期刊文献+

高光谱遥感图像的监督分类 被引量:12

Supervised Classification Method for Hyperspectral Images
下载PDF
导出
摘要 图像分类是高光谱遥感图像分析与应用的重要手段。总结了目前用于高光谱图像监督分类的主要方法,包括最小距离法、最大似然法、神经元网络法和支持向量机法,分析了上述方法的特点,并探讨了高光谱遥感图像分类方法的发展趋势。 Classification is an important means for analysis and application of hyperspectral images.The main method of supervised classification for hyperspectral images including Minimum Distance Classifier,Maximum Likelihood Classifier and Artificial Neural Network Classifier were introduced and the characteristic of the method were analyzed.Finally,the develop trend of classification method for hyperspectral images was discussed.
出处 《地理空间信息》 2011年第5期81-83,166,共3页 Geospatial Information
基金 中国工程物理研究院科学技术发展基金资助项目(2010B0401049)
关键词 高光谱图像 图像分类 监督分类 遥感应用 Hyperspectral images Images classification Supervised classification Remote sensing application
  • 相关文献

参考文献13

  • 1李小娟,刘晓萌,胡德勇,等.ENVI遥感影像处理[M].北京:中国环境科学出版社,2008,9:322-347.
  • 2杨国鹏,余旭初,刘伟,陈伟.面向高光谱遥感影像的分类方法研究[J].测绘通报,2007(10):17-20. 被引量:15
  • 3Helmi Z M, Affendi Suhaili and Shattri Mansor. The Performance of Maximum Likelihood, Spectral Angle Mapper, Neural Net- work and Decision Tree Classifiers in Hyperspectral Image Analysis[J]. Journal of Computer Science, 2007, 3 (6): 419-423.
  • 4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. 被引量:12
  • 5Jia X and Richards J A.Segmented Principal Components Trans- formation Forefficient Hyperspectral Remote-Sensing Image Display and Classification[J]. IEEE Transaetions on Geoscience and Remote Sensing, 1999,37(1):538-542.
  • 6M and Tatnall A R L. Introduction to Neural Networks in Remote Sensing[J]. International Journal of Remote Sensing, 1997, 11 : 699-709.
  • 7Weeks P J D and Gaston K J. Image Analysis, Neural Networks and the Taxonomic Impediment to Biodiversity Studies[J]. Biodi- versity and Conservation, 1997, 6:263-274.
  • 8Foody G M and Mathur A. A Relative Evaluation of Multiclass Image Classification by Support Vector Machines [J]. Transac- tions On Geoscience And Remote Sensing, 2004, 42:1335-1343.
  • 9Osuna E,Fretmd R, Girosi E Improved Training Algorithm for Support Vector Machines[J]. Proceedings of Workshop on Neural Networks for Signal Processing,1997,10:500-505.
  • 10刘正军,王长耀,张继贤.基于小波与遗传算法的特征提取与特征选择(英文)[J].遥感学报,2005,9(2):176-185. 被引量:7

二级参考文献43

  • 1赵春晖,刘春红.超谱遥感图像降维方法研究现状与分析[J].中国空间科学技术,2004,24(5):28-36. 被引量:19
  • 2刘颖,谷延锋,张晔.基于改进遗传算法的超光谱图像特征选择方法[J].哈尔滨工业大学学报,2005,37(6):733-735. 被引量:4
  • 3[1]Kittler J,Hater M,Duin R,et al.On Combining Classifiers[J].IEEE Trans On Pattern Analysis and Machine Intelligence,1998,20(3):226-239.
  • 4[4]Duin R,Tax D.Experiments with Classifier Combining Rules[A].Proceedings of the 1 st International Workshop on Multipie Classifier Systems[C].Italy,Cagliari,2000:16-19.
  • 5Pearlman J, Carman S, Segal C, et al. Overview of the Hyperion Imaging Spectrometer for the NASA EO-1 Mission [ A ], IEEE2001 International Geoscience and Remote Sensing Symposium,[C]. July 9-13, 2001, Sydney, Australia.
  • 6Barry P, Segal C, Pearlman J, et al. Carman Hyperion Data Collection: Performance Assessment and Science Application [ A ],IEEE 2001 International Geoscience and Remote Sensing Symposium[ C]. July 9-13, 2001, Sydney, Australia.
  • 7Van Niel T, McVicar T, Campbell S, et al. The Coleambally Agricultural Component of Hyperion Instrument Validation [ A ].IEEE 2001 International Geoscience and Remote Sensing Symposium[ C ]. July 9-13, 2001, Sydney, Australia.
  • 8Hughes G. On the Mean Accuracy of Statistical Pattern Recognizers [J]. IEEE Trans. Inform. Theory 1968, IT-14, 55-63.
  • 9Lee C, Landgrebe D. Feature Extraction and Classification Algorithms for High dimensional Data [ R]. TR-ENVIRONMENT 93-1, Purdue University, 1993.
  • 10Hsu P H, Tseng Y H. Feature Extraction for Hyper Spectral Image [ C]. 20th Asian Conference on Remote Sensing, November22-25, 1999, Hong Kong, China.

共引文献39

同被引文献195

引证文献12

二级引证文献91

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部