Land Cover Classification with SVM Based on NWFE and Texture Features
CUI Lin-lin1,2, LUO Yi1, BAO An-ming1
1. Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi 830011, China;
2. Graduate School, Chinese Academy of Sciences, Beijing 100049, China
Abstract:Land cover classification based on remote sensing image is of significant importance to agriculture, forestry and environment monitoring. Algorithm of remote sensing information retrieval is always an important research topic in this field. This paper made an effort to combine the Nonparametric Weighted Feature Extraction (NWFE) and texture features with the Support Vector Machines (SVM) so as to achieve a higher classification precision. The combined approach was applied to land cover classification of the Manasi River oasis in Xinjiang in 2006, and was compared with approaches of SVM based on Principal Component Analysis (PCA) and texture features and based on original bands and texture features. The results show that the method of SVM combined with NWFE and texture features can capture not only the distribution of land cover but also the difference among land cover types. An overall classification accuracy of 89.17% is obtained, which is better than those of two other classification results.
崔林林, 罗毅, 包安明. NWFE结合纹理特征的SVM土地覆被分类方法研究[J]. 国土资源遥感, 2012, 24(1): 36-42.
CUI Lin-lin, LUO Yi, BAO An-ming. Land Cover Classification with SVM Based on NWFE and Texture Features. REMOTE SENSING FOR LAND & RESOURCES, 2012, 24(1): 36-42.
[1] 王静.土地资源遥感监测与评价方法[M].北京:科学出版社,2006:60-61.[2] 喻小倩,刘娜,李红,等.基于线性光谱混合分解和最大似然分类相结合的土地覆被分类——以红寺堡灌区为例[J].国土资源遥感,2010(1):96-100.[3] 孙秀邦,范伟,严平,等.遥感影像土地覆被分类研究进展[J].中国农学通报,2007,23(9):607-610.[4] 关泽群,刘继琳,崔卫红.利用地物的几何属性改进影像分类效果[J].国土资源遥感,2001(1):31-35.[5] 钱乐祥,崔海山.运用归一化光谱混合模型分析城市地表组成[J].国土资源遥感,2006(2):64-68.[6] 汪闽,万其明,张大骞,等.光谱、形状特征结合的多精度图像分割算法与应用[J].地球信息科学学报,2010(2):2261-2268.[7] Kuo B C,Landgrebe D A.Improved Statistics Estimation and Feature Extraction for Hyperspectral Data Classification[D].Ph D Thesis and School of Electrical and Computer Engineering,Purdue University,West Lafayette,IN,Tech Rep TR-ECE,2001:1-6.[8] 王硕,周激流,彭博.基于API序列分析和支持向量机的未知病毒检测[J].计算机应用,2010,27(8):1942-1943.[9] 祁亨年,杨建刚,方露明.基于多类支持向量机的遥感图像分类及其半监督式改进策略[J].复旦学报:自然科学版,2004,43(5):781-784.[10] 朱志宇,张冰,刘维亭.基于模糊支持向量机的语音识别方法[J].计算机工程,2006,32(2):180-182.[11] Tadjudin S,Landgrebe D A.Classification of High Dimensional Data with Limited Training Samples[D].Purdue University,West Lafayette,IN,TR-EE 98-8,April,1998:35-82.[12] 唐发明,王仲东,陈绵云.支持向量机多分类分类算法研究[J].控制与决策,2005,20(7):746-749,754.[13] 中国科学院计算机网络信息中心国际科学数据服务平台[DB/OL].[2011-05-31].http://datamirror.csdb.cn.[14] Gao Y N,Zhang W C.Variable Empirical Coefficient Algorithm for Removal of Topographic Effects on Remotely Sensed Data from Rugged Terrain[C]//IGARSS’2007,IEEE,2007:4733-4736.[15] 祁享年.支持向量机及其应用研究综述[J].计算机工程,2004,30(10):6-9.[16] Richards J A,Jia X P.Remote Sensing Digital Image Analysis:An Introduction,4th ed.[M].Berlin,Germany:Springer-Verlag,2006.[17] 舒宁.卫星遥感影像纹理分析与分形分维方法[J].武汉测绘科技大学学报,1998,23(4):370-373.[18] Barald A,Parminggian F.An Investigation on the Texture Characteristics Associated with Gray Level Co-occurrence Matrix Statistical Parameters[J].IEEE Trans on Geosciences and Remote Sensing,1995,32(2):293-303.[19] Roli F,Fumera G.Support Vector Machines for Remote Sensing Image Classification[C]//Proc of SPIE,2001:160-166.[20] Vapnik V N.The Nature of Statistical Learning Theory[M].New York:Springer,2000.[21] 谢承旺.不同种类支持向量机算法的比较研究[J].小型微型计算机系统,2008,29(1):106-109.[22] Keerthi S S,Lin C I.Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel[J].Neural Computation,2003,15(7):1667-1689.