中文摘要：

云类识别是实现卫星云图自动分析的基础,针对卫星云图易受噪声干扰且不同云系往往相互交叠的特点,构造一种面向云类识别的自适应模糊支持向量机。该方法不仅改进了隶属度函数的表现形式,而且通过定义控制临界隶属度和隶属度衰减趋势的参数,使隶属度能根据不同云系样本的具体分布特性自适应调整,解决了传统模糊支持向量机的隶属度函数难以反映样本分布的问题。在MTSAT卫星云图上的实验结果表明,通过提取云图可见光通道的反照率、红外通道的亮温及三种亮温差作为云图的光谱特征,并结合统计纹理特征,所构造的自适应模糊支持向量机分类器能有效区分晴空区、低云、中云、高云及直展云;云类识别准确率优于标准支持向量机和传统模糊支持向量机,且具有更强的稳定性和自适应性。

英文摘要：

The classification of clouds plays an important role in analyzing satellite imagery automati- cally. Specific to the characteristics that satellite imagery is susceptible to noises and different types of clouds tend to overlap, a classifier based on adaptive fuzzy support vector machine （AFSVM） for clas- sification of clouds is constructed. First, the classifier confirms a minimum hypersphere to distinguish effective samples and no-effective samples by Support Vector Data Description （SVDD） method. The samples inside of the hypersphere are taken as effective samples, while the samples outside of the hy- persphere are regard as no-effective samples. Then the formula of membership function is modified to make that the membership attenuation speed of the effective samples is slower than that of the no-ef- fective samples. Finally, the paper defines three parameters to control specially the critical member- ship degree and the attenuation trend of membership function. The proposed membership function o- vercomes the shortcoming of the traditional FSVM that its membership function could not describe the distribution of samples effectively, and makes itself adjust adaptively according to the specific dis- tribution characteristics of different cloud sample sets. Experiments were conducted on MTSAT satel- lite imagery, the results showed that by extracting the spectral feature of the albedo of VIS channel, the bright temperatures of four IR channels and the three bright temperature differences as the spec- tral features, and combined with the statistical texture features, the proposed classifier is able to dis- tinguish the clear weather, low clouds, middle clouds, high clouds and clouds with vertical develop- ment effectively with high accuracies, and the performances are superior to the standard SVM and tra- ditional FSVM in terms of stability and adaptability.