首页> 外文会议>Asian conference on remote sensing >EXTRACTION OF FLOW DESCRIPTORS FOR RIVERS IN SATELLITE IMAGES
【24h】

EXTRACTION OF FLOW DESCRIPTORS FOR RIVERS IN SATELLITE IMAGES

机译:卫星图像中河流流量描述符的提取

获取原文

摘要

This paper proposes an approach that extracts water bodies, e.g. rivers and ca-nals, in satellite images, and describes their occurrence in vector form. The advantage of this special way of representation is the data independency, I.e. aspects like different spatial resolu-tions and rotational invariance can be overcome. The main problem is to be insensitive to noise whereby noise in this context incorporates features that aggravate the extraction of the actual feature under consideration. Most prominent are bridges and jetties, which interfere with the water body. For example they prohibit the estimation of the flow direction in rivers and the exact definition of riverbanks. The extracted features can be used as input for geographical information systems or for the characterisation of the corresponding image data in content-based retrieval systems.
机译:本文提出了一种提取水体的方法,例如,提取水体。河流和CA-NALS,在卫星图像中,并描述了他们的载体形式的发生。这种特殊的代表方式的优势是数据独立性,即可以克服不同的空间分辨率和旋转不变性的方面。主要问题是对噪声不敏感,在此上下文中的噪声包含加剧所考虑的实际特征的提取的功能。最突出的是桥梁和码头,干扰水体。例如,它们禁止估算河流中的流动方向和河岸的确切定义。提取的特征可以用作地理信息系统的输入或用于基于内容的检索系统中的相应图像数据的表征。

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