基于AdaBoost算法的遥感影像水体信息提取

Water body extraction from remote sensing image based on AdaBoost algorithm

AdaBoost算法利用每个特征构造一个简单分类器,然后将简单分类器进行训练组合成一个强分类器。算法能够充分利用每个分类器的优势并避免其劣势,得到一个最佳判别,达到提高分类精度的目的。本文利用TM影像,将影像各波段灰度、水体指数和谱间关系特征相结合,构成提取水体的强分类器,实现水体提取。实验结果表明,算法能够非常有效地、高精度地提取水体信息。

For water body extraction from RS image, previous algorithms have devoted to found a sophisticated classifier based on single feature, which can not make full use of image information and are very difficult to train complex classifier. Adaboost algorithm constructs a simple classifier using each feature, the ＂strong classifier＂ is formed after training these simple classifiers. The algorithm can make use of the advantages of the various classifiers and avoid their weaknesses, so it can get a prefer judgment and improve the classification accuracy. In this paper, the strong classifier of extracting body information was constructed after combining spectral infor- mation of each band, water index and relationship between spectrums. Using TM imagery as study data, the resuhs of experiment showed that the algorithm could extract water body information effectively and accurately.