一种利用纹理特征和朴素贝叶斯分类器检测近景影像植被的方法

针对植被对近景摄影测量自动滑坡监测影响严重的问题,提出了一种基于纹理特征和朴素贝叶斯分类器的滑坡植被区域检测算法。对算法的有效性、影像对比度拉伸以及样本训练通用性对检测植被区域的效果等若干问题进行了实验探讨。通过与基于视觉认知特征的检测方法比较,验证了本算法的实用性和有效性。实验结果表明,本文算法能够很好地检测出近景影像中的植被区域,结果比较满意。

Vegetation Detection of Close-Range Images Based on Texture Features and Naive Bayes Classifier

Considering of the problems of serious effects caused by vegetation on automatic landslide monitoring in close-range photogrammetry,we present a method of detecting vegetation regions in landslide images based on texture features and naive Bayes classifier.Some meaningful discussions and analysis have been done mainly for the effectiveness of this algorithm,image contrast stretching and the generality problem of samples training.Comparing with another detection method based on visual cognition features,we prove the availability and the validity of this method.The experimental results show that the vegetation detection method can almost detect the vegetation regions from close-range images and the result is satisfying.