基于正交匹配小波算法的台风云系提取研究  

Segmentation of typhoon cloud systems with orthogonal matching pursuit algorithm

作　　者：王毅[1] 孙佳俊[1,2] 项杰[1] 任建齐[1] 

机构地区：[1]解放军理工大学气象海洋学院 [2]91323部队气象台

出　　处：《海洋学报》2012年第5期59-64,共6页

基　　金：江苏省自然科学基金项目(BK2011125);解放军理工大学预研基金项目(20110401);国家自然科学基金(40805006)资助项目

摘　　要：西北太平洋是世界上台风发生频率最高、强度最强的一个海区,因此对西北太平洋台风的发生发展进行相关的分析研究是很有意义的。论文中利用静止卫星观测数据,进行了滤波、去噪等预处理,及综合优化的云检测处理;在此基础上,利用改进的正交匹配小波算法,实现了西北太平洋地区台风云系特征的提取。运用该算法提取出的台风云系特征参数简单,与其他算法比较,尽管提取精度有待改进,但是用于台风的监测预警可提高效率,适用于台风预报预警监测的业务化应用。The North-west Pacific（NWP） Ocean is one of the places that have the maximal frequency of tropical cyclones（TC） and the highest intensity of TCs in the world.It is significant to investigate the characteristics of TCs in the NWP.Nephogram is an important tool for monitoring tropical cyclone and typhoon in the tropical ocean,effective classification of image data and the segmentation of typhoon cloud are key steps for subsequent image feature extraction.Matching pursuit is one of the most important algorithm in signal processing and of vast application remote sensing image pattern recognition.In the paper,Matching pursuit algorithm is proposed to realize typhoon feature extraction in the NWP.Although the veracity is needed to be improved,the algorithm could efficiency segment the main typhoon cloud systems,and can satisfy typhoon forecast and monitoring well in the meteorological applications.

关 键 词：图像处理 特征提取 正交 匹配 西北太平洋 台风 

分 类 号：P407.8[天文地球—大气科学及气象学]