOWYER K. Combination of multiple classifiers using local accuracy estimates[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(4):405-410.
[17] ZHOU Z H, WU J X, TANG W. Ensembling neural networks:many could be better than all[J]. Artificial Intelligence, 2002, 137(1/2):239-263.
[18] 张春霞, 张讲社.选择性集成学习算法综述[J].计算机学报, 2011, 34(8):1399-1410.ZHANG Chunxia, ZHANG Jiangshe.A survey of selective ensemble learning algorithms[J]. Chinese Journal of Computers, 2011, 34(8):1399-1410.
[19] AKSELA M, LAAKSONEN J. Using diversity of errors for selecting members of a committee classifier[J]. Pattern Recognition, 2006, 39(4):608-623.
[20] BENEDIKTSSON J A, CHANUSSOT J, FAUVEL M. Multiple classifier systems in remote sensing:from basics to recent developments[C]//Proceedings of the 7th International Conference on Multiple Classifier Systems.:Berlin:Springer-Verlag, 2007:501-512.
[21] MARINA S, ROBERT P W.Combining feature subsets in feature selection[C]//Proceedings of the 5th International Conference on Multiple Classifier Systems. Berlin, 2005:165-175.
[22] XAVIER C, BJöRN W, JON A B, et al. Ensemble strategies for classifying hyperspectral remote sensing data[C]//Proceedings of the 9th International Conference on Multiple Classifier Systems, Berlin:Springer-Verlag, 2009:62-71.
[23] DU Peijun, ZHANG Wei, SUN Hao. Multiple classifier combination for hyperspectral remote sensing image classification[C]//Proceedings of the 9th International Conference on Multiple Classifier Systems, Berlin, 2009:52-61.
- 相似文献/References:
-
[1]王立国,赵亮,石瑶.基于最大最小距离的高光谱遥感图像波段选择[J].智能系统学报,2018,13(1):131.[doi:10.11992/tis.201703023]
WANG Liguo,ZHAO Liang,SHI Yao.Maximin distance algorithm-based band selection for hyperspectral imagery[J].CAAI Transactions on Intelligent Systems,2018,13():131.[doi:10.11992/tis.201703023]
[2]李景灿,丁世飞.基于人工鱼群算法的孪生支持向量机[J].智能系统学报,2019,14(6):1121.[doi:10.11992/tis.201905025]
LI Jingcan,DING Shifei.Twin support vector machine based on artificial fish swarm algorithm[J].CAAI Transactions on Intelligent Systems,2019,14():1121.[doi:10.11992/tis.201905025]
[3]刘金平,周嘉铭,贺俊宾,等.面向不均衡数据的融合谱聚类的自适应过采样法[J].智能系统学报,2020,15(4):732.[doi:10.11992/tis.201909062]
LIU Jinping,ZHOU Jiaming,HE Junbin,et al.Spectral clustering-fused adaptive synthetic oversampling approach for imbalanced data processing[J].CAAI Transactions on Intelligent Systems,2020,15():732.[doi:10.11992/tis.201909062]
备注/Memo
收稿日期:2014-04-16。
基金项目:国家自然科学基金资助项目(61170200 )
作者简介:常纯,女,1989年生,硕士研究生,主要研究方向为图像处理与模式识别。
通讯作者:李士进,男,1973年生,教授,博士,主要研究方向为模式识别与计算机视觉,E-mail:lishijin@hhu.edu.cn。
更新日期/Last Update:
1900-01-01