高分辨率多光谱影像城区建筑物提取研究

城区高空间分辨率遥感数据由于存在大量同物异谱和异物同谱现象，应用传统的基于像元光谱分类的方法进行建筑物分类提取难以取得满意的效果。本文发展了一种从高分辨率Ikonos卫星影像上基于知识规则的面向对象分类提取城区建筑物方法，包括如下步骤：(1)融合1m全色和4m多光谱波段影像，生成1m分辨率的多光谱融合影像；（2）分割融合影像；（3）执行基于对象光谱的最近邻监督分类；（4）应用模糊逻辑分类器结合光谱、空间、纹理和上下文特征等知识规则进行建筑物分类。精度统计结果表明，本文提出的分类方法提取城区建筑物取得了93%的精度。

Urban Building Extraction from VHR Multi-spectral Images Using Object-based Classification

Building extraction in urban environment requires high spatial resolution remotely sensed data. However, traditional pixel-based classifiers based on spectral features are ineffective for high-resolution multi-spectral images due to large within-class spectral variations and between-class spectral confusions. In this study, a rule-based object-oriented classification method for building extraction is developed from an Ikonos urban scene. The method includes the following steps: (1) fusion of 1m panchromatic and 4m multispectral bands to produce a pan-sharpened 1m multispectral image; (2) segmentation of the 1m dataset; (3) supervised object-based classification into broad spectral classes; and (4) spectral, spatial, textural and contextual parameters developed from sample building objects are implemented in a fuzzy logic rule base to separate building rooftops from other impervious surface classes. The rule-based method identifies building rooftops with 93% accuracy in the experiment.