浏览全部资源
扫码关注微信
1.武汉科技大学 信息科学与工程学院, 湖北 武汉 430081
2.武汉科技大学 教育部冶金自动化与检测技术工程研究中心, 湖北 武汉 430081
Received:21 August 2022,
Revised:02 October 2022,
Published:05 July 2023
移动端阅览
GU Yun-di, XU Wang-ming, HE Qin. Design of image-based intelligent meter reading system for wheel meters[J]. Chinese journal of liquid crystals and displays, 2023, 38(7): 985-996.
GU Yun-di, XU Wang-ming, HE Qin. Design of image-based intelligent meter reading system for wheel meters[J]. Chinese journal of liquid crystals and displays, 2023, 38(7): 985-996. DOI: 10.37188/CJLCD.2022-0275.
为了克服人工抄表效率低和现有图像识别方法对双半字符识别不准的问题,设计了基于窄带物联网(NB-IoT)技术和轻量级卷积神经网络(CNN)的字轮式仪表智能图像抄表系统。首先,图像采集终端用NB-IoT模组将摄像头获取的表盘图像上传至云平台;然后,使用局部特征提取与匹配方法估计仿射变换矩阵,将输入的表盘图像转换至模板图像所在坐标空间并分割出各个读数的字符子图像;最后,使用基于多标签分类的轻量级CNN模型识别这些子图像并通过后处理得到最终表盘读数结果。实验结果表明,系统的图像采集终端休眠电流小于10 μA,可确保2节锂亚电池工作5年以上;所提出的基于多标签分类的CNN模型能准确识别单字符和双半字符,达到了96.36%的字符识别准确率和94.15%的读数识别准确率,优于对比的其他识别算法。
To overcome the problems of low efficiency in manual meter reading and inaccurate recognition for double half-characters by existing image recognition methods, an image-based intelligent meter reading system based on narrow band Internet of things (NB-IoT) and lightweight convolutional neural network (CNN) is designed. Firstly, the image acquisition terminal uses NB-IoT module to upload the meter image collected by the camera to cloud platform. Then, the method of local feature extraction and matching is applied to estimate an affine transform matrix and convert the input meter image to the coordinate space of the template image, and every sub-image of reading character is segment out. Finally, a multi-label classification-based lightweight CNN model is proposed to recognize these sub-images, and the final reading result is obtained by post-processing. Experimental results indicate that the sleep current of the image acquisition terminal of the designed system is less than 10 μA,which can ensure two Li/SOCl
2
batteries working for more than 5 years, and that the proposed CNN model based on multi-label classification can accurately recognize both single characters and double half-characters and has achieved a character accuracy rate of 96.36% and a reading accuracy rate of 94.15%, which is superior to other recognition algorithms.
MÓCZÁR G , CSUBÁK T , VÁRADY P . Distributed measurement system for heat metering and control [J]. IEEE Transactions on Instrumentation and Measurement , 2002 , 51 ( 4 ): 691 - 694 . doi: 10.1109/tim.2002.803087 http://dx.doi.org/10.1109/tim.2002.803087
鲍卫兵 , 杜丰 , 周云水 . GPRS在远程抄表终端中应用 [J]. 浙江工业大学学报 , 2006 , 34 ( 4 ): 420 - 424 . doi: 10.3969/j.issn.1006-4303.2006.04.016 http://dx.doi.org/10.3969/j.issn.1006-4303.2006.04.016
BAO W B , DU F , ZHOU Y S . Application of GPRS in remote terminals for automatic meter reading [J]. Journal of Zhejiang University of Technology , 2006 , 34 ( 4 ): 420 - 424 . (in Chinese) . doi: 10.3969/j.issn.1006-4303.2006.04.016 http://dx.doi.org/10.3969/j.issn.1006-4303.2006.04.016
PRASAD P Y , HEERA H , PADMAJA N , et al . A comparative analysis of long range and NB-IoT in terms of quality of connectivity [J]. Materials Today: Proceedings , 2021 , doi: 10.1016/j.matpr.2020.12.350 http://dx.doi.org/10.1016/j.matpr.2020.12.350 .
MUTEBA F , DJOUANI K , OLWAL T . A comparative survey study on LPWA IoT technologies: design, considerations, challenges and solutions [J]. Procedia Computer Science , 2019 , 155 : 636 - 641 . doi: 10.1016/j.procs.2019.08.090 http://dx.doi.org/10.1016/j.procs.2019.08.090
吴正平 , 张兆蒙 , 李东 , 等 . 基于NB-IoT智能水表抄表系统设计与实现 [J]. 传感器与微系统 , 2019 , 38 ( 11 ): 93 - 95 .
WU Z P , ZHANG Z M , LI D , et al . Design and implementation of intelligent water meter reading system based on NB-IoT [J]. Transducer and Microsystem Technologies , 2019 , 38 ( 11 ): 93 - 95 . (in Chinese)
江曼婷 . 基于NB-IoT的燃气抄表系统设计 [D]. 成都 : 电子科技大学 , 2020 . doi: 10.15251/cl.2021.188.449 http://dx.doi.org/10.15251/cl.2021.188.449
JIANG M T . Research on remote reading system of gas meter based on NB-IoT [D]. Chengdu : University of Electronic Science and Technology of China , 2020 . (in Chinese) . doi: 10.15251/cl.2021.188.449 http://dx.doi.org/10.15251/cl.2021.188.449
李升 . 基于NB-loT电表远程抄表系统设计和实现 [D]. 青岛 : 山东科技大学 , 2020 .
LI S . Design and implementation of remote meter reading system based on NB-IoT [D]. Qingdao : Shandong University of Science and Technology , 2020 . (in Chinese)
宋洪儒 , 王宜怀 , 杨凡 . 基于窄带物联网智能燃气表系统设计与实现 [J]. 传感器与微系统 , 2019 , 38 ( 3 ): 113 - 116 .
SONG H R , WANG Y H , YANG F . Design and implementation of intelligent gas meter system based on NBIoT [J]. Transducer and Microsystem Technologies , 2019 , 38 ( 3 ): 113 - 116 . (in Chinese)
孟月波 , 石德旺 , 刘光辉 , 等 . 多维度卷积融合的密集不规则文本检测 [J]. 光学 精密工程 , 2021 , 29 ( 9 ): 2210 - 2221 . doi: 10.37188/OPE.20212909.2210 http://dx.doi.org/10.37188/OPE.20212909.2210
MENG Y B , SHI D W , LIU G H , et al . Dense irregular text detection based on multi-dimensional convolution fusion [J]. Optics and Precision Engineering , 2021 , 29 ( 9 ): 2210 - 2221 . (in Chinese) . doi: 10.37188/OPE.20212909.2210 http://dx.doi.org/10.37188/OPE.20212909.2210
王爱丽 , 薛冬 , 吴海滨 , 等 . 基于条件生成对抗网络的手写数字识别 [J]. 液晶与显示 , 2020 , 35 ( 12 ): 1284 - 1290 . doi: 10.37188/YJYXS20203512.1284 http://dx.doi.org/10.37188/YJYXS20203512.1284
WANG A L , XUE D , WU H B , et al . Handwritten digit recognition based on conditional generative adversarial network [J]. Chinese Journal of Liquid Crystals and Displays , 2020 , 35 ( 12 ): 1284 - 1290 . (in Chinese) . doi: 10.37188/YJYXS20203512.1284 http://dx.doi.org/10.37188/YJYXS20203512.1284
徐平 , 许彬 , 常英杰 . 双半字识别算法在水表字符识别系统中的应用 [J]. 杭州电子科技大学学报(自然科学版) , 2016 , 36 ( 1 ): 80 - 85 .
XU P , XU B , CHANG Y J . Application of improved double half-word recognition method in water character recognition system [J]. Journal of Hangzhou Dianzi University (Natural Sciences) , 2016 , 36 ( 1 ): 80 - 85 . (in Chinese)
高菊 , 叶桦 . 一种有效的水表数字图像二次识别算法 [J]. 东南大学学报(自然科学版) , 2013 , 43 ( S1 ): 153 - 157 . doi: 10.3969/j.issn.1001-0505.2013.S1.032 http://dx.doi.org/10.3969/j.issn.1001-0505.2013.S1.032
GAO J , YE H . An effective two-times recognition algorithm of meter digital image [J]. Journal of Southeast University (Natural Science Edition) , 2013 , 43 ( S1 ): 153 - 157 . (in Chinese) . doi: 10.3969/j.issn.1001-0505.2013.S1.032 http://dx.doi.org/10.3969/j.issn.1001-0505.2013.S1.032
张艰 , 赵宇明 , 陈德权 . 分时电表表盘数字读数的自动识别系统 [J]. 计算机工程 , 2005 , 31 ( 5 ): 178 - 180 . doi: 10.3969/j.issn.1000-3428.2005.05.062 http://dx.doi.org/10.3969/j.issn.1000-3428.2005.05.062
ZHANG J , ZHAO Y M , CHEN D Q . Automatic recognition system for numeric characters on time-sharing ammeter dial plate [J]. Computer Engineering , 2005 , 31 ( 5 ): 178 - 180 . (in Chinese) . doi: 10.3969/j.issn.1000-3428.2005.05.062 http://dx.doi.org/10.3969/j.issn.1000-3428.2005.05.062
金静晓 , 信昆仑 . 改进的半字识别算法在水表读数系统中的应用 [J]. 供水技术 , 2015 , 9 ( 1 ): 43 - 45 . doi: 10.3969/j.issn.1673-9353.2015.01.010 http://dx.doi.org/10.3969/j.issn.1673-9353.2015.01.010
JIN J X , XIN K L . Application of improved half-word recognition method in automatic meter reading system [J]. Water Technology , 2015 , 9 ( 1 ): 43 - 45 . (in Chinese) . doi: 10.3969/j.issn.1673-9353.2015.01.010 http://dx.doi.org/10.3969/j.issn.1673-9353.2015.01.010
王志威 , 郑恭明 . 改进残差网络的字轮式数字表盘识别算法 [J]. 科学技术与工程 , 2022 , 22 ( 6 ): 2357 - 2362 . doi: 10.3969/j.issn.1671-1815.2022.06.027 http://dx.doi.org/10.3969/j.issn.1671-1815.2022.06.027
WANG Z W , ZHENG G M . Improved residual network recognition algorithm for digital dial [J]. Science Technology and Engineering , 2022 , 22 ( 6 ): 2357 - 2362 . (in Chinese) . doi: 10.3969/j.issn.1671-1815.2022.06.027 http://dx.doi.org/10.3969/j.issn.1671-1815.2022.06.027
HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas : IEEE , 2016 : 770 - 778 . doi: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90
王望 , 徐望明 , 伍世虔 , 等 . 基于卷积神经网络的字轮式仪表双半字符识别 [J]. 武汉科技大学学报 , 2021 , 44 ( 1 ): 68 - 73 .
WANG W , XU W M , WU S Q , et al . Double half-character recognition for wheel-type meter based on convolutional neural network [J]. Journal of Wuhan University of Science and Technology , 2021 , 44 ( 1 ): 68 - 73 . (in Chinese)
YANG F , JIN L W , LAI S X , et al . Fully convolutional sequence recognition network for water meter number reading [J]. IEEE Access , 2019 , 7 : 11679 - 11687 . doi: 10.1109/access.2019.2891767 http://dx.doi.org/10.1109/access.2019.2891767
SHI B G , BAI X , YAO C . An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 ( 11 ): 2298 - 2304 . doi: 10.1109/tpami.2016.2646371 http://dx.doi.org/10.1109/tpami.2016.2646371
马学文 . 基于图像识别的指针式工业仪表远程抄录技术研究 [D]. 西安 : 西安电子科技大学 , 2021 .
MA X W . Research on remote transcription technology of pointer type industrial instrument based on image recognition [D]. Xi'an : Xidian University , 2021 . (in Chinese)
江亚杰 . 基于深度学习的电力仪表视觉校对系统 [D]. 武汉 : 湖北工业大学 , 2020 .
JIANG Y J . Power meter visual proofreading system based on deep learning [D]. Wuhan : Hubei University of Technology , 2020 . (in Chinese)
王杜毅 , 常相茂 . MeterEye:基于NB-IoT和图像处理的普适远程抄表系统 [J]. 小型微型计算机系统 , 2021 , 42 ( 9 ): 1950 - 1954 . doi: 10.3969/j.issn.1000-1220.2021.09.025 http://dx.doi.org/10.3969/j.issn.1000-1220.2021.09.025
WANG D Y , CHANG X M . MeterEye: a general remote meter reading system based on NB-IoT and image processing [J]. Journal of Chinese Computer Systems , 2021 , 42 ( 9 ): 1950 - 1954 . (in Chinese) . doi: 10.3969/j.issn.1000-1220.2021.09.025 http://dx.doi.org/10.3969/j.issn.1000-1220.2021.09.025
CRUZ-MOTA J , BOGDANOVA I , PAQUIER B , et al . Scale invariant feature transform on the sphere: theory and applications [J]. International Journal of Computer Vision , 2012 , 98 ( 2 ): 217 - 241 . doi: 10.1007/s11263-011-0505-4 http://dx.doi.org/10.1007/s11263-011-0505-4
BAY H , TUYTELAARS T , VAN GOOL L . SURF: speeded up robust features [C]// Proceedings of the 9th European Conference on Computer Vision . Graz : Springer , 2006 : 404 - 417 . doi: 10.1007/11744023_32 http://dx.doi.org/10.1007/11744023_32
余永维 , 韩鑫 , 杜柳青 . 基于Inception-SSD算法的零件识别 [J]. 光学 精密工程 , 2020 , 28 ( 8 ): 1799 - 1809 .
YU Y W , HAN X , DU L Q . Target part recognition based Inception-SSD algorithm [J]. Optics and Precision Engineering , 2020 , 28 ( 8 ): 1799 - 1809 . (in Chinese)
邸亮 , 涂俊翔 , 禹杰 . 基于Lenet-5网络组合特征融合的水表数字识别 [J]. 机械制造与自动化 , 2020 , 49 ( 6 ): 189 - 192 .
DI L , TU J X , YU J . Digital recognition of water meter based on combined features fusion of Lenet-5 network [J]. Machine Building & Automation , 2020 , 49 ( 6 ): 189 - 192 . (in Chinese)
SELVARAJU R R , COGSWELL M , DAS A , et al . Grad-CAM: visual explanations from deep networks via gradient-based localization [C]. 2017 IEEE International Conference on Computer Vision . Venice : IEEE , 2017 : 618 - 626 . doi: 10.1109/iccv.2017.74 http://dx.doi.org/10.1109/iccv.2017.74
ZUO C , QIAN J M , FENG S J , et al . Deep learning in optical metrology: a review [J]. Light: Science & Applications , 2022 , 11 ( 1 ): 39 . doi: 10.1038/s41377-022-00714-x http://dx.doi.org/10.1038/s41377-022-00714-x
0
Views
85
下载量
1
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution