Instrument recognition method based on Faster R-CNN

Na LI; Zhi JIANG; Jun WANG; Xing-fa DONG

doi:10.37188/YJYXS20203512.1291

您当前的位置：

首页 >

文章列表页 >

Instrument recognition method based on Faster R-CNN

Image Processing | 更新时间：2020-12-04

- Instrument recognition method based on Faster R-CNN
- Chinese Journal of Liquid Crystals and Displays Vol. 35, Issue 12, Pages: 1291-1298(2020)
- 作者机构：
  
  1.苏州科技大学电子与信息工程学院, 江苏苏州 215009
  2.中国白城兵器试验中心, 吉林白城 137001
  3.中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
- 作者简介：
- 基金信息：
  
  Jiangsu Province Graduate Workstation Project(2017272)
- DOI：10.37188/YJYXS20203512.1291
  CLC： TP391.41
- Received：06 August 2020，
  
  Revised：26 August 2020，
  
  Accepted：26 August 2020，
  
  Published：2020-12
- 稿件说明：
移动端阅览
Na LI, Zhi JIANG, Jun WANG, et al. Instrument recognition method based on Faster R-CNN[J]. Chinese journal of liquid crystals and displays, 2020, 35(12): 1291-1298.
DOI：

Na LI, Zhi JIANG, Jun WANG, et al. Instrument recognition method based on Faster R-CNN[J]. Chinese journal of liquid crystals and displays, 2020, 35(12): 1291-1298. DOI： 10.37188/YJYXS20203512.1291.

摘要

针对仪表识别系统背景复杂，对小目标不敏感，检测精度低等问题，本文提出一种特征融合金字塔（FPN）和Faster R-CNN网络结合的仪表自动识别方法。首先使用FPN和Faster R-CNN网络的RPN结合定位表盘和指针区域，并对多类仪表进行分类；此外为了平衡仪表图像的正负样本，提高检测准确性，引入Focal Loss损失函数与RPN网络结合进行训练数据集；其次对指针区域进行基于FPN的图像分割，将FPN网络与反卷积结合，提高指针区域分割准确性；最后拟合指针获取指针偏转角度，得到仪表读数。实验结果表明，提出的方法准确率达到94.25%，与传统算法相比，提出的方法不仅检测精度高，而且实用性更强。

Abstract

In view of the complex background of the instrument recognition system

insensitive to small targets

and low detection accuracy

an automatic instrument identification method combining Feature Fusion Pyramid (FPN) and Faster R-CNN network is proposed in this paper. First

FPN and the RPN of the Faster R-CNN network are used to combine the positioning of the dial and the pointer area

and to classify multiple types of meters. In addition

in order to balance the positive and negative samples of the meter images and improve the detection accuracy

the Focal Loss loss function is combined with the RPN network to train the data set. The FPN-based image segmentation is performed on the pointer area. The FPN network and deconvolution are combined to improve the accuracy of the pointer area segmentation

and finally the pointer is fit to obtain the pointer deflection angle and obtain the meter reading.The experimental results show that the accuracy of the proposed method reaches 94.25%. Compared with the traditional algorithm

the proposed method not only has high detection accuracy

but also has stronger practicability.

关键词

Keywords

references

HE P L, ZUO L, ZHANG C H, et al . A value recognition algorithm for pointer meter based on improved mask-RCNN[C]// Proceedings of the 2019 9 th International Conference on Information Science and Technology . Hulunbuir, China: IEEE, 2019: 108-113.

FANG Y X, DAI Y, HE G L, et al . A mask RCNN based automatic reading method for pointer meter[C]// Proceedings of 2019 Chinese Control Conference . Guangzhou, China: IEEE, 2019: 8466-8471.

RAO Y, YAN F, ZHUANG Y, et al . A real-time auto-recognition method for pointer-meter under uneven illumination[C]// Proceedings of 2019 IEEE International Conference on Real-Time Computing and Robotics . Irkutsk, Russia: IEEE, 2019: 890-894.

V KUCHERUK , I KURYTNIK , P KULAKOV , 等 . Definition of dynamic characteristics of pointer measuring devices on the basis of automatic indications determination . Archives of Control Sciences , 2018 . 28 ( 3 ): 401 - 418 .

韩绍超 , 徐遵义 , 尹中川 , 等 . 指针式仪表自动读数识别技术的研究现状与发展 . 计算机科学 , 2018 . 45 ( S1 ): 54 - 57 . http://www.cnki.com.cn/Article/CJFDTotal-JSJA2018S1011.htm http://www.cnki.com.cn/Article/CJFDTotal-JSJA2018S1011.htm .

S C HAN , Z Y XU , Z C YIN , 等 . Research review and development for automatic reading recognition technology of pointer instruments . Computer Science , 2018 . 45 ( S1 ): 54 - 57 . http://www.cnki.com.cn/Article/CJFDTotal-JSJA2018S1011.htm http://www.cnki.com.cn/Article/CJFDTotal-JSJA2018S1011.htm .

朱海霞 . 基于改进Hough变换和BP网络的指针仪表识别 . 电测与仪表 , 2015 . 52 ( 5 ): 11 - 14 . http://www.cnki.com.cn/Article/CJFDTotal-DCYQ201505003.htm http://www.cnki.com.cn/Article/CJFDTotal-DCYQ201505003.htm .

H X ZHU . Pointer instrument recognition based on BP network and improved Hough transform . Electrical Measurement & Instrumentation , 2015 . 52 ( 5 ): 11 - 14 . http://www.cnki.com.cn/Article/CJFDTotal-DCYQ201505003.htm http://www.cnki.com.cn/Article/CJFDTotal-DCYQ201505003.htm .

朱柏林 , 郭亮 , 吴清文 . 基于ORB和改进Hough变换的指针仪表智能识读方法 . 仪表技术与传感器 , 2017 . ( 1 ): 29 - 33, 73 . http://www.cnki.com.cn/Article/CJFDTOTAL-YBJS201701009.htm http://www.cnki.com.cn/Article/CJFDTOTAL-YBJS201701009.htm .

B L ZHU , L GUO , Q W WU . Intelligent recognition method for pointer meters based on ORB and improved Hough transform . Instrument Technique and Sensor , 2017 . ( 1 ): 29 - 33, 73 . http://www.cnki.com.cn/Article/CJFDTOTAL-YBJS201701009.htm http://www.cnki.com.cn/Article/CJFDTOTAL-YBJS201701009.htm .

姚洋 , 彭道刚 , 王志萍 . 基于改进Canny检测与Hough变换的仪表图像识别算法 . 上海电力学院学报 , 2020 . 36 ( 2 ): 183 - 189 . http://d.wanfangdata.com.cn/periodical/shdlxyxb202002015 http://d.wanfangdata.com.cn/periodical/shdlxyxb202002015 .

Y YAO , D G PENG , Z P WANG . The instrument image recognition algorithm based on Canny detection and Hough transform . Journal of Shanghai University of Electric Power , 2020 . 36 ( 2 ): 183 - 189 . http://d.wanfangdata.com.cn/periodical/shdlxyxb202002015 http://d.wanfangdata.com.cn/periodical/shdlxyxb202002015 .

邢浩强 , 杜志岐 , 苏波 . 变电站指针式仪表检测与识别方法 . 仪器仪表学报 , 2017 . 38 ( 11 ): 2813 - 2821 . http://www.cnki.com.cn/Article/CJFDTOTAL-YQXB201711024.htm http://www.cnki.com.cn/Article/CJFDTOTAL-YQXB201711024.htm .

H Q XING , Z Q DU , B SU . Detection and recognition method for pointer-type meter in transformer substation . Chinese Journal of Scientific Instrument , 2017 . 38 ( 11 ): 2813 - 2821 . http://www.cnki.com.cn/Article/CJFDTOTAL-YQXB201711024.htm http://www.cnki.com.cn/Article/CJFDTOTAL-YQXB201711024.htm .

徐发兵 , 吴怀宇 , 陈志环 , 等 . 基于深度学习的指针式仪表检测与识别研究 . 高技术通讯 , 2019 . 29 ( 12 ): 1206 - 1215 . http://www.cnki.com.cn/Article/CJFDTotal-GJSX201912007.htm http://www.cnki.com.cn/Article/CJFDTotal-GJSX201912007.htm .

F B XU , H Y WU , Z H CHEN , 等 . Research on pointer instrument detection and recognition based on deep learning . Chinese High Technology Letters , 2019 . 29 ( 12 ): 1206 - 1215 . http://www.cnki.com.cn/Article/CJFDTotal-GJSX201912007.htm http://www.cnki.com.cn/Article/CJFDTotal-GJSX201912007.htm .

HUANG Y, DAI X Y, MENG Q H. An automatic detection and recognition method for pointer-type meters in natural gas stations[C]// Proceedings of 2019 Chinese Control Conference . Guangzhou, China: IEEE, 2019: 7866-7871.

陈献明 , 王阿川 , 王春艳 . 基于深度学习的木材表面缺陷图像检测 . 液晶与显示 , 2019 . 34 ( 9 ): 879 - 887 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1384499&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1384499&Fpath=&index=-1&l=zh .

X M CHEN , A C WANG , C Y WANG . Image detection of wood surface defects based on deep learning . Chinese Journal of Liquid Crystals and Displays , 2019 . 34 ( 9 ): 879 - 887 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1384499&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1384499&Fpath=&index=-1&l=zh .

陈景明 , 金杰 , 王伟锋 . 基于特征金字塔网络的改进算法 . 激光与光电子学进展 , 2019 . 56 ( 21 ): 211505 http://www.cnki.com.cn/Article/CJFDTotal-JGDJ201921022.htm http://www.cnki.com.cn/Article/CJFDTotal-JGDJ201921022.htm .

J M CHEN , J JIN , W F WANG . Improved algorithm based on feature pyramid networks . Laser & Optoelectronics Progress , 2019 . 56 ( 21 ): 211505 http://www.cnki.com.cn/Article/CJFDTotal-JGDJ201921022.htm http://www.cnki.com.cn/Article/CJFDTotal-JGDJ201921022.htm .

代勤 , 王延杰 , 韩广良 . 基于改进Hough变换和透视变换的透视图像矫正 . 液晶与显示 , 2012 . 27 ( 4 ): 552 - 556 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1694612&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1694612&Fpath=&index=-1&l=zh .

Q DAI , Y J WANG , G L HAN . Perspective image rectification based on improved Hough transformation and perspective transformation . Chinese Journal of Liquid Crystals and Displays , 2012 . 27 ( 4 ): 552 - 556 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1694612&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1694612&Fpath=&index=-1&l=zh .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Camouflaged object segmentation based on edge enhancement and feature fusion

Point cloud denoising method based on image segmentation

Red blood cell image segmentation based on NODE-UNet++ and marker watershed

Improved multi-scale flame detection method

Traffic sign detection algorithm based on improved Faster R-CNN

Related Author

ZHU Ming

WU Chuan

LI Mingyan

GUAN Hao-yuan

LONG Jia-le

DU Zi-hao

ZHANG Jian-min

CHEN Fu-jian

Related Institution

University of Chinese Academy of Sciences

Changchun Institute of Optics， Fine Mechanics and Physics， Chinese Academy of Sciences

Beijing Xiaomi Mobile Software Co.， Ltd.

Faculty of Intelligent Manufacturing， Wuyi University

College of Medicine Information， Changchun University of Chinese Medicine

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰