霍夫变换在卫星云图异常数据检测中的应用  

Application of Hough Transform to Abnormal Data Detection in Satellite Cloud Pictures

作　　者：蔡菲菲[1] 闫振宇[1] 郎宏山[1] 

机构地区：[1]国家卫星气象中心北京气象卫星地面站,北京100094

出　　处：《气象科技》2018年第1期39-42,50,共5页Meteorological Science and Technology

摘　　要：由于噪声与干扰的存在,导致卫星云图接收过程中产生丢线、马赛克等异常数据。依靠人工进行检测与统计,不仅工作效率低,准确性也得不到保证。研究基于霍夫变换的卫星云图异常数据的检测方法,并且结合其分布特点,针对卫星云图实时性要求高、传统霍夫变换运算量大的问题对边缘检测算子检测方向进行了优化,试验结果表明可以有效提高30%的运算速度。实现对卫星云图异常数据的准确定位与快速检测,对于日后排查干扰源,进一步提高卫星云图接收质量具有重要意义。The existence of noise and interference results in the occurrence of abnormal data such as mosaic and losing signals in the receiving process of satellite cloud pictures.Relying upon artificial detection and positioning,the work efficiency and the accuracy cannot be guaranteed.An abnormal data detection method of satellite cloud pictures is studied in this paper based on Hough Transform,which improved the direction of the edge detection operator to aim at the problem of the high requirement of real-time satellite cloud pictures and large-amount calculation of traditional Hough Transform combining with the characteristics of abnormal data.Experiment results show that the improved algorithm improved the arithmetic speed by 30%.It realizes the accurate positioning and rapid detection of satellite cloud picture abnormal data and has great significance for the interference source investigation and the improvement of the reception quality of satellite cloud images in the future.

关 键 词：卫星云图 异常数据 边缘检测 霍夫变换 

分 类 号：P409[天文地球—大气科学及气象学]