• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Signal, Information and Data Processing >An Automatic Thresholding Method For Water Body Detection From SAR Image
【24h】

An Automatic Thresholding Method For Water Body Detection From SAR Image

机译：一种SAR图像水体自动检测的阈值方法

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

摘要

This paper presents a water body detection framework with an automatic threshold determination procedure. Water bodies in SAR image often appear dark and homogeneous due to specular reflection. Therefore, the water bodies can easily be detected with a thresholding method. However, the threshold needs to be adjusted interactively for every SAR data due to backscatter differences between water bodies in SAR data. The recursive Otsu thresholding method is used to determine the threshold automatically. The normalized between-class variance is introduced to select optimal threshold from threshold set generated by the recursive Otsu thresholding. The presented framework eliminates the manual operating interaction and has a near-real-time capability in extracting water bodies from huge amounts of data. Experimental results with TerraSAR-X stripmap data verify the effectiveness of the framework.
机译：本文提出了一种具有自动阈值确定程序的水体检测框架。由于镜面反射，SAR图像中的水体通常显得暗淡且均匀。因此，可以通过阈值方法容易地检测出水体。但是，由于SAR数据中水体之间的反向散射差异，需要针对每个SAR数据交互调整阈值。递归Otsu阈值化方法用于自动确定阈值。引入归一化的类间方差以从由递归Otsu阈值生成的阈值集中选择最佳阈值。提出的框架消除了手动操作交互，并具有从大量数据中提取水体的近实时功能。 TerraSAR-X条形图数据的实验结果证明了该框架的有效性。

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