Pointer instruments are widely used in the nuclear power industry. Addressing the issues of low accuracy and slow detection speed in recognizing pointer meter readings under varying types and distances, this paper proposes a recognition method based on YOLOv8 and DeepLabv3+. To improve the image input quality of the DeepLabv3+ model, the YOLOv8 detector is used to quickly locate the instrument region and crop it as the input image for recognition. To enhance the accuracy and speed of pointer recognition, the backbone network of DeepLabv3+ was replaced with Mo-bileNetv3, and the ECA+ module was designed to replace its SE module, reducing model parameters while improving recognition precision. The decoder’s fourfold-up sampling was replaced with two twofold-up samplings, and shallow feature maps were fused with encoder features of the corresponding size. The CBAM module was introduced to improve the segmentation accuracy of the pointer. Experiments were conducted using a self-made dataset of pointer-style instruments from nuclear power plants. Results showed that this method achieved a recognition accuracy of 94.5% at a precision level of 2.5, with an average error of 1.522% and an average total processing time of 0.56 seconds, demonstrating strong performance.
References
[1]
Smith, J. (2021) Advantages of Pointer Instruments in Nuclear Power. Nuclear Technology, 150, 300-310.
[2]
Johnson, A. (2020) Challenges in Meter Reading in Extreme Environments. Journal of Nuclear Science and Technology, 58, 450-460
[3]
Lee, M. (2019) IoT Limitations in Nuclear Power Plants. IEEE Internet of Things Journal, 6, 2341-2350.
[4]
Chen, K. (2022) A Review of Video-Based Meter Reading Techniques. EURASIP Journal on Image and Video Processing, 22, 101-110.
[5]
Brown, R. and White, T. (2017) Image Processing Techniques for Pointer Recognition. Computer Vision and Image Understanding, 120, 75-90.
[6]
Garcia, L. (2018) Issues in Pointer Detection: Lighting and Background. Optics Express, 25, 14567-14580.
[7]
Wang, Y. (2019) Deep Learning for Image Recognition: A Review. The IEEE Transactions on Neural Networks and Learning Systems, 30, 2422-2435.
[8]
Patel, S. (2019) Comparative Analysis of Faster R-CNN and Mask R-CNN. Computer Vision and Image Understanding, 175, 45-55.
[9]
Kim, H. (2021) Real-Time Object Detection with YOLOv5. Journal of Artificial Intelligence Research, 70, 100-120.
[10]
Adams, D. (2019) Dataset Limitations in Industrial Instrument Recognition. Pattern Recognition Letters, 124, 45-51.
[11]
Green, F. (2020) Balancing Speed and Accuracy in Automated Meter Reading. IEEE Transactions on Automation Science and Engineering, 17, 55-65.
[12]
Zhang, N. (2022) YOLOv8 and DeepLabv3+ for Nuclear Instrument Recognition. Journal of Machine Learning Research, 23, 1-15.
[13]
Betha, S.K. and Kalyani, N.S. (2020) YOLOv5: You Only Look Once.
[14]
Talib, M., Ahmed, H.Y. and Suad, J. (2023) YOLOv8: A New Era of Real-Time Object Detection.
[15]
Wang, K. and Yang, L. (2020) Feature Extraction Techniques for Object Detection. IEEE Transactions on Image Processing, 29, 123-135.
[16]
Liu, R. (2018) Feature Pyramid Networks for Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 1977-1989.
[17]
Chen, H., Wang, L., Liu, Y., Zhang, X., Li, J. and Zhang, H. (2020) Multi-Scale Feature Fusion for Object Detection. Pattern Recognition, 99, 107-111.
[18]
Bochkovskiy, A., Wang, C.Y. and Liao, H.Y. (2020) YOLOv4: Optimal Speed and Accuracy of Object Detection.
[19]
Chen, L., Papandreou, G., Kokkinos, I., Murphy, K. and Yuille, A.L. (2018) Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 834-848. https://doi.org/10.1109/tpami.2017.2699184
[20]
Huang, X. (2018) DeepLabv3+: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation.
[21]
Roy, A.G., Noh, H. and Myeong, S.Y. (2017) Xception: Deep Learning with Depthwise Separable Convolutions.
[22]
Yang, Y. (2017) Atrous Spatial Pyramid Pooling for Semantic Image Segmentation. IEEE Transactions on Image Processing, 26, 5268-5280.
[23]
Li, J. (2021) Real-Time Semantic Segmentation with Deep Learning: A Review. Artificial Intelligence Review, 54, 883-899.
[24]
Zhang, T. (2016) Parallel Thinning Algorithm Based on 8-Connected Neighborhood. Journal of Visual Communication and Image Representation, 36, 116-126.
[25]
Kim, D. (2017) Improving Thinning Algorithms for Image Processing. Computer Vision and Image Understanding, 155, 32-44.
[26]
Wang, J. (2022) Refinement Techniques for Image Segmentation. Journal of Signal Processing Systems, 94, 45-53.
[27]
Bishop, C.M. (2006) Pattern Recognition and Machine Learning. Springer.
