基于OpenCV的透明瓶装无色液体液位实时检测
DOI:
CSTR:
作者:
作者单位:

(1.聊城大学 物理科学与信息工程学院,山东 聊城 252059; ;2.山东省光通信科学与技术重点实验室,山东 聊城 252059)

作者简介:

姚 坤(1990-),男,山东菏泽人,硕士研究生,主要从事机器视觉方向的研究。 葛广英(1964-),男,山东聊城人,教授,硕士研究生导师,主要从事机器视觉、物联网方向的研究。[FQ)]

通讯作者:

中图分类号:

基金项目:

国家自然科学基金(10874063)。


Real-time Detection of Colorless Liquid Level in Transparent Bottle Based on OpenCV
Author:
Affiliation:

(1.College of physics and information engineering,Liaocheng University,Liaocheng 252059, China; ;2.Shandong Key Laboratory of Optical Communication Science and Technology,Liaocheng University, Liaocheng 252059,China)[JZ)]

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为了实现对无色液体透明瓶装产品的非接触性检测,设计一种液位实时检测系统;系统通过工业数字摄像头实时采集产品图像,基于OpenCV开源平台,对其进行相关的预处理,检索液体区域的轮廓,提出了一种适合液位检测的包围盒取高算法,可得到液位高度;图像采集过程中利用白色背景和特殊的光源设计突显液体区域,不借助外部测量仪器对液位进行实时检测;对100副不同液位的产品图像进行测试,测量结果表明,此系统能够快速准确地获得瓶装液体的高度信息,最大相对误差0.8%,具有较好的准确性和实时性。

    Abstract:

    In order to realize the non-contact detection of colorless liquid level in transparent bottle, a kind of liquid level real-time detection system was designed. The system acquires the real-time image of products through a industrial digital camera, and then retrieve the liquid region after a series of pretreatments which are based on OpenCV open-source platform, a bounding box algorithm suitable for liquid level detection was proposed, the height of liquid level can be obtained. The white background and a special design of light source highlight the liquid area, the system can realize real-time detection without external measuring instrument. In a test including 100 images of products with different liquid levels, the measured results showed that this system can get the height of bottled liquid rapidly and accurately, the maximum relative error is 0.8%, which has a good accuracy and real-time performance.

    参考文献
    相似文献
    引证文献
引用本文

姚坤,葛广英,肖海俊,隋婉婉.基于OpenCV的透明瓶装无色液体液位实时检测计算机测量与控制[J].,2015,23(1):34-36.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2015-03-27
  • 出版日期:
文章二维码