基于光谱与纹理信息的Worldview-2影像地物分类Land Use /cover Classification of Worldview-2 Images Based on Spectral and Texture Information
章文龙;林贤彪;仝川;曾从盛;
摘要(Abstract)：
高分辨率遥感影像分类是遥感影像处理领域中的一个重要的研究方向.选取Worldview-2影像,分别以光谱信息和光谱结合纹理信息为分类数据,采用最大似然法(MLC)和支持向量机法(SVM)进行监督分类,用混淆矩阵对分类结果进行评价.结果表明,9×9为最佳纹理窗口;SVM法分类精度明显优于MLC法;基于光谱结合纹理信息的分类精度明显优于单纯基于光谱信息的分类结果.辅以影像纹理特征,采用SVM法可以较为有效提取Worldview-2地物信息.
关键词(KeyWords)： Worldview-2影像;纹理特征;SVM;MLC
基金项目(Foundation): 国家基础科学人才培养基金资助项目(J0830521);; 福建省科技计划重点项目(2009R10039-1)
作者(Authors): 章文龙;林贤彪;仝川;曾从盛;
参考文献(References)：
- [1]贾萍,李海涛,林卉,等.基于SVM的多源遥感影像分类研究[J].测绘科学,2008,33(4):21-22.
- [2]黄立贤,沈志学.高光谱遥感图像的监督分类[J].地理空间信息,2011,9(5):81-83.
- [3]李智峰,朱谷昌,董泰锋.基于灰度共生矩阵的图像纹理特征地物分类应用[J].地质与勘探,2011,47(3):456-461.
- [4]胡杏花,朱谷昌,徐文海.基于分形理论的遥感影像分类研究[J].遥感信息,2011,26(5):100-103.
- [5]孙建国,杨树文,段焕娥,等.基于光谱和纹理特征的山区高分辨率遥感影像分类[J].测绘科学,2009,34(6):92-93.
- [6]丁海勇,卞正富.基于SVM算法和纹理特征提取的遥感图像分类[J].计算机工程与设计,2008,29(8):2131-2132.
- [7]姜青香,刘慧平.利用纹理分析方法提取TM图像信息[J].遥感学报,2004,8(5):458-464.
- [8]张锦水,何春阳,潘耀忠,等.基于SVM的多源信息复合的高空间分辨率遥感数据分类研究[J].遥感学报,2006,10(1):49-57.
- [9]李玲,王红,刘庆生,等.基于纹理特征和支持向量机的ALOS图像土地覆被分类[J].国土资源遥感,2011,23(4):58-63.
- [10]Zhang Q,Wang J,Gong P,et al.Study of urban spatial patterns from SPOT panchromatic imagery using textural analy-sis[J].International Journal of Remote Sensing,2003,24(21):4137-4160.
- [11]钟桦,杨晓鸣,焦李成.基于多分辨共生矩阵的纹理图像分类[J].计算机研究与发展,2011,48(11):1991-1999.
- [12]冯建辉,杨玉静.基于灰度共生矩阵提取纹理特征图像的研究[J].北京测绘,2007,21(3):19-22.
- [13]陈启浩,高伟,刘修国.辅以纹理特征的高分辨率遥感影像分类[J].测绘科学,2008,33(1):88-90.
- [14]Zhang Y.Optimisation of building detection in satellite images by combining multispectral classification and texture filte-ring[J].ISPRS Journal of Photogrammetry and Remote Sensing,1999,54(1):50-60.
- [15]陆超.基于Worldview-2影像的面向对象信息提取技术研究[D].杭州:浙江大学,2012.
- [16]凌春丽,朱兰艳,吴俐民.Worldview-2影像林地信息提取的研究与实现[J].测绘科学,2010,35(5):205-207.
- [17]Upadhyay P,Kumar A,Roy P S,et al.Effect on specific crop mapping using Worldview-2multispectral add-on bands:soft classification approach[J].Journal of Applied Remote Sensing,2012,6(1):24-35.
- [18]Pacifici F,Chini M,Emery W J.A neural network approach using multi-scale textural metrics from very high-resolu-tion panchromatic imagery for urban land-use classification[J].Remote Sensing of Environment,2009,113(6):1276-1292.
- [19]Longbotham N,Chaapel C,Bleiler L,et al.Very high resolution multiangle urban classification analysis[J].Ieee Transactions on Geoscience and Remote Sensing,2012,50(4):1155-1170.
- [20]Mutanga O,Adam E,Cho M A.High density biomass estimation for wetland vegetation using Worldview-2imagery and random forest regression algorithm[J].International Journal of Applied Earth Observation and Geoinformation,2012,18:399-406.
- [21]Eckert S.Improved forest biomass and carbon estimations using texture measures from Worldview-2satellite data[J].Remote Sensing,2012,4(4):810-829.
- [22]阳牧男,姜贞白.WorldviewⅡ卫星影像融合方法的探讨[J].测绘,2011,34(5):225-227.
- [23]Haralick R M,Shanmugam K,Dinstein I H.Textural features for image classification[J].Systems,Man and Cyber-netics,IEEE Transactions on,1973,1(6):610-621.
- [24]Baraldi A,Parmiggiani F.An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters[J].Geoscience and Remote Sensing,IEEE Transactions on,1995,33(2):293-304.
- [25]Vapnik V N.The nature of statistical learning theory[M].New York:Springer-Verlag,2000.
- [26]王旭红,肖平,郭建明.高光谱数据降维技术研究[J].水土保持通报,2006,26(6):89-91.