高分一号多光谱遥感数据的面向对象分类Object-oriented classification method based on GF-1 multi-spectral remote sensing image
刘书含,顾行发,余涛,王珂,张周威,鞠颂
摘要(Abstract)：
文章针对高分一号(GF-1)高分辨率遥感数据,提出了一种基于多特征的面向对象遥感图像分类算法:首先,对GF-1卫星数据进行分水岭分割,并利用仿射不变矩形状特征算子获得遥感图像的几何特征;其次,利用主成分分析和灰度共生矩阵获得遥感图像的纹理特征;然后,基于多特征数据进行均值漂移滤波,并利用自动标记分水岭分割方法实现遥感图像分割;最后,结合基于像元的最大似然监督分类结果做投票分类处理,从而实现面向像元与面向对象相结合的遥感数据分类。以高分一号遥感数据进行分类实验,结果表明:本文方法可有效地提高遥感图像分类精度。
关键词(KeyWords)： 均值漂移;多特征;分水岭分割;高分一号;面向对象分类
基金项目(Foundation): 民用航天“十二五”预先研究项目(D040201,Y1K0030044);; 中国科学院遥感与数字地球研究项目(Y4SF010030)
作者(Author): 刘书含,顾行发,余涛,王珂,张周威,鞠颂
DOI: 10.16251/j.cnki.1009-2307.2014.12.030
参考文献(References)：
- [1]陈建杰,叶智宣.多分类SVM主动学习及其在遥感图像分类中的应用[J].测绘科学,2009,34(4):97-100.
- [2]柏延臣,王劲峰.结合多分类器的遥感数据专题分类方法研究[J].遥感学报,2005,9(5):555-562.
- [3]LI Shijin,TAO Jian,WAN Dingsheng,et al.Contentbased Remote Sensing Image Retrieval Using Co-training of Multiple Classifiers[J].Journal of Remote Sensing,2010(03):493-499.
- [4]Shackelford A K,Davis C H.A Combined Fuzzy Pixelbased and Object-based Approach for Classification of High-resolution Multispectral Data over Urban Areas[C]//IEEE Transactions on Geoscience and Remote Sensing,2003,41(10):2354-2363.
- [5]Arroyo L A,Healey S P,Cohen W B,et al.Using Object-oriented Classification and High-resolution Imagery to Map Fuel Types in a Mediterranean Region[J].Journal of Geophysical Research-Biogeosciences,2006:111-119.
- [6]Platt R V,Rapoza L.An Evaluation of an Object-oriented Paradigm for Land Use/Land Cover Classification[J].The Professional Geographer,2008,60(1):87-100.
- [7]Stow D,Lopez A,Lippitt C,et al.Object-based Classification of Residential Land Use within Accra,Ghana based on QuickBird Satellite Data[J].Intenational Journal of Remote Sensing,2007,28(22):5167-5173.
- [8]Su W,Li J,Chen Y,et al.Textural and Local Spatial Statistics for the Object-oriented Classification of Urban Areas Using High Resolution Imagery[J].International Journal of Remote Sensing,2008,29(11):3105-3117.
- [9]Cleve C,Kelly M,Kearns F R,et al.Classification of the Wild Land-urban Interface:A Comparison of Pixel and Object-based Classification Using High-resolution Aerial Photography[J].Computers,Environment and Urban Systems,2008,32(4):317-326.
- [10]梅丹丹,张晓祥,余其鹏,等.利用辅助数据的荒漠区高分辨率遥感分类研究[J].遥感信息,2013,28(5):77-84.
- [11]高薇,王珂,原发杰,等.基于不变矩的高分辨率遥感图像的建筑物提取方法[J/OL]//计算机应用研究.(2014).http://www.cnki.net/kcms/detail/51.1196.TP.20130910.1707.006.html.
- [12]王珂,顾行发,余涛,等.结合光谱相似性与相位—致模型的高分辨率遥感图像分割方法[J].红外与毫米波学报,2013(1):73-79.
- [13]肖鹏峰,冯学治,赵书河,等.基于相位一致的高分辨率遥感图像分割方法[J].测绘学报,2007,36(2):146-151.