基于机器视觉的试管液位检测方法研究  

Research on Test Tube Liquid Level Detection Method Based on Machine Vision

作　　者：董军 Dong Jun(University of Shanghai for Science and Technology,Shanghai 200434,China)

机构地区：[1]上海理工大学,上海市200434

出　　处：《农业装备与车辆工程》2021年第1期108-111,115,共5页Agricultural Equipment & Vehicle Engineering

摘　　要：利用目前机器视觉技术,提出一种基于数字形态学结合Laplacian算子的边缘检测算法,将其应用到对试管液面检测中,得到了精度高、定位准的液面位置,从而可以得出液面高度与试管内试剂体积。通过CCD工业相机拍摄试管图像,对图像进行灰度化、滤波,图像增强后,利用LoG边缘检测算法结合数字形态学操作得到清晰的边缘图像,最后得出准确的图像液位高度,可以在无外界辅助测量设备的情况下完成试管液位检测。通过对80张不同液位高度的试管图像进行测试,结果表明,该算法可以有效完成液位非接触测量,并可以快速地得出准确的测量结果。This paper uses the current machine vision technology to propose an edge detection algorithm based on digital morphology and combined with Laplacian operator.It is applied to the test tube liquid level detection,and the liquid level position with high precision and accurate positioning can be obtained,therefore the height of the liquid level and the volume of the reagent in the test tube are got.The test tube image is taken by the CCD industrial camera,the image is grayed,filtered,and the image is enhanced.The LoG edge detection algorithm combined with the digital morphology operation is used to obtain a clear edge image,and finally an accurate image liquid level height can be obtained.Test tube liquid level detection is completed without external auxiliary measuring equipment.By testing 80 test tube images with different liquid level heights,the experimental results show that the algorithm can effectively complete non-contact liquid level measurement and can quickly obtain accurate measurement results.

关 键 词：机器视觉 液位检测 数字形态学 LOG算法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]