基于改进U2-Net的指针式仪表读数方法
Reading Method of Pointer Instrument Based on Improved U2-Net
DOI: 10.12677/met.2024.135046, PDF,   
作者: 王 奇, 李 莉, 王 震, 王树云：天津职业技术师范大学电子工程学院，天津
关键词: 指针式仪表；U2-Net；自动读数；仪表识别；Pointer Instrument； U2-Net； Automatic Reading； Instrument Identification
摘要: 当前工业指针式仪表读数过程中存在特殊环境下依赖人工和推理精度低等问题，本文提出一种基于改进U2-Net的指针式仪表读数方法。针对目前仪表识别算法推理精度差和模型参数数量过多的问题，将U2-Net编码阶段的RSU4和RSU5的最深层的两个卷积更换成深度可分离卷积，并在每个RSU的编码阶段后加入了ECA注意力模块，使模型更好地关注指针和刻度区域，提高指针和刻度的识别精度。本文在收集到的数据集上进行评估，通过对比实验表明，相较于SegNet、Deeplabv3+及U2-Net方法，本文改进的模型查准率达到94.58%，针对两种量程25 MPa和1.6 MPa的压力仪表读数引用误差达到1.012%，具有较好的性能表现。
Abstract: At present, there are some problems in the reading process of industrial pointer instruments, such as relying on manual work and low reasoning accuracy. This paper proposes a reading method for pointer instruments based on improved U2-Net. Aiming at the problems of poor reasoning accuracy and too many model parameters in the current instrument identification algorithm, the deepest two convolutions of RSU4 and RSU5 in the U2-Net coding stage are replaced by deep separable convolutions, and the ECA attention module is added after each RSU coding stage, which made the model pay more attention to the pointer and scale area and improved the recognition accuracy of pointer and scale. In this paper, the collected data sets are evaluated. Compared with SegNet, Deeplabv3+ and U2-Net methods, the accuracy of the improved model in this paper reaches 94.58%, and the reference error of pressure instruments with two measuring ranges of 25 MPa and 1.6 MPa reaches 1.012%, which has good performance.
文章引用：王奇, 李莉, 王震, 王树云. 基于改进U2-Net的指针式仪表读数方法[J]. 机械工程与技术, 2024, 13(5): 394-403. https://doi.org/10.12677/met.2024.135046

参考文献

[1] 杨兆昭. 基于深度学习的指针式仪表识别方法研究[D]: [硕士学位论文]. 西安: 西安石油大学, 2023.
[2] 房桦, 蒋涛, 李红玉, 等. 一种适用于智能变电站巡检机器人的双针仪表读数的识别算法[J]. 山东电力技术, 2013(3): 9-13+69.
[3] Gao, J., Xie, H., Zuo, L. and Zhang, C. (2017) A Robust Pointer Meter Reading Recognition Method for Substation Inspection Robot. 2017 International Conference on Robotics and Automation Sciences, Hongkong, 26-29 August 2017, 43-47. [Google Scholar] [CrossRef] 
[4] Kucheruk, V., Kurytnik, I., Kulakov, P., et al. (2018) Definition of Dynamic Characteristics of Pointer Measuring Devices on the Basis of Automatic Indications Determination. Archives of Control Sciences, 28, 401-418.
[5] 万吉林, 王慧芳, 管敏渊, 等. 基于Faster R-CNN和U-Net的变电站指针式仪表读数自动识别方法[J]. 电网技术, 2020, 44(8): 3097-3105.
[6] 金爱萍, 袁亮, 周德勤, 等. 基于YOLOv5和U-Net的指针式仪表读数识别方法[J]. 仪表技术与传感器, 2022(11): 29-33.
[7] Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R. and Jagersand, M. (2020) U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection. Pattern Recognition, 106, Article 107404. [Google Scholar] [CrossRef] 
[8] 舒小锋, 吴晓红, 卿粼波, 等. 基于改进U~2Net的岩石薄片图像分割[J]. 计算机系统应用, 2024, 33(2): 159-165.
[9] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W.M. and Frangi, A.F., Eds., Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Springer, 234-241. [Google Scholar] [CrossRef] 
[10] Howard, A.G., Zhu, M., Chen, B., et al. (2017) Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications.
https://arxiv.org/abs/1704.04861
[11] Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W. and Hu, Q. (2020). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 13-19 June 2020, 11531-11539.[CrossRef] 
[12] Badrinarayanan, V., Kendall, A. and Cipolla, R. (2017) Segnet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 2481-2495. [Google Scholar] [CrossRef] [PubMed]
[13] Chen, L., Zhu, Y., Papandreou, G., Schroff, F. and Adam, H. (2018) Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Computer Vision—ECCV 2018, Springer, 833-851. [Google Scholar] [CrossRef] 

为你推荐