Real Time Power Equipment Meter Recognition based on Deep Learning

• Published in: IEEE transactions on instrumentation and measurement Vol. 71; p. 1
• Main Authors: Fan, Zizhu, Shi, Linrui, Xi, Chao, Wang, Hui, Wang, Song, Wu, Gaochang
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Automatic meter reading; Automation; Computer vision; Convolutional neural networks; Datasets; Deep learning; Edge computing; Feature extraction; Lightweight; Machine learning; meter recognition; Meters; Object detection; Power equipment meter; real-time detection; Real-time systems; Recognition; Substations; Yolov5
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2022.3191709

Reading power equipment meters often requires loads of manpower, which is a trivial, repetitive and error-prone task. While conventional automated recognition methods using Computer Vision (CV) techniques are inflexible under diverse scenarios. In this paper we propose a lightweight meter recognition method that combines deep learning and traditional CV techniques for automated meter reading. For meter detection, an adaptive anchor and Global Context (GC) module are deployed to improve the feature extraction ability of lightweight backbone without increasing computational cost. Then a FPN and a PANet are developed to realize the information interaction between different feature layers and achieve multiscale prediction. Our method also includes a multi-task segmented network to read the detected meters, accelerating the detection speed. Experiments demonstrate that our proposed method can achieve a detection speed of 123 FPS in GeForce GTX 1080 and can obtain an accuracy of 88.2% mAP50:95. In the case of insufficient training samples, the method can still achieve an accuracy of 80.9% mAP50:95. In addition, we build a Power Meter Images (PMI) dataset which contains 1800 images in real scene. The dataset and method we proposed can help with further upgrades of traditional substations. In the future, we also hope to extend the algorithm to edge computing cameras for substations. The newly developed dataset and code are available at https://github.com/zzfan3/electric_meter_detect_recognize.