隨著物聯網技術的蓬勃發展，政府逐漸淘汰了傳統電錶，開始了智能電錶的時代。然而，更換智能電錶的價格昂貴且面臨通訊不良等問題，導致智能電錶佈建緩慢，我們的想法是開發一種低成本的解決方案，該解決方案使用帶有攝影鏡頭的邊緣設備自動辨識傳統電錶，然後將辨識的值上傳到雲端。過去已有研究通過傳統的圖像分割方法自動讀取錶盤，但是由於傳統的電錶大多設置在遮蔽性高、光線昏暗、灰塵多的環境中，因此對於不清晰的電錶圖像，傳統方法難以獲得良好的辨識結果。在本文中，我們提出了一種基於輕量化卷積神經網路的自動讀錶器並實現在邊緣設備上，為了減輕佈建難度和提高錶盤辨識的準確率，我們所提出的錶盤讀取器具有自動調整傾斜錶盤圖像的能力。實驗結果顯示，相較於其他相關方法，所提出的輕量化卷積神經網路在分割錯誤，誤報和運行時間方面取得了顯著改善。

With the vigorous development of the Internet of Things technology, the government has gradually phased out the traditional meter and began the era of smart meters. However, the replacement of smart meters is expensive and the yield is too low, which has led to the slow deployment of smart meters. Our idea is to develop a low-cost alternative solution that uses an edge device with a camera to automatically identify traditional electric dial meters, and then uploads the identified value to cloud servers. In the past, there have been studies to automatically read dial meters through traditional image segmentation methods. However, because traditional electric meters are mostly set in an environment with high concealment, dim light, and dirt, it is difficult for traditional methods to obtain good identification results for unclear meter images. In this thesis, we propose a cost-effective automatic dial meter reader with a lightweight convolutional neural network on edge devices. In order to easily deploy and improve the accuracy of dial meter recognition, the proposed meter reader has the ability to automatically adjust tilt meter images. Experimental results show that the proposed lightweight convolutional neural network achieves significant improvements in segmentation errors, false positives, and elapsed time compared with the relative approaches.

[1] D. Shu, S. Ma, and C. Jing, "Study of the Automatic Reading of Watt Meter Based on Image Processing Technology," 2007 2nd IEEE Conference on Industrial Electronics and Applications, Harbin, China, pp. 2214-2217, 2007.

[2] J. Han, E. Li, B. Tao, and M. Lv, "Reading recognition method of analog measuring instruments based on improved hough transform," IEEE 2011 10th International Conference on Electronic Measurement & Instruments, Chengdu, China, pp. 337-340, 2011.

[3] J. Chi, L. Liu, J. Liu, Z. Jiang, and G. Zhang, "Machine Vision Based Automatic Detection Method of Indicating Values of a Pointer Gauge," Mathematical Problems in Engineering, vol. 2015, pp. 19, 2015.

[4] K. Cheng, Y. Zhang, H. Zhang, and J. Huang, "Research on Image Processing Technology Based on Analog Head Reading," 2019 Chinese Control And Decision Conference (CCDC), Nanchang, China, pp. 2265-2269, 2019.

[5] H. Lai, Q. Kang, L. Pan, and C. Cui, "A Novel Scale Recognition Method for Pointer Meters Adapted to Different Types and Shapes," 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), Vancouver, BC, Canada, pp. 374-379, 2019.

[6] R. Ocampo-Vega, G. Sanchez-Ante, L. E. Falcón-Morales, and H. Sossa, "Image Processing for Automatic Reading of Electro-Mechanical Utility Meters," 2013 12th Mexican International Conference on Artificial Intelligence, Mexico City, pp. 164-170, 2013.

[7] M. Souare, F. Merat, and C. Papachristou, "Efficient way of reading rotary dial utility meter using image processing," ASEE 2014 Zone I Conference, Bridgpeort, CT, USA, April 3-5, 2014.

[8] Z. Yang, W. Niu, X. Peng, Y. Gao, Y. Qiao, and Y. Dai, "An image-based intelligent system for pointer instrument reading," 2014 4th IEEE International Conference on Information Science and Technology, Shenzhen, China, pp. 780-783, 2014.

[9] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Advances in neural information processing systems, pp. 1097-1105, 2012.

[10] Y. Tang, C. Ten, C. Wang, and G. Parker, "Extraction of Energy Information From Analog Meters Using Image Processing," in IEEE Transactions on Smart Grid, vol. 6, no. 4, pp. 2032-2040, July 2015.

[11] R. O. Duda and P. E. Hart, "Use of the Hough transformation to detect lines and curves in picture," Commun. ACM, vol. 15, pp. 11-15, 1972.

[12] C. Zheng, S. Wang, Y. Zhang, P. Zhang, and Y. Zhao, "A robust and automatic recognition system of analog instruments in power system by using computer vision," Measurement, vol. 92, pp. 413-420, 2016.

[13] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," In ICLR, 2015.

[14] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," arXiv preprint arXiv:1512.03385, 2015. 2, 5, 6.

[15] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-Based Learning Applied to Document Recognition," Proc. IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.

[16] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going deeper with convolutions," CoRR, abs/1409.4842, 2014.

[17] G. Huang, Z. Liu, K. Q. Weinberger, and L. Maaten, "Densely connected convolutional networks," In CVPR, 2017.

[18] F. Chollet, "Xception: Deep learning with depthwise separable convolutions," In CVPR, 2017.

[19] S. M. Desa and Q. A. Salih, "Image subtraction for real time moving object extraction," Proceedings. International Conference on Computer Graphics, Imaging and Visualization(CGIV), Penang, Malaysia, pp. 41-45, 2004.

[20] H. Feng and J. Zhao, "Application Research of Computer Vision in the Auto-Calibration of Dial Gauges," 2008 International Conference on Computer Science and Software Engineering, Hubei, pp. 845-848, 2008.

[21] J. Lee, S. Lim, J. Kim, B. Kim and D. Lee, "Moving object detection using background subtraction and motion depth detection in depth image sequences," The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014), JeJu Island, pp. 1-2, 2014.

[22] O. E. Harrouss, D. Moujahid and H. Tairi, "Motion detection based on the combining of the background subtraction and spatial color information," 2015 Intelligent Systems and Computer Vision (ISCV), Fez, pp. 1-4, 2015.

[23] A. S. Mohan and R. Resmi, "Video image processing for moving object detection and segmentation using background subtraction," 2014 First International Conference on Computational Systems and Communications (ICCSC), Trivandrum, pp. 288-292, 2014.

[24] E. Komagal, A. Vinodhini, Archana and Bricilla, "Real time Background Subtraction techniques for detection of moving objects in video surveillance system," 2012 International Conference on Computing, Communication and Applications, Dindigul, Tamilnadu, pp. 1-5, 2012.

[25] P. Gujrathi, R. A. Priya and P. Malathi, "Detecting Moving Object Using Background Subtraction Algorithm in FPGA," 2014 Fourth International Conference on Advances in Computing and Communications, Cochin, pp. 117-120, 2014.

[26] L. Cao and Y. Jiang, "An Effective Background Reconstruction Method for Video Objects Detection," 2012 Third International Conference on Networking and Distributed Computing, Hangzhou, pp. 161-165, 2012.

[27] X. Mai, W. Li, Y. Huang and Y. Yang, "An Automatic Meter Reading Method Based on One-dimensional Measuring Curve Mapping," 2018 IEEE International Conference of Intelligent Robotic and Control Engineering (IRCE), Lanzhou, pp. 69-73, 2018.

[28] D. G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91-110, 2004.

[29] E. Rublee, V. Rabaud, K. Konolige, G. Bradski, "ORB: An efficient alternative to SIFT or SURF", Proc. IEEE Int. Conf. Comput. Vis., pp. 2564-2571, 2011.

[30] E. Rosten, T. Drummond, "Fusing Points and Lines for High Performance Tracking", Proc. 10th IEEE Int'l Conf. Computer Vision, vol. 2, pp. 1508-1515, 2005.

[31] E. Rosten, T. Drummond, "Machine learning for high-speed corner detection", Proc. 9th European Conference on Computer Vision (ECCV'06), May 2006.

[32] A. Neubeck, L. Van Gool, "Efficient Non-Maximum Suppression", Proc. 18th Int'l Conf. Pattern Recognition, 2006.

[33] M. Calonder, V. Lepetit, C. Strecha, and P. Fua. Brief: Binary robust independent elementary features. In In European Conference on Computer Vision, 2010. 1, 2, 3, 5