An Automatic Detection and Recognition Method for Pointer-type Meters in Natural Gas Stations

Huang, Yan; Dai, Xu-Yang; Meng, Qing-Hao

doi:10.23919/chicc.2019.8866386

Cited by 4 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of them focus on the recognition of cyclometers and digital meters using Optical Character Recognition (OCR) methods. Recently, deep learning approaches have received great attention in this context [4], [10], [12], [17]- [19]. Dial meter recognition research, on the other hand, is more scarce.…”

Section: Related Workmentioning

confidence: 99%

“…Region-based Fully Convolutional Networks (R-FCNs) were used for meter detection [12]. Although the authors used deep learning for detection, the meter reading was performed with handcrafted methods such as binarization, line detection, and skeleton extraction.…”

Section: B Dial Meter Readingmentioning

confidence: 99%

“…Most of the dial meter recognition literature is focused on industrial applications, e.g., pressure meters [10]- [12], voltmeter [13] and ammeter [14]. As the meters are generally fixed and indoors, the image quality is strictly controlled.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning for Image-based Automatic Dial Meter Reading: Dataset and Baselines

Salomon,

Laroca,

Menotti

2020

Preprint

View full text Add to dashboard Cite

Smart meters enable remote and automatic electricity, water and gas consumption reading and are being widely deployed in developed countries. Nonetheless, there is still a huge number of non-smart meters in operation. Image-based Automatic Meter Reading (AMR) focuses on dealing with this type of meter readings. We estimate that the Energy Company of Paraná (Copel), in Brazil, performs more than 850,000 readings of dial meters per month. Those meters are the focus of this work. Our main contributions are: (i) a public real-world dial meter dataset (shared upon request) called UFPR-ADMR; (ii) a deep learning-based recognition baseline on the proposed dataset; and (iii) a detailed error analysis of the main issues present in AMR for dial meters. To the best of our knowledge, this is the first work to introduce deep learning approaches to multidial meter reading, and perform experiments on unconstrained images. We achieved a 100.0% F1-score on the dial detection stage with both Faster R-CNN and YOLO, while the recognition rates reached 93.6% for dials and 75.25% for meters using Faster R-CNN (ResNext-101).

show abstract