期刊文献+

SVM用于LiDAR数据的地物分类 被引量:9

Land Cover Classification from LiDAR Data Based on SVM
下载PDF
导出
摘要 LiDAR具有探测地表垂向结构的能力,目前还无法被其他遥感源所取代。本文提出通过变换点云提取LiDAR纹理特征,利用支持向量机(SVM)进行训练和分类,并与基于神经网络的分类方法进行比较。试验结果表明,SVM能在训练精度和推广能力之间取得折中,可有效地避免LiDAR地物分类证据不完备引起的过拟合问题,适合于LiDAR地物分类。
出处 《测绘通报》 CSCD 北大核心 2013年第7期35-38,42,共5页 Bulletin of Surveying and Mapping
基金 广东省自然科学基金(S2011040003226) 广州市科技计划(7421252729755)
关键词 LIDAR 高度纹理 SVM
  • 相关文献

参考文献11

  • 1WEHR A, LOHR U. Airborne Laser Scanning an Introduction and Overview [J]. ISPRS Journal of Photo- grammetry and Remote Sensing, 1999, 54(2) : 68-82.
  • 2BORK E W, SU J G. Integrating LiDAR Data and Multispectral Imagery for Enhanced Classification of Rangeland Vegetation: a Meta Analysis[J]. Remote Sensing of Environment, 2007,111 ( 1 ) : 11-24.
  • 3MAAS H G. The Potential of Height Texture Measures for the Segmentation of Airborne Laser Scanner Data [ C ]// Proceedings of 4th International Airborne Remote Sensing Conference and Exhibition. Ottawa: [ s. n. ] , 1999: 154-161.
  • 4DIMITRIOS C, KEITH A. A Texture-based Technique for DEM Generation from LiDAR Data [ C ]//Proceedings of the SPIE. Orlando, Florida : [ s. n. ] ,2007.
  • 5TIWARI P S,PAVDE H. Use of Laser Range and Height Texture Cues for Building Identification [ J ]. Journal of the Indian Society of Remote Sensing, 2008, 36 (3): 227 -234.
  • 6IM J,JENSEN J R, HODSON M E. Object-based Land-cover Classification Using High-posting-density LiDAR Data [J]. GIScience & Remote Sensing, 2008, 45 (2) : 209 -228.
  • 7VAPNIK V N.统计学习理论[M].许建华,张学工,译.北京:电子工业出版社,2004.
  • 8沈照庆,舒宁,陶建斌,刘玲.无惩罚系数SVM高光谱影像分类算法研究[J].测绘通报,2009(6):22-25. 被引量:3
  • 9王晓玲,杜培军.基于形态学的空间信息和光谱信息SVM影像分类[J].测绘通报,2012(12):18-22. 被引量:4
  • 10HARALICK R M. Handbook of Pattern Recognition and Image Processing [ M ]. New York: Academic Press, 1986.

二级参考文献18

  • 1周前祥,敬忠良.高光谱遥感图像联合加权随机分类器的设计与应用[J].测绘学报,2004,33(3):254-257. 被引量:8
  • 2KEERTHI S S, SHEVADE S K, BHATTACHARYYA C, et al. A Fast Iterative Nearest Point Algorithm for Support Vector Machine Classifier Design [ J ]. IEEE Transactions on Neural Networks, 2000,11(1) :124 - 136.
  • 3FAUYE M, BENEDIKTSSON J A, CHANUSSOT J,et al. Spectral and Spatial Classification of Hyperspeetral Data Using SVMs and Morphological Profiles [ J ]. IEEE Trans- actions on Geoscience and Remote Sensing, 2008, 46 (11): 3804-3814.
  • 4MYINT S W, LAM N S N, TYLER J. Wavelets for Ur- ban Spatial Feature Discrimination: Comparisons with Fractal, Spatial Autocorrelation, and Spatial Co-occur- rence Approaches[ J ]. Photogrammetric Engineering and Remote Sensing, 2004, 70(7) : 803-812.
  • 5ZHANG L, FURUMI S, MURUMATSU K, et al. Sensor- independent Analysis Method for Hyper-muhi Spectral Data Based on the Pattern Decomposition Method [ J ]. International Journal of Remote Sensing, 2006, 27 (21) : 4899-4910.
  • 6MEHER S K, SHANKAR B U,GHOSH A. Wavelet-fea- ture-based Classifiers for Multispectral Remote Sensing Images [J]. IEEE Transactions on Geoscience and Re- mote Sensing, 2007, 45 (7) : 1881-1886.
  • 7PUISSANT A, HIRSCH J, WEBER C. The Utility of Texture Analysis to Improve Perpixel Classification for High to Very High Spatial Resolution Imagery[J]. Inter- national Journal of Remote Sensing, 2005, 26 ( 4 ) : 733 -745.
  • 8OUMA Y O, TETUKO J,TATEISHI R. Analysis of Co- occurrence and Discrete Wavelet Transform Textures for Differentiation of Forest and Non-forest Vegetation in Very-high-resolution Optical-sensor imagery [ J ]. Inter- national Journal of Remote Sensing, 2008, 29 ( 12 ) : 3417-3456.
  • 9BENEDIKTSSON J A, PALMASON J A,SVEINSSON J R. Classification of Hyperspectral Data from Urban Are- as Based on Extended Morphological Profiles [ J ]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3) : 480-491.
  • 10EPIFANIO I, SOILLE P. Morphological Texture Fea- tures for Unsupervised and Supervised Segmentations of Natural Landscapes[J].IEEE Transactions on Geosci- ence and Remote Sensing, 2007, 45 (4) : 1074-1085.

共引文献36

同被引文献57

引证文献9

二级引证文献32

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