Research on algorithm of vision real-time measurement for liquid level of oil tank

LIU Qi-hai; LIN Yu-chi; WU Ying; SONG Le; ZHAO Mei-rong

doi:10.13873/j.1000-97872010.02.018

Chinese

您当前的位置：

首页 >

文章列表页 >

Research on algorithm of vision real-time measurement for liquid level of oil tank

更新时间：2025-09-11

- Research on algorithm of vision real-time measurement for liquid level of oil tank
- Vol. 29, Issue 2, Pages: 54-56(2010)
- 作者机构：
  
  天津大学精密测试技术及仪器国家重点实验室
- 作者简介：
- 基金信息：
- DOI：10.13873/j.1000-97872010.02.018
  CLC： TP391.41
- Published：2010
- 稿件说明：
移动端阅览
[1]刘启海,林玉池,吴颖,宋乐,赵美蓉.油舱液位视觉实时测量算法的研究[J].传感器与微系统,2010,29(02):54-56.

LIU Qi-hai, LIN Yu-chi, WU Ying, et al. Research on algorithm of vision real-time measurement for liquid level of oil tank[J]. 2010, 29(2): 54-56.
[1]刘启海,林玉池,吴颖,宋乐,赵美蓉.油舱液位视觉实时测量算法的研究[J].传感器与微系统,2010,29(02):54-56. DOI： 10.13873/j.1000-97872010.02.018.

LIU Qi-hai, LIN Yu-chi, WU Ying, et al. Research on algorithm of vision real-time measurement for liquid level of oil tank[J]. 2010, 29(2): 54-56. DOI： 10.13873/j.1000-97872010.02.018.

摘要

为了实现油轮油舱液位测量的自动化和数字化

研制了一种基于S3C2440 ARM9平台的视觉自动测量仪器

使用C语言和嵌入式开发工具ADS开发出一种有效的自适应图像处理算法。根据液位测量范围自制了30m长的特殊尺子。提出了以自适应阈值二值化、数学形态学除噪和字符分割为基础的尺子图像预处理算法。在总结尺子数字和刻度特征的基础上

分析了尺子整数数字识别和小数部分读数的算法。实验结果表明:仪器每次自动读数的时间小于0.4 s;识别的准确率达98%以上;精度为0.1 mm。该算法具有高精度、高速度、稳定性好、自动化程度高等特点

有效解决了传统油位测量中需要人工读数和测量精度低的问题

完全满足油舱液位的实时测量要求。

Abstract

In order to realize automatic measurement for liquid level of oil tank

a new type of vision automatic measurer is developed based on S3C2440 ARM9 platform.A type of adaptive image processing algorithms are developed by C language and embedded development tool

arm development suite（ADS）.According to measuring range

a 30 m long ruler is specially made.Pretreatment algorithms of ruler image are presented on the basis of adaptive threshold binarization

mathematic morphology noise-removing and characters segmentation.After features of ruler characters and scales are summarized

the algorithm of integer recognition and decimal reading is analyzed.Experimental results indicate that it takes no more than 0.4 s averagely in each auto-reading and the recognition accuracy rate is 98 %

and the precision is 0.1 mm.The algorithm has the advantages of high precision

high speed

well stability

high automation

and can effectively solve the problem of low measurement precision of manual measurement methods

thus completely satisfied requirement of real-time measurement for oil tank liquid level.

关键词

Keywords

references

工件图像识别的边缘匹配方法研究 [J]. 王红涛,傅卫平,康业娜. 仪器仪表学报 . 2008(05)

万能工具显微目镜视场字符识别的预处理算法 [J]. 陈智君,林玉池,赵美蓉,周文斌,黄银国,王帅. 光电子·激光 . 2005(01)

利用中值滤波进行图像处理 [J]. 孙宏琦,施维颖,巨永锋. 长安大学学报(自然科学版) . 2003(02)

数字图像处理与分析[M]. 清华大学出版社 , 龚声蓉,刘纯平,王强等编著, 2006

Visual C++/MATLAB图像处理与识别实用案例精选[M]. 人民邮电出版社 , 胡小锋,赵辉编著, 2004

Handwritten numeral recognition using gradient and curvature of gray scale image [J] . Meng Shi,Yoshiharu Fujisawa,Tetsushi Wakabayashi,Fumitaka Kimura. Pattern Recognition . 2002 (10)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Cricket vision control system based on double-loop PID algorithm and Otsu method

Processing of crown character on paper currency image captured by CIS

Application in measuring plant growth increment with a linear CCD technology

Study on quick capturing and recognition of moving numeric characters on static background

Related Author

XU Yunji

GONG Ming

GONG Cheng

WANG Li

WU Lu-lu

WANG Yuan-qing

WEI Jun-li~

宋良图

Related Institution

Electrical and Information Engineering Branch,Institute of Technology,East China Jiaotong University

College of Mechanical and Electrical Engineering,Nanchang University

College of Information and Communication Engineering,Hainan University

School of Electronic Science and Engineering,Nanjing University

1,2),SONG Liang-tu~1

⁰