基于支持向量机分类树的地基云图分类分析-classification and analysis of foundation nephogram based on support vector machine classification tree.docx

AbstractNowadays, Clouds are playing an essential role in the atmosphere and cloud classes can be seen as indicators of the type and intensity of locally active thermal processes. Cloud cover, type and height measurements are collected by means of both satellite and ground-based weather stations. However, the satellite images data storage space is so vast that it can’t afford a real-time process operation. Consequently, we have to predict weather in a short time and local area by using the ground-based cloud images,In this paper, we propose a novel method for ground-based cloud classification. We firstly compute different texture features from the ground-based cloud images according to the images’ characteristics, and we select three feature groups from lots of features for image analyze. But with further experimentations we can find out that features from Gabor feature group have high discrimination performance. The Gabor feature group is based on 2D Gabor filters with the theory of multichannel decomposition. These features are more robust and effective than the well-known features such as gray-level co-occurrence matrix (GLCM), the Run-Length Texture Feature and the structure features.Due to the training samples are usually selected randomly, which can cause high complexity of the classifier, thus the training samples were clustered into several clusters by using the supervised clustering algorithm. And a small quantity of representative instances was chosen as training sets.At last, Ensemble SVMs and binary-tree SVMs were constructed. According to lots of experimentations, the result shows that these methods have higher classification accuracy and lower space complexity comparing to the other classification algorithms. KeyWords: Ground-based cloud, classification-tree, Gabor filter, support vector machine, sorted spectral histogram, Bag of Words目录摘要 IAbstract II1绪论1.1研究的目的和意义 (1)1.2气象云图分类研究现状 (2)1.3地基云图分类的难点 (3)1.4论文研究内容和结构 (4)2地基云图的纹理特征提取2.1