摘要： 为改善遥感影像分类精度，提出混合多分类器结合算法。考虑抽象级和测量级2个层次的特点，综合最优子分类器、Bagging算法和最大置信度区间法。应用到不同分辨率的遥感影像分类进行验证，结果表明，与选用的子分类器相比，该算法的总体精度和单个类别分类精度有明显提高，是有效的高中精度遥感影像分类算法。

关键词: 遥感分类, 混合多分类器结合, 抽象级, 测量级

Abstract: To improve the precision of remote sensing image classification, this paper proposes hybrid multi-classifier combination method. Taking the characteristic of abstract level and measurement level into consideration, the optimal sub-classifier, bagging algorithm and the most large confidence algorithm are combined. This method used in diffierent image classification shows a better enhancement, and results indicate that the hybrid multi-classifier combination algorithm is an effective algorithm for medium-high precision remote sensing image classification.

Key words: remote sensing classification, hybrid multi-classifier combination, abstract level, measurement level

中图分类号: 

• TP75