Two-factor vehicle identification system for checkpoints

The article deals with the problem of increasing the accuracy and reliability of automatic vehicle access control systems. Modern methods of license plate recognition provide high accuracy in laboratory conditions, but their efficiency decreases under unfavorable external factors (weather conditions, license plate contamination, etc.). In this regard, a method of two-factor vehicle identification is proposed, including traditional license plate recognition and additional authentication by MAC-address of the driver's mobile device using IEEE 802.11 Wi-Fi network.

Research methods include analyzing the network interaction between client devices and Wi-Fi access points, using the monitoring mode of wireless adapters to intercept Probe Request packets, and applying machine learning algorithms to associate cars with the MAC addresses of their owners. A structural scheme of the system is developed in which a Wi-Fi access point captures the MAC addresses of devices in the network coverage area and checks them against a database. The system automatically opens the barrier when one or both identification factors are successfully matched.

The results show that the use of two-factor authentication significantly improves the reliability of the access control system, compensating for the shortcomings of computer vision methods.

1. Mehak, Arshid., M., Azam., Zahid, Mahmood. (2024). A Comparative Study on Detection and Recognition of Nonuniform License Plates. Big data and cognitive computing, 8(11):155-155. DOI: 10.3390/bdcc8110155.

2. Gopal, D., Upadhye. (2024). Advanced Automated Number Plate Recognizer using Machine Learning Technique. Deleted Journal, 32(1s):419-431. DOI: 10.52783/cana.v32.2206.

3. Er., Inderjeet, Singh., Parvez, Rahi., Vanshika, Jain., Nidhi, Sharma., Yuvraj, Anand., Ashutosh, Kumar, Shukla. (2024). Recognition System: Detection of License Plate. 3:171-177. DOI: 10.1109/iccpct61902.2024.10673076.

4. M., C., Rademeyer., A., Barnard., Marthinus, J., Booysen. (2020). Optoelectronic and Environmental Factors Affecting the Accuracy of Crowd-Sourced Vehicle-Mounted License Plate Recognition. 1:15-28. doi: 10.1109/OJITS.2020.2991402.

5. Ibanez, J., Zeadally, S., & Contreras-Castillo, J. (2018). Sensor Technologies for Intelligent Transportation Systems. Sensors (Basel, Switzerland), 18. https://doi.org/10.3390/s18041212.

6. Tekhnologii sovremennyh besprovodnyh setej Wi-Fi: uchebnoe posobie / [E.V. Smirnova, A.V. Proletarskij i dr.]; pod obshch. red. A.V. Proletarskogo. - M. : Izd-vo MGTU im. N.E. Baumana, 2017. - 446 s.

7. Choubisa, M., Kumar, V., Kumar, M., & Khanna, D. (2023). Object Tracking in Intelligent Video Surveillance System Based on Artificial System. 2023 International Conference on Computational Intelligence, Communication Technology and Networking (CICTN), 160-166. https://doi.org/10.1109/cictn57981.2023.10140727.

8. Pratomo, A., Mokodenseho, S., & Aziz, A. (2023). Data Encryption and Anonymization Techniques for Enhanced Information System Security and Privacy. West Science Information System and Technology. https://doi.org/10.58812/wsist.v1i01.176.

9. Understanding RSSI https://www.metageek.com/training/resources/understandingrssi/?utmsource=chatgpt.com (10 февраля 2024).