基于视觉的某炮弹药筒退弹槽槽底宽度精确测量研究  

Groove Width Detection of Right-angle Trapezoidal Groove Based on Vision

作　　者：张川川[1] 吴秀玲[1] 曾志强[1] 王俊元[1] 柳旭[1] 

机构地区：[1]中北大学机械与动力工程学院,太原030051

出　　处：《包装工程》2014年第3期74-77,136,共5页Packaging Engineering

基　　金：2013山西省自然科学基金项目(2013011025-1)

摘　　要：目的某炮弹药筒退弹槽底宽检测速度和精度要求比较高,传统的手工测量适应不了自动化生产的需要。方法用DH-SV1410型CCD摄像机及可调LED光源构建图像采集系统,并在VS2010平台上用C#语言编写一套基于机器视觉的测量系统。采用亚像素边缘轮廓提取方法精确定位退弹槽的边缘轮廓,并设计一个针对退弹槽底宽检测算法。结果通过对一个零件相同部位进行重复对比实验和多个零件测量对比试验表明,该系统在微米级上有误差,但最大误差最大不超过2μm。结论该系统的检测精度能够达到10μm,完全能满足某炮弹药筒在线测量的速度和精度要求,且测量结果不受主观因素的影响。Objective According to industrial inspection speed and accuracy requirements of groove width detection of cartridge, traditional manual measurement does not meet the needs of automatic production. Methods An Image Collection System was constructed using CCD camera of DH-SV1410 and LED source, meanwhile a measurement system was compiled by C# on VS2010 platform based on machine vision. The method of sub-pixel edge contour extraction was used to exact the location of groove edge and a groove width detection method of cartridge was designed. Results Comparative experiments on the same part of one cartridge and multiple cartridges showed that the system had micron error, with a maximum error of less than 2 micron. Conclusion The detection accuracy of the system in groove width of cartridge could achieve 10 micron order, which meets the requirement of online measurement of cartridge, and the measurement results were not influenced by subjective factors, with very high efficiency.

关 键 词：机器视觉 槽底宽检测 边缘检测 亚像素 拟合 

分 类 号：TB487[一般工业技术—包装工程] TB486