高分辨率遥感图像中建筑物阴影的提取  

Extraction of Building Shadows from Urban High Resolution Remote Sensing Image

作　　者：刘小洲[1] 周石琳[1] 李智勇[1] 

机构地区：[1]国防科学技术大学电子科学与工程学院,湖南长沙410073

出　　处：《计算机仿真》2008年第8期197-200,204,共5页Computer Simulation

摘　　要：在利用城区高分辨率遥感图像进行变化检测及目标提取等应用时,建筑物阴影的影响相对严重。要消除建筑物阴影的影响,就需要准确提取出建筑物的阴影。在分析了现有建筑物阴影提取方法不足的基础上,介绍了一种基于形态学重构来自动提取城区高分辨率遥感图像中的建筑物阴影的算法的原理及方法,并进行了实验。实验表明,算法能很好地去除绿化带和道路的影响,而且也能消除图像背景不均匀对结果产生的影响,提取出的建筑物阴影的大小和形状都能保持得比较好。When using urban high resolution remote sensing image to carry out change detection, target extraction and so on, building shadow＇s influence is relatively serious. In order to eliminate building shadow＇s influence, people need accurately to withdraw the building shadow. In order to solve the problem, the paper introduces an algorithm including its principle and method for automatic extracting building shadows from urban high resolution remote sensing image based on morphological reconstruction, and makes an experiment. The experiment indicates that the algorithm can remove the infection of virescence zone and road commendably. The size and shape of the extracted building shadow maintain quite well.

关 键 词：阴影提取 高分辨率遥感图像 形态学重构 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]