基于图像自动识别技术的雨滴谱测量方法  

Automatic measurement method of raindrop size distribution based on computer vision

作　　者：朱磊[1,2] 曹治国[1] 肖阳[1] 李肖霞[3] 马舒庆[3] 

机构地区：[1]华中科技大学自动化学院,武汉430074 [2]武汉科技大学信息科学与工程学院,武汉430081 [3]中国气象局大气探测中心,北京100081

出　　处：《计算机应用研究》2015年第9期2866-2869,2873,共5页Application Research of Computers

基　　金：国家公益性行业(气象)科研专项基金资助项目(GYHY200906032);国家大学生创新创业训练计划资助项目(201410488015);武汉科技大学青年科技骨干培育计划(校基金)资助项目(2015X2010)

摘　　要：针对摄像方式的雨滴谱测量方法中存在人工参与多的缺点,提出了一种基于计算机视觉的雨滴谱测量方法。该方法分为雨滴目标自动识别及雨滴谱计算两个步骤。采用各项异性扩散滤波的方式对雨滴图像进行降噪,结合图像分割与形态学等操作达到识别个体雨滴目标的目的。基于识别结果以及雨滴平面—立体转换方程,进一步计算得到实时雨滴谱。实验证明,该方法对雨滴群中单独个体的检测较为准确,并能够测量具有较广谱宽的雨滴谱分布。As the photograph-based raindrop size measurement std＇fcrs from various manual interactions,this paper proposed a new method for measuring raindrop size distribution based on computer vision. This approach included two steps ： firstly,it ap- plied the anisotropic filtering to reduce the image noise and recognized raindrops automatically by incorporating the techniques such as segmentation and morphologic operations. Based on the recognition results and the calibrated 2D-3D transier equation, this method computed raindrop size distribution directly from all raindrops. Experimental results demonstrate that the proposed method achieves a good performance on detecting raindrops and is capable of measuring raindrop size distribution with wide bandwidth.

关 键 词：雨滴谱 计算机视觉 各项异性扩散滤波 图像分割 形态学操作 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]