苏腾飞,李瑞平

• 1:内蒙古农业大学

摘要(Abstract)：

为了提高农业遥感数据处理中多光谱影像分割的精度,文章提出了一种面向农田信息提取的遥感影像分割算法:利用KMeans非监督分类算法和Fisher标准估算多光谱遥感影像中各个波段的权值,并将估算的波段权值应用到光谱合并计算中,能够较好地提高农田区域的分割精度,实现基于全局最优合并的区域生长算法,得到最优化的分割结果;从分割结果中提取基于区域的NDVI信息可以较为快速、准确地区分农田和非农田区域。实验结果说明:该方法的分割精度优于传统的全局最优合并算法和FNEA算法,并对遥感影像中旱田和水田的提取均有较好的效果。

关键词(KeyWords)： 多光谱遥感影像;农田;波段权值;图像分割

Abstract:

Keywords:

基金项目(Foundation): 内蒙古自治区科技计划项目(20140153);; 内蒙古自治区水利科技项目(NSK201403)

作者(Author): 苏腾飞,李瑞平

DOI: 10.16251/j.cnki.1009-2307.2016.03.010

参考文献(References)：

• [1]MARK L,MUTLU O,XIAOJIN Z.Crop type classification by simultaneous use of satellite images of different resolutions[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(6):3637-3649.
• [2]CAROLYN E,RONALD J,IMANTS S,et al.Segmenting multispectral Landsat TM images into field units[J].IEEE Transactions on Geoscience and Remote Sensing,2002,40(5):1054-1064.
• [3]李晖,肖鹏峰,冯学智,等.基于向量场模型的多光谱遥感图像多尺度边缘检测[J].测绘学报,2012,41(1):1-10.
• [4]李正国,唐华俊,杨鹏,等.植被物候特征的遥感提取与农业应用综述[J].中国农业资源与区划,2012,33(5):20-28.
• [5]IM J,JENSEN R,TULLIS A.Object-based change detection using correlation image analysis and image segmentation[J].International Journal of Remote Sensing,2008,29(2):399-423.
• [6]NEUBERT M,HEROLD H,MEINEL G.Evaluation of remote sensing image segmentation quality-further results and concepts[C]//Proceedings 1st International conference on OBIA.Salzburg,Austria,2006.
• [7]ROLF A,LEANNE B.Seeded region growing[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(6):641-647.
• [8]BAATZ M,SCHPE A.Multiresolution segmentation:an optimizing approach for high quality multiscale segmentation[C]//Angewandte Geographich Informationsverarbeitung,XII.J.Strobl and T.Blaschke,Eds.Heidelberg,Germany:Wichmann,2000,12-23.
• [9]BEAULIEU J,GOLDBERG M.Hierarchy in picture segmentation:a stepwise optimization approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(2):150-163.
• [10]TILTON J,TARABALKA Y,MONTESNO P,et al.Best merge region growing with integrated non-adjacent region object aggregation[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(11):4454-4467.
• [11]YANFEI Z,BEI Z,LIANGPEI Z.Multiagent objectbased classifier for high spatial resolution imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(2):841-857.
• [12]YU Q,CLAUSI D.IRGS:image segmentation using edge penalties and region growing[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(12):2126-2139.