本文提出了一种基于多源卫星图像融合的水坝检测方法，该方法在特征级融合的模式下，利用多源卫星图像特征信息互补的优势，先后提取多个卫星图像中目标的特征信息，再通过多传感器数据融合方法中的逻辑模板法对特征进行融合，得到系统的目标结果输出。试验结果显示，该算法能在大幅复杂背景下有效地对水坝进行检测并定位，并减少了单源卫星图像进行目标检测的错判、误判率。整个算法能完全实现自动检测，可达到预想的目的。

A method of dam detection based on multi-source satellite images fusion is brought forward. Under the pattern of feature level fusion, this approach utilizes the advantage, which adopts commutative complementarily characters of multi-source remote sensing. First, extra the features in multi-source satellite images in turn. Then these features are fused by logic template of multi-sensor fusion to get the target detection output of the system. The result of the test proves that the approach can effectively detect and locate the dam in the large complex remote sensing image and reduce the miscarriage of justice and mistake in only one satellite image. The whole algorithm can work automatically, achieving the anticipating aim.