机器视觉石油筛管割缝亚像素检测方法  

Oil Screen Slot Sub-pixel Detection Method Based on Machine Vision

作　　者：梁春疆 段发阶[1] 徐瀛[1] 冯帆[1] 

机构地区：[1]天津大学精密仪器与光电子工程学院,天津300072

出　　处：《纳米技术与精密工程》2016年第3期186-190,共5页Nanotechnology and Precision Engineering

基　　金：国家自然科学基金资助项目(51275349)

摘　　要：针对目前石油筛管割缝缝宽人工检测的局限性和不确定性,提出一种基于机器视觉检测技术的石油筛管割缝缝宽检测方法.首先通过CCD相机采集筛管割缝图像;然后对割缝进行高斯滤波预处理去除杂散噪声,利用改进的Sobel算法提取割缝边缘,使用最小二乘法对提取的灰度边缘进行直线拟合,再计算两条直线间距平均值;最后输出割缝的缝宽.本方法实现了对筛管割缝缝宽的快速自动化高精度测量,实验结果表明:本方法的测量误差小于0.02 mm,检测时间小于3 s,测量结果稳定可靠,为石油筛管的制造和使用提供了一种新的测量手段.To overcome the limitations and uncertainties in manual detection of oil screen slot, a new oil screen slot detection method based on machine vision inspection technology is proposed. First, the screen slot image is acquired by CCD camera. Second, the slot is pretreated to remove spurious noise with Gaussian filtering and then the edge is extracted with improved Sobel algorithm. The gray edges are fitted to two straight lines by least squares method, between which the average distance is calculated. At last, the width of the slot is output. This method realizes fast automated precision measurement of screen slot. Experimental result shows that the measurement error is less than 0 . 02 mm and the detection time is less than 3 s. The stable and reliable results provide a new measurement means of producing and using oil screen.

关 键 词：石油筛管割缝 亚像素 边缘检测 图像处理 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]