首页> 外文会议>Dragon 3 Final Results Dragon 4 Kick-Off Symposium >A FEATURES SELECTIONFOR CROPS CLASSIFICATION
【24h】

A FEATURES SELECTIONFOR CROPS CLASSIFICATION

机译:作物分类的功能选择

获取原文

摘要

The components of the polarimetrictarget decomposition reflect the differences of target since they linked with the scattering properties of the target and can be imported into SVM as the classification features. The result of decomposition usually concentrate on part of the com-ponents. Selecting a combination of componentscan reduce the features that importing into the SVM. The features reduction can lead to less calculation and targeted classification of one target when we classify a multi-class area. In this research, we import different combina-tionsof features into the SVM and find a better combination for classification with a data of AGRISAR.
机译:PolarimetrictarGet分解的组件反映了目标的差异,因为它们与目标的散射特性链接,并且可以作为分类特征导入SVM。分解的结果通常集中在一部分Com-Ponest。选择ComponentSCAN的组合会降低导入SVM的功能。当我们分类多级别区域时,减少功能可能导致一个目标的计算和目标分类。在这项研究中,我们将不同的Combina-TiOSOOF的功能导入SVM,并找到与Agrisar数据进行分类的更好组合。

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