Information extraction from very high resolution satellite imagery over Lukole refugee camp, Tanzania
Information extraction from very high resolution satellite imagery over Lukole refugee camp, Tanzania
复制标题
DOI：
10.1080/0143116021000035021
复制
发表时间：
2003-11-01
影响因子：
3.4
通讯作者：
Soille, P
中科院分区：
文献类型：
--
作者：
Giada, S;De Groeve, T;Soille, P
本文讨论了信息提取IKONOS图像在坦桑尼亚的Lukole难民营。更具体地说，它描述了自动图像分析程序，用于快速可靠地识别难民帐篷及其空间范围。从已确定的帐篷中可以得出难民人数，并可绘制难民营地图，用于改善难民营管理。对四种信息提取方法进行了测试和比较：监督分类、非监督分类、多分辨率分割和数学形态学分析。后两个程序的基础上面向对象的分类器执行最好的空间精度超过85%，统计精度超过97%。这些方法可用于在其他地理环境中以及在具有不同空间和光谱分辨率的图像上提取难民营信息。
This paper addresses information extraction from IKONOS imagery over the Lukole refugee camp in Tanzania. More specific, it describes automatic image analysis procedures for a rapid and reliable identification of refugee tents as well as their spatial extent. From the identified tents, the number of refugees can be derived and a map of the camp can be generated, which can be used for improving refugee camp management. Four information extraction methods have been tested and compared: supervised classification, unsupervised classification, multi-resolution segmentation and mathematical morphology analysis. The latter two procedures based on object-oriented classifiers perform best with a spatial accuracy above 85% and a statistical accuracy above 97%. These methods could be used for refugee camp information extraction in other geographical settings and on imagery with different spatial and spectral resolutions.