A Highly Efficient Neural Network Solution for Automated Detection of Pointer Meters with Different Analog Scales Operating in Different Conditions
We investigate a neural network–based solution for the Automatic Meter Reading detection problem, applied to analog dial gauges. We employ a convolutional neural network with a non-linear Network in Network kernel. Presently, there is a significant interest in systems for automatic detection of anal...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/8/7/1104 |
| _version_ | 1797563237268455424 |
|---|---|
| author | Alexey Alexeev Georgy Kukharev Yuri Matveev Anton Matveev |
| author_facet | Alexey Alexeev Georgy Kukharev Yuri Matveev Anton Matveev |
| author_sort | Alexey Alexeev |
| collection | DOAJ |
| description | We investigate a neural network–based solution for the Automatic Meter Reading detection problem, applied to analog dial gauges. We employ a convolutional neural network with a non-linear Network in Network kernel. Presently, there is a significant interest in systems for automatic detection of analog dial gauges, particularly in the energy and household sectors, but the problem is not yet sufficiently addressed in research. Our method is a universal three-level model that takes an image as an input and outputs circular bounding areas, object classes, grids of reference points for all symbols on the front panel of the device and positions of display pointers. Since all analog pointer meters have a common nature, this multi-cascade model can serve various types of devices if its capacity is sufficient. The model is using global regression for locations of symbols, which provides resilient results even for low image quality and overlapping symbols. In this work, we do not focus on the pointer location detection since it heavily depends on the shape of the pointer. We prepare training data and benchmark the algorithm with our own framework a3net, not relying on third-party neural network solutions. The experimental results demonstrate the versatility of the proposed methods, high accuracy, and resilience of reference points detection. |
| first_indexed | 2024-03-10T18:40:41Z |
| format | Article |
| id | doaj.art-8d836338274b4cc496a7ecf9b164c17b |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T18:40:41Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-8d836338274b4cc496a7ecf9b164c17b2023-11-20T05:54:36ZengMDPI AGMathematics2227-73902020-07-0187110410.3390/math8071104A Highly Efficient Neural Network Solution for Automated Detection of Pointer Meters with Different Analog Scales Operating in Different ConditionsAlexey Alexeev0Georgy Kukharev1Yuri Matveev2Anton Matveev3Huawei Research Center, 197022 Saint Petersburg, RussiaDepartment of Software Engineering and Computer Applications, Saint Petersburg Electrotechnical University “LETI”, 197022 Saint Petersburg, RussiaInformation Technologies and Programming Faculty, ITMO University, 197101 Saint Petersburg, RussiaInformation Technologies and Programming Faculty, ITMO University, 197101 Saint Petersburg, RussiaWe investigate a neural network–based solution for the Automatic Meter Reading detection problem, applied to analog dial gauges. We employ a convolutional neural network with a non-linear Network in Network kernel. Presently, there is a significant interest in systems for automatic detection of analog dial gauges, particularly in the energy and household sectors, but the problem is not yet sufficiently addressed in research. Our method is a universal three-level model that takes an image as an input and outputs circular bounding areas, object classes, grids of reference points for all symbols on the front panel of the device and positions of display pointers. Since all analog pointer meters have a common nature, this multi-cascade model can serve various types of devices if its capacity is sufficient. The model is using global regression for locations of symbols, which provides resilient results even for low image quality and overlapping symbols. In this work, we do not focus on the pointer location detection since it heavily depends on the shape of the pointer. We prepare training data and benchmark the algorithm with our own framework a3net, not relying on third-party neural network solutions. The experimental results demonstrate the versatility of the proposed methods, high accuracy, and resilience of reference points detection.https://www.mdpi.com/2227-7390/8/7/1104AMRdial gaugepointer meterobject detectionCNNNiN |
| spellingShingle | Alexey Alexeev Georgy Kukharev Yuri Matveev Anton Matveev A Highly Efficient Neural Network Solution for Automated Detection of Pointer Meters with Different Analog Scales Operating in Different Conditions Mathematics AMR dial gauge pointer meter object detection CNN NiN |
| title | A Highly Efficient Neural Network Solution for Automated Detection of Pointer Meters with Different Analog Scales Operating in Different Conditions |
| title_full | A Highly Efficient Neural Network Solution for Automated Detection of Pointer Meters with Different Analog Scales Operating in Different Conditions |
| title_fullStr | A Highly Efficient Neural Network Solution for Automated Detection of Pointer Meters with Different Analog Scales Operating in Different Conditions |
| title_full_unstemmed | A Highly Efficient Neural Network Solution for Automated Detection of Pointer Meters with Different Analog Scales Operating in Different Conditions |
| title_short | A Highly Efficient Neural Network Solution for Automated Detection of Pointer Meters with Different Analog Scales Operating in Different Conditions |
| title_sort | highly efficient neural network solution for automated detection of pointer meters with different analog scales operating in different conditions |
| topic | AMR dial gauge pointer meter object detection CNN NiN |
| url | https://www.mdpi.com/2227-7390/8/7/1104 |
| work_keys_str_mv | AT alexeyalexeev ahighlyefficientneuralnetworksolutionforautomateddetectionofpointermeterswithdifferentanalogscalesoperatingindifferentconditions AT georgykukharev ahighlyefficientneuralnetworksolutionforautomateddetectionofpointermeterswithdifferentanalogscalesoperatingindifferentconditions AT yurimatveev ahighlyefficientneuralnetworksolutionforautomateddetectionofpointermeterswithdifferentanalogscalesoperatingindifferentconditions AT antonmatveev ahighlyefficientneuralnetworksolutionforautomateddetectionofpointermeterswithdifferentanalogscalesoperatingindifferentconditions AT alexeyalexeev highlyefficientneuralnetworksolutionforautomateddetectionofpointermeterswithdifferentanalogscalesoperatingindifferentconditions AT georgykukharev highlyefficientneuralnetworksolutionforautomateddetectionofpointermeterswithdifferentanalogscalesoperatingindifferentconditions AT yurimatveev highlyefficientneuralnetworksolutionforautomateddetectionofpointermeterswithdifferentanalogscalesoperatingindifferentconditions AT antonmatveev highlyefficientneuralnetworksolutionforautomateddetectionofpointermeterswithdifferentanalogscalesoperatingindifferentconditions |