地理研究 ›› 2001, Vol. 20 ›› Issue (1): 62-67.doi: 10.11821/yj2001010009

• 论文 • 上一篇    下一篇

卫星图像中不同水体类型识别研究

秦其明, 袁吟欢, 陆荣建   

  1. 北京大学遥感与地理信息系统研究所, 北京 100871
  • 收稿日期:2000-09-07 修回日期:2000-12-02 出版日期:2001-02-15 发布日期:2001-02-15
  • 作者简介:秦其明(1955-),男,江苏人,博士,北京大学遥感与地理信息系统研究所副所长,教授。 主要从事遥感图像解译与地理信息系统应用模型研究,先后发表学术论文20余篇,出版 编著4本。
  • 基金资助:

    国家自然科学基金资助项目(69872004);国家重点基础研究发展规划项目(G2000077900)

The recognition of various types of water bodies on satellite image

QIN Qi ming, YUAN Yin huan, LU Rong jian   

  1. Institute of Remote Sensing and GIS, Peking University, Beijing 100871, China
  • Received:2000-09-07 Revised:2000-12-02 Online:2001-02-15 Published:2001-02-15

摘要:

在具有高空间分辨率特性的图像上,城市中大型建筑物、道路、河流、湖泊和其他人工地物形状特征和纹理特征清晰可辨。针对高分辨率卫星图像的特点,文章以水体类型识别为例,从卫星数字图像目标地物波谱特征抽取入手,通过图像分类,将水体从背景中分离并予以识别,同时实现像素重组。在区域分割与边界跟踪基础上,对卫星图像进行水体形状特征的抽取与描述,实现不同水体类型的识别。

关键词: 模式识别, 卫星图像, 特征抽取

Abstract:

The data of satellite remote sensing can provide real time information of the earth's surface accurately. Now the commercial satellites can provide the satellite images with the resolution between 10 meter and 1 meter. With those high spatial resolution images, shape features and texture features of the ground objects including large buildings of city, roads, rivers, lakes and other man made objects are very clear. With the characters of the high resolution satellite image, we will use the recognition of the type of water bodies as an example, begin with the extraction of the spectrum features of the ground objects from the satellite digital images, separate water bodies from background and recognize it through the classification of the image, implement the recombination of the pixels, then extract and describe the shape features of water bodies and implement the recognition of various water bodies on the partition of areas and the tracing of boundary. The experiments of the recognition of various types of water bodies on the satellite image prove this recognizing method is feasible with high spatial resolution satellite images.

Key words: pattern recognition, satellite image, feature extraction

  • TP79