Image-based Automatic Dial Meter Reading in Unconstrained Scenarios

Salomon, Gabriel; Laroca, Rayson; Menotti, David

doi:10.1016/j.measurement.2022.112025

Cited by 14 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) UFPR-ADMR Dataset [25,26]. This dataset consists of two versions, UFPR-ADMR-v1 and UFPR-ADMR-v2.…”

Section: Introduction To Available Evaluation Datasetsmentioning

confidence: 99%

A comprehensive research on measurement and evaluation of intelligent meter reading systems

Zhang,

Bai,

Zhang

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

Based on the machine vision and artificial intelligence technologies, the reading and acquisition of meter values have become the mainstream technical solutions for real-time monitoring of production data in the current industrial field. At the same time, the number of intelligent instruments and meters is increasing, and the quality varies. There is a lack of scientifically measurement methods and quality trust for intelligent meter reading algorithms. To promote their reliable and widespread application in various fields, it is necessary to conduct in-depth research on the assessment system of artificial intelligence in intelligent meter reading systems. This paper comprehensively studies various aspects involved in the emerging measurement field of artificial intelligence evaluation at the current stage, providing scientific measurement and evaluation references for the quality trust of artificial intelligence in the field of meters.

show abstract

“…(1) UFPR-ADMR Dataset [25,26]. This dataset consists of two versions, UFPR-ADMR-v1 and UFPR-ADMR-v2.…”

Section: Introduction To Available Evaluation Datasetsmentioning

confidence: 99%

A comprehensive research on measurement and evaluation of intelligent meter reading systems

Zhang,

Bai,

Zhang

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…The image processing such as tilt correction, binarization processing, scale line extraction, and straight line extraction of the pointer meter image after localization is performed to calculate more accurate pointer readings. Salomon et al [11] introduced a new data set in unconstrained scenarios, which improves the meter recognition rate combining YOLOv4 with a novel regression method (AngReg). Literature [2] developed an automatic pointer meter recognition system based on line scan vision.…”

Section: Introductionmentioning

confidence: 99%

“…In previous work on automatic pointer meter reading such as [2,[6][7][8][9][10][11] only addressed meter detection, pointer extraction and automatic reading content, and did not consider the problem of pointer meter reading in low illumination situations. And in the work of image enhancement such as [12][13][14][15][16][17][18][19] are targeted for natural images with low illumination, not combined with pointer meter reading, and most of the image enhancement networks are complex and time consuming affecting the reading efficiency.…”

Section: Introductionmentioning

confidence: 99%

An optimized design of the pointer meter image enhancement and automatic reading system in low illumination environment

Ge¹,

Yu²,

Hu³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

As meter data becomes more and more important in the power industry, detection robots are led into substations for automatic collection of the pointer meters. However, the meter images captured in low illumination environments are unclear, resulting in poor recognition of the meter reading. A low-illumination image enhancement method based on virtual exposure is proposed in this paper, improving the dark and bright areas of low-illumination images, respectively. Then the image fusion was performed based on the Laplace pyramid to obtain clear meter images. In addition, the dial area was extracted using the Hough circle transform, and the pointer’s rotation center was fitted using the least squares approach. Finally, the straight line of the pointer was extracted, and the data reading was based on the line segment detector algorithm. Case studies show the above method has good robustness in low illumination environment, with high rate, and accuracy during the image enhancement and automatic reading of the pointer meter.

show abstract

“…The accuracy and anti-jamming ability of the system could meet application requirements, and the average basic error is 0.48%. Salomon et al [26] proposed novel approaches for automatic dial meter reading, introduced new data set in unconstrained scenarios, combined YOLOv4 with a novel regression approach, and explored several postprocessing techniques. Compared with previous works, the mean absolute error was reduced from 1343 to 129, and a meter recognition rate of 98.9% was achieved with an error tolerance of 1 kWh.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method for Recognizing Readings in Images of Electric Circuit Inspection Meters Based on Deep Learning

Xia¹,

Zhang²,

Zheng³

et al. 2023

View full text Add to dashboard Cite

For electric circuit inspection, the conventional manual inspection method has a series of problems including the heavy work load of recording the readings, the low accuracy, and the hidden safety hazards. The intelligent recognization method for images of meter readings based on digital image technology has a great practical value. However, the existing recognization methods for meter readings based on deep learning generally ignore the extraction of key points such as the pointer and scale on meter dashboard, the existing algorithms are of poor robustness and anti-jamming ability, therefore, this paper aims to study a novel method for recognizing readings in the images of electric circuit inspection meters based on deep learning. At first, this paper corrects the tilt of meter dashboard, and accurately positions the dashboard center. Then, based on the YOLOv5 network model, this paper constructs the said recognization model, gives the structure of the YOLOv5 network model, and introduces its working principle. At last, experimental results are drawn to verify the validity of the proposed method for processing the images of meter readings and the constructed recognization model.

show abstract

Image-based Automatic Dial Meter Reading in Unconstrained Scenarios

Cited by 14 publications

References 29 publications

A comprehensive research on measurement and evaluation of intelligent meter reading systems

A comprehensive research on measurement and evaluation of intelligent meter reading systems

An optimized design of the pointer meter image enhancement and automatic reading system in low illumination environment

A Novel Method for Recognizing Readings in Images of Electric Circuit Inspection Meters Based on Deep Learning

Contact Info

Product

Resources

About