Image-based Automatic Dial Meter Reading in Unconstrained Scenarios

被引：17
作者：
Salomon G. [1 ]
Laroca R. [1 ]
Menotti D. [1 ]
机构：
[1] Department of Informatics, Federal University of Paraná (UFPR), PR, Curitiba
来源：
Measurement: Journal of the International Measurement Confederation | 2022年 / 204卷
关键词：
Automatic Meter Reading; Deep learning; Dial meters; Pointer-type meters; Public dataset;
D O I：
10.1016/j.measurement.2022.112025
中图分类号：
学科分类号：
摘要：
The replacement of analog meters with smart meters is costly, laborious, and far from complete in developing countries. The Energy Company of Paraná (Copel) (Brazil) performs more than 4 million meter readings (almost entirely of non-smart devices) per month, and we estimate that 850 thousand of them are from dial meters. Therefore, an image-based automatic reading system can reduce human errors, create a proof of reading, and enable the customers to perform the reading themselves through a mobile application. We propose novel approaches for Automatic Dial Meter Reading (ADMR) and introduce a new dataset for ADMR in unconstrained scenarios, called UFPR-ADMR-v2. Our best-performing method combines YOLOv4 with a novel regression approach (AngReg), and explores several post-processing techniques. Compared to previous works, it decreased the Mean Absolute Error (MAE) from 1343 to 129 and achieved a meter recognition rate (MRR) of 98.9% — with an error tolerance of 1 Kilowatt-hour (kWh). © 2022 Elsevier Ltd
引用
收藏
相关论文
共 57 条
[21]  
ANEEL - Agencia Nacional de Energia Eletrica R.C., Perdas de energia elétrica na distribuição, (2019)
[22]  
Bochkovskiy A., Wang C.-Y., Liao H.-Y.M., YOLOv4: Optimal speed and accuracy of object detection, pp. 1-14, (2020)
[23]  
Tang Y., Ten C., Wang C., Parker G., Extraction of energy information from analog meters using image processing, IEEE Trans. Smart Grid, 6, 4, pp. 2032-2040, (2015)
[24]  
Laroca R., Barroso V., Diniz M.A., Goncalves G.R., Schwartz W.R., Menotti D., Convolutional neural networks for automatic meter reading, J. Electron. Imaging, 28, 1, (2019)
[25]  
Tsai C., Shou T.D., Chen S., Hsieh J., Use SSD to detect the digital region in electricity meter, International Conference on Machine Learning and Cybernetics, ICMLC, pp. 1-7, (2019)
[26]  
Yang F., Jin L., Lai S., Gao X., Li Z., Fully convolutional sequence recognition network for water meter number reading, IEEE Access, 7, pp. 11679-11687, (2019)
[27]  
Hou L., Qu H., Automatic recognition system of pointer meters based on lightweight CNN and WSNs with on-sensor image processing, Measurement, 183, (2021)
[28]  
Zheng C., Wang S., Zhang Y., Zhang P., Zhao Y., A robust and automatic recognition system of analog instruments in power system by using computer vision, Measurement, 92, pp. 413-420, (2016)
[29]  
Luz E., Et al., Deep periocular representation aiming video surveillance, Pattern Recognit. Lett., 114, pp. 2-12, (2020)
[30]  
Zuo L., He P., Zhang C., Zhang Z., A robust approach to reading recognition of pointer meters based on improved mask-RCNN, Neurocomputing, 388, pp. 90-101, (2020)
123456