###
气象:2007,33(10):73-79
本文二维码信息
码上扫一扫!
基于支持向量机的遥感大雾判识
(国家卫星气象中心,北京 100081)
Fog Judgment Based on the Support Vector Machine by Remote Sensing Data
(National Satellite Meteorological Center,Beijing 100081)
摘要
图/表
参考文献
相似文献
本文已被:浏览 566次   下载 738
投稿时间:2007-06-06    修订日期:2007-08-05
中文摘要: 提出了一种基于支持向量机的卫星遥感数据大雾判识方法:首先通过对风云 1D卫星大雾区域的各通道辐射值出现频次进行概率统计,利用其阈值来粗判识大雾;然后在 粗判识的基础上通过支持向量机的方法进行大雾细判识;最后利用腐蚀和膨胀的图像处理技 术对判识后的图像进行优化处理。在对我国2006年9-12月的65条监测到大雾的风云1D轨道 的探测数据进行分析之后,发现大雾判识结果与专家标记吻合。检验结果表明,利用1、2、 4、6、7、10通道组合进行粗判识的结果最好,5交叉正确率为89.9849%,TS评分为74.04%。 利用上述方法对个例的分析检验表明,基于支持向量机的遥感大雾判识方法是切实可行的。
Abstract:A method is put forward to recognize the fog based on the support vect or machine, according to the satellite remote sensing data. Firstly, the probabi lity statistics method is used to roughly judge the fog, according to the freque ncy of the fog areas appearing at different channels of FY 1D satellite; second ly, based on the former judgment, the support vector machine is applied to judge the fog carefully; lastly, erosion and dilation techniques are used to optimize the result of the second procedure. From September to December in 2006, 65 over passes of FY 1D satellite data including fog areas are analyzed, and the judged fog areas are found to correspond well to the experts' experience. And the resu lt shows that the combination of 1, 2, 4, 6, 7 and 10 channels is the best of ju dgment. The 5 fold cross validation is 89.9849% and the TS score is74.04%. This method is also used to recognize the fog during other time, and fou nd that this method is excellent.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本:
刘年庆,蒋建莹,吴晓京,2007.基于支持向量机的遥感大雾判识[J].气象,33(10):73-79.
Liu Nianqing,Jiang Jianying,Wu Xiaojing,2007.Fog Judgment Based on the Support Vector Machine by Remote Sensing Data[J].Meteor Mon,33(10):73-79.