Robust Angle Invariant GAS Meter Reading

Abstract

In this work we propose a novel method for automatic gas meter reading from real world images. In a wide range of countries all over the world, the existing automatic technology is not adopted, usually the reading is manually done on site, and a picture is taken through a mobile device as a proof of reading. In order to confirm the reading, a tedious work of checking the proof images is commonly done offline by an operator. With this contribution we aim to supply an effective system, able to provide a real support to the validation process reducing the human effort and the time consumed. We exploit both region-based and Maximally Stable Extremal Regions techniques, during the phase involving the localization of the meter area and to detect the meter counter digits in the detection step respectively. The evaluation has been carried out on every step of our approach, as well as on the overall assessment; although the problem is complex, the proposed method leads to good results even when applied to degraded images, it represents an effective solution to the gas meter reading problem and it can be utilized in real applications

Convolutional neural networks for automatic meter reading

“…Such a fact is relevant since gas meters usually have red decimal digits that should be discarded in the reading process. 2,5,11,13 Therefore, we manually labeled, in each image, a bounding box containing only the significant digits for training Fast-YOLO. These annotations are also publicly available to the research community at https://web.inf.ufpr.br/vri/databases/ ufpr-amr/.…”

“…Automatic Meter Reading (AMR) refers to automatically record the consumption of electric energy, gas and water for both monitoring and billing. [1][2][3] Despite the existence of smart readers, 4 they are not widespread in many countries, especially in the underdeveloped ones, and the reading is still performed manually on site by an operator who takes a picture as reading proof. 2,5 Since this operation is prone to errors, another operator needs to check the proof image to confirm the reading.…”

“…2,5 Since this operation is prone to errors, another operator needs to check the proof image to confirm the reading. 2,5 This offline checking is expensive in terms of human effort and time, and has low efficiency. 6 Moreover, due to a large number of images to be evaluated, the inspection is usually done by sampling 7 and errors might go unnoticed.…”

“…Finally, an impressive recognition rate of 97.30% was achieved using Fast-YOLO and CR-NET in a set of images proposed for end-to-end evaluations of AMR systems, called Meter-Integration subset, 5 against 85% and 87% achieved by the baselines. 2,5 In addition, the CR-NET and Multi-Task models are able to achieve outstanding frames per second (FPS) rates in a high-end GPU, being possible to process respectively 185 and 250 FPS.…”

Deployment framework for the Internet of water meters using computer vision on ARM platform

“…Gallo et al [17] propose an automated solution of gas metering with computer vision for a situation wherein some company personnel has to go to residences or industries and read customers' gas usage. In addition to the human meter reading, the personnel takes a picture of the flow-instrument display at the scene, which becomes a checking element to try to mitigate human reading mistakes later on.…”