Development of an Access Control System for Monitoring Vehicle Movement using Computer Vision and Token-Based Authentication | IJCT Volume 13 – Issue 3 | IJCT-V13I3P93
International Journal of Computer Techniques
ISSN 2394-2231
Author
Akintoye A. Onamade, Benjamin Francis Daria, Taiwo Gabriel Aboderin, Ilerioluwa Israel Fagbayike, Saheed Opeyemi Abioye, Jeremiah Ademola Balogun, Olusegun Gbenga Lala
Abstract
Securing vehicle access points in places like corporate organisations, university campuses, markets, and residential buildings has long been a challenge. Most existing systems either rely totally on manual checks, which are slow and error-prone, or single-phase methods such as RFID cards that can be cloned. Neither approach offers the security and efficiency that modern environments require. This study addresses that gap by developing an Automated Vehicle Access Control System (AVACS) that combines two phases of verification: Automatic Number Plate Recognition (ANPR) and token-based authentication. Rather than relying on a single phase, the system requires both a valid vehicle plate for entry and an authenticated token for exit, making it significantly harder to bypass. On the technical side, the system uses YOLOv8n for real-time vehicle detection, EasyOCR/Tesseract for plate number character recognition, and a FastAPI backend paired with a React/Tailwind frontend. Data is stored in MongoDB Atlas, and the ANPR component was trained to handle Nigerian Standard Plate Number formats, an area that has been largely underserved in existing research. The system was evaluated on key performance indicators, including recognition accuracy, authentication response time, and overall reliability. Results demonstrated that the integrated multi-phase approach outperforms single-phase systems in both security and operational efficiency, while also providing better audit trails for incident tracking. This work contributes to the growing body of research on vehicle access control. It lays a foundation for future exploration of multi-factor vehicle authentication in smart infrastructure and IoT environments.
Keywords
Vehicle Access Control, Computer Vision, YOLOv8n, Deep Learning
Conclusion
The proposed system effectively combines computer vision and token-based authentication to provide a reliable vehicle access control solution. It utilises YOLOv8n for real-time vehicle detection, OCR for license plate recognition, and JWT for secure validation, thereby overcoming major limitations associated with manual and single-factor authentication systems. Experimental results demonstrated an ANPR accuracy of 91.5% and response times below 500 ms, indicating that the system is suitable for real-world deployment in environments such as university campuses, residential estates, corporate organisations, and logistics facilities.
The study achieved its objective of developing a functional, scalable, and secure vehicle access control framework that improves authentication reliability and audit tracking through multi-phase verification. The integration of Automatic Number Plate Recognition with token-based authentication also demonstrates the practical potential of combining computer vision and lightweight digital authentication techniques in modern smart access systems.
Future work should focus on improving system robustness under challenging environmental conditions, particularly low-light and night-time scenarios. This may involve the integration of infrared-assisted imaging, adaptive image enhancement techniques, and more advanced deep learning models for illumination-invariant recognition. In addition, future research should expand the training dataset to include multiple Nigerian plate categories such as government, military, diplomatic, commercial, and customised license plates in order to improve generalisation and deployment readiness across diverse operational environments. Further optimisation of computational efficiency and edge deployment techniques may also enhance scalability for large-scale smart city and intelligent transportation applications.
References
[1] S. Capkun, M. Cagalj, and J.-P. Hubaux, “Tailing RFID tags for clone detection,” in Proc. Network and Distributed System Security Symposium (NDSS), Internet Society, 2012. [Online]. Available: https://www.ndss-symposium.org
[2] C. Munoz-Ausecha, “RFID applications and security review,” Algorithms, vol. 14, no. 6, p. 169, 2021, doi: 10.3390/computation9060069.
[3] F. Alsakka, S. Assaf, I. El-Chami, and M. Al-Hussein, “Computer vision applications in off-site construction,” Automation in Construction, vol. 154, p. 104980, 2023, doi: 10.1016/j.autcon.2023.104980.
[4] Z. Liu, M. Xu, and Y. Zhang, “A survey on deep learning for intelligent transportation systems: methods, applications, and challenges,” Expert Systems with Applications, vol. 236, p. 121364, 2024, doi: 10.1016/j.eswa.2023.121364.
[5] Y. Gong, K. Li, L. Xiao, J. Cai, J. Xiao, and W. Liang, “VASERP: An adaptive, lightweight, secure, and efficient RFID-based authentication scheme for Internet of Vehicles,” Sensors, vol. 23, no. 11, p. 5198, 2023.
[6] F. Alharbi, R. Alshahrani, M. Zakariah, A. Aldweesh, and A. A. Alghamdi, “YOLO and blockchain technology applied to intelligent transportation license plate character recognition for security,” Computers, Materials & Continua, vol. 77, no. 3, pp. 3697–3722, 2023.
[7] K. Roy, M. Ahmad, N. A. Ghani, J. Uddin, and J. Shin, “An automated precise authentication of vehicles for enhancing visual security protocols,” Information, vol. 14, no. 8, p. 466, 2023.
[8] A. Jodeiri Akbarfam, S. Barazandeh, H. Maleki, and D. Gupta, “DLACB: Deep learning-based access control using blockchain,” arXiv preprint arXiv:2303.14758, 2023.
[9] V. Rai, G. Kumar, A. K. Kushwaha, A. Pandey, and V. Kumar, “TrALPR: Automatic license plate recognition using transformers,” in Proc. IEEE MOSICOM, 2023, pp. 144–149.
[10] M. Kim, I. Oh, J. Park, M. Sahlabadi, and Z. Shukur, “Security of 6G-enabled vehicle-to-everything communication in emerging federated learning and blockchain technologies,” IEEE Access, vol. 12, pp. 33972–34001, 2024.
[11] A. Jodeiri Akbarfam, S. Barazandeh, D. Gupta, and H. Maleki, “Deep learning meets blockchain for automated and secure access control,” arXiv preprint arXiv:2311.06236, 2023.
[12] F. Alharbi et al., “Intelligent transportation using wireless sensor networks and blockchain-based license plate recognition,” Sensors, vol. 23, no. 5, p. 2670, 2023.
[13] N. M. Alahdal et al., “Real-time object detection in autonomous vehicles with YOLO,” Procedia Computer Science, 2024.
[14] M. Talib, A. Al-Noori, and J. Suad, “YOLOv8-CAB: Improved YOLOv8 for real-time object detection,” Karbala International Journal of Modern Science, vol. 10, 2024, doi: 10.33640/2405-609X.3339.
[15] M. Samantaray, A. K. Biswal, D. Singh, et al., “Optical character recognition (OCR)-based vehicle’s license plate recognition system using Python and OpenCV,” in Proc. 5th Int. Conf. Computing, Communication and Intelligent Systems (ICCCIS), 2021.
[16] R. Buoy, M. Wamura, S. Srun, and K. Kise, “Toward a low-resource non-Latin complete baseline: An exploration of Khmer optical character recognition,” IEEE Access, 2023, doi: 10.3390/s21093028.
[17] S. Talakola and S. P. Veluru, “Managing authentication in REST Assured, OAuth, JWT and more,” International Journal of Emerging Trends in Computer Science and Information Technology, 2023.
[18] A. Juels, “RFID security and privacy: A research survey,” IEEE Journal on Selected Areas in Communications, vol. 24, no. 2, pp. 381–394, Feb. 2006, doi: 10.1109/JSAC.2005.861395.
[19] K. L. Ng, C. W. R. Chiong, and R. Reine, “Vehicle recognition system using RFID technology for parking management system,” IOP Conference Series: Materials Science and Engineering, vol. 495, no. 1, 2019, doi: 10.1088/1757-899X/495/1/012022.
[20] N. Mufti and S. A. Shah, “Automatic number plate recognition: A detailed survey of relevant algorithms,” Sensors, vol. 21, no. 9, p. 3028, 2021, doi: 10.3390/s21093028.
[21] P. Surekha, P. Gurudath, R. Prithvi, et al., “Automatic license plate recognition using image processing and neural network,” 2018.
[22] M. Al-Hasan, A. Alenezi, and H. Alsaif, “Automatic number plate recognition using YOLOv8 and deep learning techniques,” Technologies, vol. 12, no. 9, p. 164, 2024, doi: 10.3390/technologies12090164.
[23] S. Moussaoui, A. Chfadi, and Y. Ruichek, “Real-time vehicle and license plate recognition using YOLOv8 and OCR techniques,” Scientific Reports, vol. 14, no. 1, p. 65272, 2024, doi: 10.1038/s41598-024-65272-1.
[24] M. Siddiqui, A. Khan, and S. Rehman, “Vehicle and driver recognition for access control using YOLOv8 and EasyOCR,” in Proc. 2024 Int. Conf. Artificial Intelligence and Smart Systems (ICAIS), 2024, pp. 411–417.
[25] D. H. Brainard and B. A. Wandell, “Analysis of the Retinex theory of colour vision,” Journal of the Optical Society of America A, vol. 3, no. 10, pp. 1651–1661, 1986.
[26] B. Liu, M. Ding, S. Shaham, W. Rahayu, F. Farokhi, and Z. Lin, “When machine learning meets privacy: A survey and outlook,” arXiv preprint arXiv:2011.11819, 2020.
How to Cite This Paper
Akintoye A. Onamade, Benjamin Francis Daria, Taiwo Gabriel Aboderin, Ilerioluwa Israel Fagbayike, Saheed Opeyemi Abioye, Jeremiah Ademola Balogun, Olusegun Gbenga Lala (2026). Development of an Access Control System for Monitoring Vehicle Movement using Computer Vision and Token-Based Authentication. International Journal of Computer Techniques, 13(3). ISSN: 2394-2231.
Development of an Access Control System for Monitoring Vehicle Movement using Computer Vision and Token-Based AuthenticationDownload
Related Posts:
