Intelligent Recognition in Automated Meters Surveying
| Autor: | Alexandr Chuvakov, Nikita Svechkov, Anton Ivaschenko, Yuliya Tyshkovskaya, Tatiana Feschenko, Arkadiy Krivosheev, Denis Sveshnikov |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Artificial neural network
Computer science Process (engineering) media_common.quotation_subject Real-time computing Hand held devices neural networks photo fixation lcsh:Telecommunication meters surveying Identification (information) image recognition lcsh:TK5101-6720 distributed architecture Metre Quality (business) Scope (computer science) media_common |
| Zdroj: | FRUCT Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 27, Iss 1, Pp 84-89 (2020) |
| DOI: | 10.23919/fruct49677.2020.9211047 |
| Popis: | The paper proposes a new multi-layer solution to combine various algorithms implementing Artificial Intelligence (AI) for image recognition. Several neural networks are introduced to solve specific problems of objects identification. Additional “pre-launch matcher” is supplemented to scope out various objects and assigns them to the most corresponding AI modules. Distributed meter surveying is taken as an illustrative example of successful use. The introduced solution was implemented to process and analyze the results of electrical meters that are manually monitored by a group of patrol personnel inspectors using hand held devices. The results of development and testing show how the quality of neural network used for meter processing can be improved in practice. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|