基于机器视觉的浮选气泡体积和表面积测量研究  

Research on Measurement of Volume and Surface Area of Flotation Bubbles Based on Machine Vision

作　　者：梁秀满 刘文涛 牛福生 田童 Liang Xiuman;Liu Wentao;Niu Fusheng;Tian Tong(College of Electrical Engineering,North China University of Science and Technology,Tangshan,Hebei 063210,China;College of Mining Engineering,North China University of Science and Technology,Tangshan,Hebei 063210,China)

机构地区：[1]华北理工大学电气工程学院,河北唐山063210 [2]华北理工大学矿业工程学院,河北唐山063210

出　　处：《光学学报》2018年第12期263-270,共8页Acta Optica Sinica

基　　金：国家自然科学基金(51474087)

摘　　要：受颗粒碰撞、机械搅拌等因素的影响,运动上升的浮选气泡会产生严重的偏转与形变。对此,提出一种用于测量气泡的体积和表面积的水平置位分割方法。建立了浮选工艺过程中运动气泡的观测系统,采集气泡图像。利用基于区域分割的边缘检测方法提取气泡边缘。针对重叠气泡,使用曲率尺度空间角点检测算法和方向链码标记凹点,以此分割重叠的轮廓,最小二乘拟合重建独立气泡的边缘。根据边缘计算气泡的偏转角度,自适应选取分割间隔。通过各分割部分的计算,累加得到气泡的体积和表面积。实验表明:所提取的边缘准确,不易受光照环境的影响。在不同搅拌速率条件下,测量气泡体积的平均误差与标准差分别为4.52%和0.057mm3。与其他方法相比,本文方法精度较高。Due to the impact of particles,the mechanical agitation and other factors,the rising floatation bubbles causes severe deflection and deformation.The horizontal set partitioning method is proposed for measuring the volume and surface area of the air bubbles.First,we establish an observation system for moving bubbles during the flotation process,and collect the bubble image.We use an edge detection method based on area segmentation to extract bubble edge.For overlapping bubbles,we use curvature scale space corner detection algorithm and direction chain code to mark the pits,thereby divide the overlapping contour.The edges of independent bubbles are fitted and reconstructed by least squares.Then we calculate the deflection angle of the bubble according to the edge,and adaptively select the separation interval,and finally the volume and surface area of the bubble are obtained by the accumulation of the divided portions.Experimental results show that the edge extracted by this method is accurate and not easily affected by the light environment.Under the conditions of different agitation rates,the average error and standard deviation of the measured bubble volume are 4.52%and 0.057mm3,which are more accurate than other methods.

关 键 词：机器视觉 气泡体积和表面积 边缘提取 矿物浮选 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]