• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>SPIE Conference on Remote Sensing for Environmental Monitoring, GIS Applications, and Geology >From fuzzy and object based classification tofuzzy and object based uncertainty evaluation
【24h】

From fuzzy and object based classification tofuzzy and object based uncertainty evaluation

机译：从基于模糊和基于对象的分类Tofuzzy和基于对象的不确定性评估

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Regarding thematic processing of remote sensing data new problems have arisen with the rapid increase of geometricand spectral resolution. These have been partly solved through the application of object oriented methods and alternative(e.g. fuzzy logic) approaches for the actual allocation of a feature to a topographical object whereas these methods do notapply comprehensively to the quality assessment of the processed data. We present an integrated approach for theassessment of classified high-resolution remote sensing scenes which considers uncertainties – not only in the classifieddata but in the reference ("ground truth") data as well. Instead of discrete object boundaries we define transition zonesbetween adjacent objects; a fuzzy function describes the distribution of class membership values within these zones.Thus we can compute an evaluation measure on the basis of the uncertainty model – the CFCM (Class-specific FuzzyCertainty Measure) provides a quality assessment for classified remote sensing data considering uncertainties ingeometry and semantics. The work is part of the project "CLassification Assessment using an Integrated Method(CLAIM)".
机译：关于遥感数据的主题处理，新问题具有新的问题，随着几何频谱分辨率的快速增加。这些方法已经部分解决了对象的方法和替代（例如模糊逻辑）对地形对象的实际分配方法的方法，而这些方法会全面地对处理数据的质量评估进行全面地进行。我们展示了综合方法，用于筛选分类的高分辨率遥感场景，其考虑不确定性 - 不仅在分类数据库中，而且在参考（“地面真理”）数据中也是如此。而不是离散对象边界，我们定义了相邻对象的过渡Zones;模糊函数描述了这些区域内的类成员身份的分布.Thus我们可以根据不确定性模型计算评估措施 - CFCM（类特定的Fuzzycertainty测量）为考虑不确定性进入的分类遥感数据提供了质量评估和语义。该工作是项目的一部分“使用综合方法（索赔）”。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号