• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Geoscience and Remote Sensing Symposium >Maximum variance unfolding based co-location decision tree for remote sensing image classification
【24h】

Maximum variance unfolding based co-location decision tree for remote sensing image classification

机译：基于最大方差展开的并置决策树的遥感影像分类

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

摘要

Since conventional decision tree (DT) induction methods cannot efficiently take advantage of geospatial knowledge in the classification of remotely sensed imagery, a co-location decision tree (CL-DT) method, combining the co-location technique with the conventional DT method, has been proposed by several researchers. However, the CL-DT method only considers the Euclidean distance of neighborhood events, which cannot truly reflect the co-location relationship between instances for which there is a nonlinear distribution in a high-dimensional space. For this reason, this paper develops the theory and method for a maximum variance unfolding (MVU)-based CL-DT method (known as MVU-based CL-DT). The presented method has been validated by classifying remote sensing image and is compared with CL-DT method and random forest (RF) method. The experimental results show that the proposed method can better construct decision tree and reach a high classification accuracy.
机译：由于常规决策树（DT）归纳方法无法在遥感影像的分类中有效利用地理空间知识，因此将共置位技术与常规DT方法相结合的共置位决策树（CL-DT）方法具有由几位研究人员提出。但是，CL-DT方法仅考虑邻域事件的欧几里得距离，不能真正反映高维空间中存在非线性分布的实例之间的共址关系。因此，本文开发了基于最大方差展开（MVU）的CL-DT方法（称为基于MVU的CL-DT）的理论和方法。通过对遥感图像进行分类验证了该方法的有效性，并与CL-DT方法和随机森林（RF）方法进行了比较。实验结果表明，该方法能够较好地构造决策树，并达到较高的分类精度。

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