计算机科学 ›› 2014, Vol. 41 ›› Issue (12): 283-287.doi: 10.11896/j.issn.1002-137X.2014.12.061
任越美,李垒,张艳宁,魏巍,李映
REN Yue-mei,LI Lei,ZHANG Yan-ning,WEI Wei and LI Ying
摘要： 针对高光谱图像分类过程中数据波段多以及信息冗余量大引起的处理速度慢及Hughes现象等问题,提出了一种基于多粒子协同进化算法进行高光谱图像自动波段选择与分类的方法:使用多粒子群协同进化算法 搜索 特征子集,对粒子群优化算法进行改进,定义新的位置和速度的更新策略,并以支持向量机为分类器, 同时 对特征子集和SVM核函数参数进行优化。在协同搜索过程中,引入遗传算法改善粒子群优化的“早熟”收敛问题,构建了一种新的MPSO-SVM(Multiple particle swarm optimization-SVM)分类模型。对高光谱遥感图像的实验结果表明:MPSO-SVM方法不仅能有效地压缩光谱的特征维数,得到最佳的波段组合,还能得到最优的SVM参数,达到较好的分类效果,提高分类精度。
| [1] Fu Zhou-yu,Antonio R-K.Discriminant Absorption-FeatureLearning for Material Classification [J].IEEE Transaction on Geoscience and Remote Sensing,2011,49(5):1536-1556 [2] Hughes G.On the mean accuracy of statistical pattern recogni-zers [J].IEEE Transaction on Information Theory,1968,14(1):55-63 [3] Dalla Mura M,Villa A,et al.Classification of Hyperspectral Ima-ges by Using Extended Morphological Attribute Profiles and Independent Component Analysis [J].IEEE Geoscience and Remote Sensing Letters,2011,8(3):542-546 [4] 常威威,郭雷,刘坤,等.基于Contourlet变换和主成分分析的高光谱数据噪声消除方法[J].电子与信息学报,2009,31(12):2892-2896 [5] Chen Shi-guo,Zhang Dao-qiang.Semisupervised Dimensionality Reduction With Pairwise Constraints for Hyperspectral Image Classification [J].IEEE Geoscience and Remote Sensing Letters,2011,8(2):369-373 [6] He M,Mei S.Dimension reduction by random projection forendmember extraction [C]∥Proc.IEEE Conference on Industrial Electronics and Applications.Taichung,Jun.2010:2323-2327 [7] Pal M,Foody G M.Feature Selection for Classification of Hyperspectral Data by SVM [J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(5):2297-2307 [8] Li S,Wu H,et al.An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine [J].Knowledge-Based Systems,2011,24(1):40-48 [9] 潘泓,李晓兵,等.一种基于二值粒子群优化和支持向量机的目标检测算法[J].电子与信息学报,2011,33(1):117-121 [10] Chion C,Landry J A.A Genetic programming based Method for Hyperspectral Data Information Extraction:Agricultural Applications [J].IEEE Transaction on Geoscience and Remote Sen-sing,2008,46(8):2446-2457 [11] Ding S.Spectral and wavelet-based feature selection with particle swarm optimization for hyperspectral classification [J].Journal of Software,2011,6(7):1248-1256 [12] Yang H,Du Q,Chen G.Particle swarm optimization-based hyperspectral dimensionality reduction for urban land cover classification [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012,5(2):544-554 [13] Li Yan-shan.A New Bands Selection Algorithm for Hyperspectral Image using Hyperspectral Derivative on Clifford Manifold[J].Information Technology Journal,2012,11(7):904-909 [14] Vapnik V N.Statistical Learning Theory[M].NewYork:Wiley,1998 [15] Mingmin C,Bruzzone L.Semisupervised Classification of Hyperspectral Images by SVMs Optimized in the Primal[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(6):1870-1880 [16] Kennedy J,Eberhart R C.Particle swarm optimization[C]∥Proc.IEEE International Conference on Neutral Networks.Perth,Australia,1995:1942-1948 [17] Asmara A,Krohling R A,Hoffmann F.Parameter Tuning of a Computed-Torque Controller for a 5 Degree of Freedom Robot Arm using Co-evolutionary Particle Swarm Optimization [C]∥Proc.IEEE Conference on Swarm Intelligence Symposium.Pasadena,USA,2005:162-168 [18] Kennedy J,Eberhart R C.A discrete binary version of the particle swarm algorithm[C]∥Proc.IEEE International Conference on Systems,Man,and Cybernetics.Washington,USA,1997:4104-4109 |
| No related articles found! |
|
||
首页