几种天绘一号卫星影像分割方法及质量评价Comparative analysis on segmentation methods for TH-1 images
李霞,朱倩,邓良
摘要(Abstract)：
为寻求更适合天绘一号卫星影像的分割方法,文章采用均值偏移分割、分水岭分割、数学形态学分割、连通分量分割4种图像分割方法对天绘一号卫星影像进行分割实验,并从视觉和定量两方面对分割结果进行评估。结果表明:均值偏移方法的分割质量更佳,且分割结果更有利于提升后续处理的效率;几何形态较规则、质地较均一、复杂度较低的地物类型分割质量较高,反之则较低。
关键词(KeyWords)： 天绘一号;遥感影像;分割方法;质量评价
基金项目(Foundation): 国家自然科学基金(41101445)
作者(Author): 李霞,朱倩,邓良
DOI: 10.16251/j.cnki.1009-2307.2014.09.030
参考文献(References)：
- [1]Y J Zhang.A survey on evaluation methods for image segmentation[J].Pattern Recognition,1996.29(8):1335-1346.
- [2]M Everingham,H Muller,B Thomas.Evaluating image segmentation algorithms using monotonic hulls in fitness/cost space[C]//12th British Machine Vision Conference.2002.
- [3]M Neubert,H Herold.Assessment of remote sensing image segmentation quality[G]//International Archives of Photogrammetry,Remote Sensing and Spatial Information Sciences.Calgary,Canada:GEOBIA 2008.
- [4]V Mezaris,I Kompatsiaris,M G.Strintzis.Still Image Segmentation Tools for Object-based Multimedia Applications[J].Pattern Recognition,2004.18(4):701-725.
- [5]W Liu,J Zhai,D Dori,et al.A System for Performance Evaluation of Arc Segmentation Algorithms[C]//CVPR Workshop on Empirical Evaluation in Computer Vision.2001.
- [6]K Fukunaga,L Hostetler.The estimation of the gradient of a density function,with applications in pattern recognition[C]//IEEE Transactions on Information Theory,1975,21(1):32-40.
- [7]S Beucher,C Lantuejoul.Use of watersheds in contour detection[C]//Workshop Image Processing,Real-Time Edge and Motion Detection/Estimation.1979,CCETT/IRISA:Rennes,France.
- [8]J Serra.Image Analysis and Mathematical Morphology[M].London,U.K:Academic,1982.
- [9]C A Bouman.Digital Image Processing[R].purdue university,2013.
- [10]C J van RIJSBERGEN.Information Retrieval[M].London:Butterworths,1979.
- [11]C Pantofaru,M Hebert.A Comparison of Image Segmentation Algorithms[R].Robotics Institute,Carnegie Mellon University:Pittsburgh,Pennsylvania,2005.
- [12]M Meila.Comparing Clusterings by the Variation of Information[R].Department of Statistics,University of Washington:USA,2003.