首页> 外文会议>Fifth international workshop on the analysis of multi-temporal remote sensing images >LAND COVER CLASSIFICATION FROM MULTITEMPORAL C- AND L-BAND SAR DATA
【24h】

LAND COVER CLASSIFICATION FROM MULTITEMPORAL C- AND L-BAND SAR DATA

机译:基于多时C和L波段SAR数据的土地覆盖分类

获取原文
获取原文并翻译 | 示例

摘要

The investigation focuses on the determination of the land cover type using SAR data, including single polarisation, dual polarisation and fully polarimetric data, at C-and L-band. The results from two data sets have been compared, the EMISAR data set from the Foulum test site, and the ESAR data set from the AgriSAR07 campaign. The multitemporal acquisitions significantly improve the classification results for single and dual polarization configurations. The same trends are seen for the two data sets, with the AgriSAR data set producing better results than the Foulum data set. This can partly be explained by the much fewer classes present in the AgriSAR data set. In some case, the results from the two data sets disagree on the choice of radar frequency, mode, and method.
机译:该调查着重于使用SAR数据(包括C波段和L波段的单极化,双极化和全极化数据)确定土地覆盖类型。比较了来自两个数据集的结果,即来自Foulum测试站点的EMISAR数据集和来自AgriSAR07活动的ESAR数据集。多时相采集显着改善了单极化和双极化配置的分类结果。对于这两个数据集,可以看到相同的趋势,其中AgriSAR数据集比Foulum数据集产生更好的结果。部分原因可以归因于AgriSAR数据集中存在的类别少得多。在某些情况下,两个数据集的结果在雷达频率,模式和方法的选择上不一致。

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