Development and research of the software module for vehicle access control and management based on license plate recognition

E.E. Istratova, A.I. Gosteeva

Abstract


The article presents the results of the development and research of a software module for monitoring and managing the access of vehicles to the territory. Based on the analysis of literary sources, an algorithm for recognizing state license plates was developed, its software implementation was completed, its own data set was formed, and a neural network model was trained. The functionality of the program lies in the application of one-stage detection methods to solving the problem of recognizing license plates of vehicles. Thanks to this, the software product can be used for educational and research purposes, and can also be used both standalone and connected to building security systems as an embedded module. In the course of a comparative analysis of the developed software module with similar software products, it was concluded that the use of the developed model is appropriate. It can be used to recognize license plates in real time, showing good accuracy and completeness, as well as excellent frame processing speed. As a result, a software module for vehicle access control and management based on license plate recognition was implemented and studied, which has the following advantages: the ability to work on devices with low computing power; high speed image processing; possibility of integration with other software products; low cost.


Full Text:

PDF (Russian)

References


Lapteva M.A., Favorskaya M.N., Boldyrev K.M. Vehicle registration number recognition system using a neural network // Actual problems of aviation and cosmonautics. 2014. No. 10. URL: https://cyberleninka.ru/article/n/sistema-raspoznavaniya-registrationnyh-nomerov-avtomobilya-s-primeneniem-neyronnoy-seti.

Mogilin K.A., Selishchev V.A. Intelligent video surveillance systems in security complexes // Izvestiya TulGU. Technical science. 2020. №3. URL: https://cyberleninka.ru/article/n/intellektualnye-sistemy-videonablyudeniya-v-kompleksah-bezopasnosti.

Elizarov A.I., Afonasenko A.V. Methodology for building license plate recognition systems. Izvestiya TPU. 2006. No. 8. URL: https://cyberleninka.ru/article/n/metodika-postroeniya-sistem-raspoznavaniya-avtomobilnogo-nomera.

Kadrov I.V., Vorobeichik M.M., Redkin M.Yu., Myagkov A.Yu. License plate recognition using a neural network // StudNet. 2020. No. 10. URL: https://cyberleninka.ru/article/n/raspoznanie-avtomobilnyh-nomerov-s-pomoschyu-neyronnoy-seti.

GOST R 50577-2018 Signs of state registration of vehicles - M.: JSC "Kodeks", 2018. - 40 p.

Kim H.H., Park J.K., Oh J.H. Multi-task convolutional neural network system for license plate recognition. Int. J. Control Autom. Syst. 15, 2942–2949 (2017). URL: https://doi.org/10.1007/s12555-016-0332-z.

Khan K., Imran A., Rehman H.Z.U. Performance enhancement method for multiple license plate recognition in challenging environments. J Image Video Proc. 2021, 30 (2021). URL: https://doi.org/10.1186/s13640-021-00572-4.

Izidio D.M.F., Ferreira A.P.A., Medeiros H.R. An embedded automatic license plate recognition system using deep learning. Des Autom Embed Syst 24, 23–43 (2020). URL: https://doi.org/10.1007/s10617-019-09230-5.

Zou Y., Zhang Y., Yan J. License plate detection and recognition based on YOLOv3 and ILPRNET. SIViP 16, 473–480 (2022). URL: https://doi.org/10.1007/s11760-021-01981-8.

Saidani T., Touati Y.E. A vehicle plate recognition system based on deep learning algorithms. Multimed Tools Appl 80, 36237–36248 (2021). URL: https://doi.org/10.1007/s11042-021-11233-z.

Shahidi Zandi M., Rajabi R. Deep learning-based framework for Iranian license plate detection and recognition. Multimed Tools Appl (2022). URL: https://doi.org/10.1007/s11042-022-12023-x.

Istratova E.E., Bukhamer E.A., Gosteeva A.I. Program for control and management of vehicle access based on license plate recognition. Certificate of registration of the computer program 2022661265, 06/22/2022. Application No. 2022660761 dated 06/22/2022.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162