基于卷积神经网络的漏液视觉检测

李思寒; 仇怀利; 吴佳; 沈彦

doi:10.37188/CJLCD.2020-0314

您当前的位置：

首页 >

文章列表页 >

基于卷积神经网络的漏液视觉检测

图像处理 | 更新时间：2021-04-28

- 基于卷积神经网络的漏液视觉检测
- Visual detection of liquid leakage based on convolutional neural network
- 液晶与显示 2021年36卷第5期页码：741-750
- 作者机构：
  
  1.合肥工业大学电子科学与应用物理学院, 安徽合肥 230601
  2.上海西派埃智能化系统有限公司, 上海 200233
- 作者简介：
  
  [ "李思寒(1996-), 女, 安徽蚌埠人, 硕士研究生, 2018年于合肥工业大学获得学士学位, 主要从事机器学习、计算机视觉的研究。E-mail:iessy@qq.com" ]
  [ "仇怀利(1977-), 男, 山东聊城人, 博士, 副教授, 2004年于中国科学院安徽光学精密机械研究所获得博士学位, 主要从事光学薄膜材料、光电检测技术的研究。E-mail: hlq@hfut.edu.cn" ]
- 基金信息：
- DOI：10.37188/CJLCD.2020-0314
  中图分类号： P391.4;U179.8;X924.2
- 收稿日期：2020-11-26，
  
  修回日期：2020-12-16，
  
  纸质出版日期：2021-05
- 稿件说明：
移动端阅览
李思寒, 仇怀利, 吴佳, 等. 基于卷积神经网络的漏液视觉检测[J]. 液晶与显示, 2021,36(5):741-750.

Si-han LI, Huai-li QIU, Jia WU, et al. Visual detection of liquid leakage based on convolutional neural network[J]. Chinese journal of liquid crystals and displays, 2021, 36(5): 741-750.
李思寒, 仇怀利, 吴佳, 等. 基于卷积神经网络的漏液视觉检测[J]. 液晶与显示, 2021,36(5):741-750. DOI： 10.37188/CJLCD.2020-0314.

Si-han LI, Huai-li QIU, Jia WU, et al. Visual detection of liquid leakage based on convolutional neural network[J]. Chinese journal of liquid crystals and displays, 2021, 36(5): 741-750. DOI： 10.37188/CJLCD.2020-0314.

摘要

针对在工厂内设备结构复杂、杂物种类众多、地面磨损严重的现场环境下进行漏液检测时，传统图像处理方法准确率低的问题，本文提出一种基于CNN的漏液检测算法。通过对漏液检测问题进行分析，制作数据集，建立VGG16模型并结合早停算法训练样本，避免过拟合状态，实现了对复杂管道的漏液快速自动检测。在工业现场，该方法可以准确识别漏液并减小噪声干扰的影响。最终通过与多种图像处理方法作对比验证了本文算法的优越性。结果表明，该算法测试准确率可以达到99.44%，预测准确率达到97.0%，高于传统图像处理算法的准确率，且单张图片预测时间约0.2 s，满足工业现场的检测需求。

Abstract

Aiming at the problem of low accuracy of traditional image processing methods for liquid leakage detection in a factory with complex equipment structure

numerous types of debris

and severe ground wear

a leak detection algorithm based on CNN is proposed. The leak detection problems is analyzed

the data set is made

the VGG16 model is established. In order to avoid over-fitting state

combined with early stopping algorithm to train samples

the rapid and automatic detection of the leakage of complex pipelines is achieved. In industrial sites

this method can accurately identify the leakage and reduce the impact of noise interference. Finally

the superiority of this algorithm is verified by comparison with a variety of image processing methods. The results show that the test accuracy of the algorithm can reach 99.44%

and the prediction accuracy can reach 97.0%

which is higher than the accuracy of traditional image processing algorithms. The prediction time of a single picture is about 0.2 s

which can meet the detection needs of industrial sites.

关键词

Keywords

references

吴昌睿 , 黄宏伟 . 地铁隧道渗漏水的激光扫描检测方法及应用 . 自然灾害学报 , 2018 . 27 ( 4 ): 59 - 66 .

C R WU , H W HUANG . Laser scanning inspection method and application for metro tunnel leakage . Journal of Natural Disasters , 2018 . 27 ( 4 ): 59 - 66 .

何国华 , 刘新根 , 陈莹莹 , 等 . 基于数字图像的隧道表观病害识别方法研究 . 重庆交通大学学报(自然科学版) , 2019 . 38 ( 3 ): 21 - 26 . DOI: 10.3969/j.issn.1674-0696.2019.03.04 http://doi.org/10.3969/j.issn.1674-0696.2019.03.04 .

G H HE , X G LIU , Y Y CHEN , 等 . Apparent tunnel diseases identification based on digital images . Journal of Chongqing Jiaotong University (Natural Science) , 2019 . 38 ( 3 ): 21 - 26 . DOI: 10.3969/j.issn.1674-0696.2019.03.04 http://doi.org/10.3969/j.issn.1674-0696.2019.03.04 .

马勇 , 成谢锋 , 唐振民 , 等 . 野外场景分析与水体识别新方法的研究 . 电子学报 , 2013 . 41 ( 7 ): 1419 - 1424 . DOI: 10.3969/j.issn.0372-2112.2013.07.027 http://doi.org/10.3969/j.issn.0372-2112.2013.07.027 .

Y MA , X F CHENG , Z M TANG , 等 . New methods for outdoor scene analysis and water body identification . Acta Electronica Sinica , 2013 . 41 ( 7 ): 1419 - 1424 . DOI: 10.3969/j.issn.0372-2112.2013.07.027 http://doi.org/10.3969/j.issn.0372-2112.2013.07.027 .

李太文 , 范昕炜 . 基于Faster R-CNN的道路裂缝识别 . 电子技术应用 , 2020 . 46 ( 7 ): 53 - 56, 59 .

T W LI , X W FAN . Road crevice recognition based on Faster R-CNN . Application of Electronic Technique , 2020 . 46 ( 7 ): 53 - 56, 59 .

高新闻 , 简明 , 李帅青 . 基于FCN与视场柱面投影的隧道渗漏水面积检测 . 计算机测量与控制 , 2019 . 27 ( 8 ): 44 - 48 .

X W GAO , M JIAN , S Q LI . Identification of seepage area of tunnel based on FCN and field projection model . Computer Measurement & Control , 2019 . 27 ( 8 ): 44 - 48 .

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#10.3788/YJYXS20193409.0879 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193409.0879 .

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#10.3788/YJYXS20193409.0879 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193409.0879 .

马浩鹏 , 朱春媚 , 周文辉 , 等 . 基于深度学习的乳液泵缺陷检测算法 . 液晶与显示 , 2019 . 34 ( 1 ): 81 - 89 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193401.0081 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193401.0081 .

H P MA , C M ZHU , W H ZHOU , 等 . Defect detection algorithm of lotion pump based on deep learning . Chinese Journal of Liquid Crystals and Displays , 2019 . 34 ( 1 ): 81 - 89 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193401.0081 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193401.0081 .

郑远攀 , 李广阳 , 李晔 . 深度学习在图像识别中的应用研究综述 . 计算机工程与应用 , 2019 . 55 ( 12 ): 20 - 36 . DOI: 10.3778/j.issn.1002-8331.1903-0031 http://doi.org/10.3778/j.issn.1002-8331.1903-0031 .

Y P ZHENG , G Y LI , Y LI . Survey of application of deep learning in image recognition . Computer Engineering and Applications , 2019 . 55 ( 12 ): 20 - 36 . DOI: 10.3778/j.issn.1002-8331.1903-0031 http://doi.org/10.3778/j.issn.1002-8331.1903-0031 .

张睆. 基于VGG模型视觉假体中图像识别算法的硬件实现[D]. 西安: 西安理工大学, 2020.

ZHANG H. Hardware implementation of image recognition algorithm in visual prosthesis based on VGG model[D]. Xi'an: Xi'an University of Technology, 2020. (in Chinese)

孙志军 , 薛磊 , 许阳明 , 等 . 深度学习研究综述 . 计算机应用研究 , 2012 . 29 ( 8 ): 2806 - 2810 . DOI: 10.3969/j.issn.1001-3695.2012.08.002 http://doi.org/10.3969/j.issn.1001-3695.2012.08.002 .

Z J SUN , L XUE , Y M XU , 等 . Overview of deep learning . Application Research of Computers , 2012 . 29 ( 8 ): 2806 - 2810 . DOI: 10.3969/j.issn.1001-3695.2012.08.002 http://doi.org/10.3969/j.issn.1001-3695.2012.08.002 .

周飞燕 , 金林鹏 , 董军 . 卷积神经网络研究综述 . 计算机学报 , 2017 . 40 ( 6 ): 1229 - 1251 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX201706001.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX201706001.htm .

F Y ZHOU , L P JIN , J DONG . Review of convolution neural network . Chinese Journal of Computers , 2017 . 40 ( 6 ): 1229 - 1251 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX201706001.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX201706001.htm .

GULCEHRE C, MOCZULSKI M, DENIL M, et al . Noisy activation functions[C]// Proceedings of the 33 rd International Conference on Machine Learning . New York, USA: ACM, 2016.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]// Proceedings of the 3 rd International Conference on Learning Representations . 2015.

何凯 , 马红悦 , 冯旭 , 等 . 基于改进VGG-16模型的英文笔迹鉴别方法 . 天津大学学报(自然科学与工程技术版) , 2020 . 53 ( 9 ): 984 - 990 . https://www.cnki.com.cn/Article/CJFDTOTAL-TJDX202009013.htm https://www.cnki.com.cn/Article/CJFDTOTAL-TJDX202009013.htm .

K HE , H Y MA , X FENG , 等 . English handwriting identification method using an improved VGG-16 model . Journal of Tianjin University (Science and Technology) , 2020 . 53 ( 9 ): 984 - 990 . https://www.cnki.com.cn/Article/CJFDTOTAL-TJDX202009013.htm https://www.cnki.com.cn/Article/CJFDTOTAL-TJDX202009013.htm .

BOUREAU Y L, BACH F, LECUN Y, et al . Learning mid-level features for recognition[C]// Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . San Francisco, CA: IEEE, 2010: 2559-2566.

何迎. 双级卷积神经网络高光谱图像分类[D]. 兰州: 兰州大学, 2020.

HE Y. Dual-level convolutional neural network for HSI classification[D]. Lanzhou: Lanzhou University, 2020. (in Chinese)

PRECHELT L. Early stopping-but when?[M]//ORR G B, MÜLLER K R. Neural Networks : Tricks of the Trade . Berlin: IEEE, 1998.

YOO D, KWEON I S. Learning loss for active learning[C]// Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach: IEEE, 2019: 93-102.

曾文佳. 非结构化道路中水渍的检测及其移动机器人导航应用研究[D]. 杭州: 浙江大学, 2015.

ZENG W J. Water detecting and navigation on unstructured road[D]. Hangzhou: Zhejiang University, 2015. (in Chinese)

J CANNY . A computational approach to edge detection . IEEE Transactions on Pattern Analysis and Machine Intelligence , 1986 . PAMI-8 ( 6 ): 679 - 698 . http://pcp.oxfordjournals.org/external-ref?access_num=10.1109/TPAMI.1986.4767851&link_type=DOI http://pcp.oxfordjournals.org/external-ref?access_num=10.1109/TPAMI.1986.4767851&link_type=DOI .

浏览量

230

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据