计算机工程 ›› 2010, Vol. 36 ›› Issue (9): 195-196.doi: 10.3969/j.issn.1000-3428.2010.09.068

• 人工智能及识别技术 • 上一篇    下一篇

基于红外云图的台风中心智能定位方法

牛海军,杨 夙   

  1. (复旦大学计算机科学技术学院,上海 200433)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2010-05-05 发布日期:2010-05-05

Intelligent Location Method of Typhoon Center Based on Infrared Cloud Image

NIU Hai-jun, YANG Su   

  1. (School of Computer Science, Fudan University, Shanghai 200433)
  • Received:1900-01-01 Revised:1900-01-01 Online:2010-05-05 Published:2010-05-05

摘要: 台风中心附近的云墙是同心圆状云带且其灰度值范围较固定,针对该特点,利用红外云图对台风中心进行智能定位,提出由云图预处理、Snake活动轮廓模型提取台风云墙轮廓点、最小二乘法拟合圆组成的3步定位方法。实验结果表明,该方法定位速度快、精度高,能满足气象业务的实时性要求。

关键词: 台风眼, 云墙, 螺旋云带, 活动轮廓模型, 最小二乘拟合

Abstract: Cloud wall around typhoon center is concentric-circle-liked cloud band, and its gray scale is stable usually. Aiming at this feature, this paper uses infrared cloud images to intelligently locate typhoon center. It presents a three-step location method which includes pre-process of cloud image, extraction of contour points of typhoon cloud wall based on Snake active contour model, circle fitting based on Least Square(LS). Experimental results show that this method has fast location speed, high precision, and it can satisfy the real-time requirement of weather service.

Key words: typhoon eye, cloud wall, spiral band, active contour model, Least Square(LS) fitting

中图分类号: