Abstract: QuickBird image covering part of Beijing City is taken as a source. Object-oriented image analysis method is used to extract automatically the MCZ (municipal construction zones). On the basis of analyzing the characteristics of MCZ, a method combining low- and high-resolution images is presented. At low-resolution image, the crude extents of MCZ are identified; at high-resolution image, the crude extents are refined further. Compared with the visual interpretation result, the precision is about 89.7%, and the miscarriage of justice rate is about 27.6%.

Key words: high-resolution remotely sensed image, municipal construction zones, object-oriented, image analysis

摘要： 以北京市部分区域的QuickBird影像为实验数据, 运用面向对象的影像分析手段, 研究城市建设区的自动识别和提取方法。在分析城市建设区特征的基础上, 采用在低分辨率影像上粗提取, 在高分辨率影像上精提取相结合的技术, 提高提取精度。经过与目视判读结果的对比, 城市建设区的识别率达到89.7%, 误判率为27.6%。

关键词: 高分辨率影像, 城市建设区, 面向对象, 影像分析