期刊文献+

面向对象的高分辨率影像单值分类耕地提取方法研究 被引量:5

Method Research on Cultivated Land Extraction Based on Object One-Class Classification of High-spatial-resolution Images
下载PDF
导出
摘要 遥感技术已广泛应用于土地覆盖/土地利用分类中。在专题应用中,用户只对某一类地物感兴趣,如耕地提取,即单类别分类问题。随着影像分辨率的提高,基于像元的分类算法难以满足高分辨率影像高精度信息提取的需求。本文采用结合面向对象分类思想和基于正样本、未标记样本遥感单值(PUL)分类方法从多源高分辨率影像中提取耕地信息,并与基于像素的分类试验进行对比分析。结果表明,在缺少部分地类的不完全训练集下,基于面向对象的单值分类较传统神经网络分类有更较稳定的表现,并且远优于基于像素的分类结果。
出处 《测绘通报》 CSCD 北大核心 2014年第10期78-81,共4页 Bulletin of Surveying and Mapping
基金 国土空间规划决策支持与管理平台开发(2012BAB11B05) 国土空间优化配置关键技术研究与示范(2012BAB11B00)
  • 相关文献

参考文献9

  • 1HODGSON M E, JENSEN J R, TULLIS J A, et al. Synergistic Use of LiDAR and Color Aerial Photography for Mapping Urban Parcel Imperviousness [ J ] Photo- grammetry Engineering & Remote Sensing, 2003, 69 (9) : 973-980.
  • 2RICHARDS J A, JIA X. Remote Sensing Digital Image Analysis : An Introduction[ M ]. Berlin : Springer, 1999.
  • 3FOODY G M, MATHUR A,SANCHEZ H C, et al. Training Set Size Requirements for the Classification of a Specific Class [ J] Remote Sensing of Environment, 2006,104(1) :1-14.
  • 4MUNOZ M J, BRUZZONE L, CAMPS V G.A Support Vector Domain Description Approach to Supervised Classification of Remote Sensing Images [ J ]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45 (8) : 2683-2692.
  • 5LI W, GUO Q H, ELKAN C. A Positive and Unlabeled Learning Algorithm for One-class Classification of Re- mote-sensing Data [ J ]. IEEE Transactions on Geosci- ence and Remote Sensing, 2011, 49(2) : 717-725.
  • 6ELKAN C, NOTO K. Learning Classifiers from Only Positive and Unlabeled Data [ C ]//Proceedings of the 14th ACM SIGKDD International Conference on Knowl- edge Discovery and Data Mining. Las Vegas, Nevada, USA : [ s.n. ] , 2008.
  • 7OPITZ D, BLUNDELL S. Object Recognition and Image Segmentation: The Feature Analyst Approach[ C]//Ob- ject-Based Image Analysis.Berlin: Springer Berlin Hei- delberg, 2008 : 153-167.
  • 8BENZ U. Definiens Imaging GmbH: Object-Oriented Classification and Feature Detection [ J ]. IEEE Geosci- ence and Remote sensing Society Newsletter, 2001 (5) : 16-20.
  • 9GAMOTTO J P. A New Approach to Combining Region Growing and Edge Detection [ J ]. Pattern Recognition Letters, 1993, 14(11) : 869-875.

同被引文献61

引证文献5

二级引证文献57

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