期刊文献+

联合纹理和光谱特征的高光谱影像多核分类方法 被引量:6

Combined Texture-spectral Feature for Multiple Kernel Classification of Hyperspectral Images
下载PDF
导出
摘要 为充分利用高光谱影像"图谱合一"的特性,提出一种联合纹理和光谱特征的高光谱影像多核学习分类方法。该方法首先利用Gabor滤波器组提取影像的纹理特征,然后与原始光谱特征相结合形成新的特征数据,最后采用多核学习方法的MKSVM分类器进行分类。通过利用中科院上海技术物理研究所研制的PHI高光谱影像进行试验,试验结果表明该方法有效地消除了分类结果中同质区域内出现的"麻点"现象,同时提高了分类精度。
出处 《测绘通报》 CSCD 北大核心 2014年第9期38-42,共5页 Bulletin of Surveying and Mapping
基金 国家自然科学基金(青年科学基金)(41201477) 江西省数字国土重点实验室开放基金(DLLJ201403)
  • 相关文献

参考文献4

二级参考文献17

  • 1Zhou Yatong Zhang Taiyi Li Xiaohe.MULTI-SCALE GAUSSIAN PROCESSES MODEL[J].Journal of Electronics(China),2006,23(4):618-622. 被引量:4
  • 2TONG Qingxi, ZHANG Bing, ZHENG Lanfen. Hyperspec tral remote sensing-principles, techniques and applications [M]. Beijing: Higher Education Press, 2006= 129 289 (in Chinese).
  • 3Duda RO, Hart PE. Pattern classification and scene analysis [M]. New York: Wiley, 1973: 95.
  • 4Vapnik V N. The nature of statistical learning theory [M]. ZHANG Xuegong, transl. Beiiin: Tsinghua University Press, 2000 (in Chinese).
  • 5Camps-Vails G, Luis G C, Jordi M M, et al. Composite ker- nels for hyperspectral image classification [ J ]. IEEE Geoscience and Remote Sensing Letters, 2006, 3 (1): 93-97.
  • 6Mathieu F, J6n A B, Jocelyn C, et al. Spectral and spatial classification of hyperspectral data using SVMs and morphologi- cal profiles [J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46 (11): 3804-3814.
  • 7Jain AN, Farroknia F. Unsupervised texture segmentation using Gabor filters [J]. Pattern Recognition, 1991, 24 (12): 1167- 1186.
  • 8XIA Jiantao. High dimensional multispectral data classification by machine learning [D]. Xi' an.. Northwestern Polyteehnical University, 2002 (in Chinese).
  • 9WU Tao. Kernels" properties, tricks and its applications on ob- stacle detection [D]. Changsha: National University of De- fense Technology, 2003 (in Chinese).
  • 10DENG Naiyang, TIAN Yingjie. The new method in data mining-support vector machines [M]. Beijing, China: Science Press, 2004 (in Chinese).

共引文献184

同被引文献81

  • 1黄昕,张良培,李平湘.融合形状和光谱的高空间分辨率遥感影像分类[J].遥感学报,2007,11(2):193-200. 被引量:49
  • 2余旭初,冯五法,杨国鹏,等.高光谱影像分析与应用[M].北京:科学出版社,2013.
  • 3谭熊.联合空间和光谱特征的高光谱影像分类技术研究[D].郑州:信息工程大学,2014:8-16.
  • 4CAMPS-VALLS G, LUIS GOMEZ-CHOVA, JORDI MUNOZ-MARf, et al. Composite Kernels for Hyperspectral Image Clas-sification [J ]. IEEE Geoscience and Remote Sensing Letters,2006,3(1) :93-97.
  • 5PLAZA A, BENEDIKTSSON J A, BOARDMAN J W, et al.Recent Advances in Techniques for Hyperspectral Image Pro-cessing [ J ] . Remote Sensing of Environment,2009,113( 1 ):110-122.
  • 6FAUVEL M, BENEDIKTSSON J A, CHANUSSOT J,et al.Spectral and Spatial Classification of Hyperspectral Data UsingSVMs and Morphological Profiles [ J ] . IEEE Transactions onGeoscience Remote Sensing,2008,46( 11) : 3804-3814.
  • 7MAURO D M, ALBERTO V,BENEDIKTSSON J A, et alClassification of Hyperspectral Images by Using Extended Mor-phological Attribute Profiles and Independent Component Anal-ysis[ J]. IEEE Geoscience and Remote Sensing Letters,2011,8(3):542-546.
  • 8OLGA R, PEDRO G S, FILIBERTO P. Spectral-Spatial PixelCharacterization Using Gabor Filters for Hyperspectral ImageClassification[ J]. IEEE Geoscience and Remote Sensing Let-ters, 2013,10( 4) :860-864.
  • 9TARBALKA Y, FAUVEL M, CHANUSSOT J, et al. SVM-and MRF-Based Method for Accurate Classification of Hyper-spectral Images[J]. IEEE Geoscience and Remote Sensing Let-ters,2010,7(4) :736-740.
  • 10ZHANG B, LI S S, JIA X P. Adaptive Markov Random FieldApproach for Classification of Hyperspectral Imagery[ J]. IEEEGeoscience and Remote Sensing Letters, 2011,8(5) : 973-977.

引证文献6

二级引证文献49

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