Behaviour Aware Hybrid Edge-Cloud ALPR for Secure and Privacy Preserving Residential Gate Access Control

Automatic License Plate Recognition (ALPR) can automate residential vehicle access, but conventional cloud centric and edge only approaches face limitations in latency, privacy, computational capability, and recognition robustness. This study presents a deployed residential smart gate prototype that integrates a confidence aware hybrid ALPR pipeline, a Vehicle Behavior Profiling System (VBPS), and security hardened MQTT/TLS communication on a Raspberry Pi 5. The ALPR pipeline employs YOLOv5n ONNX for license plate detection and dynamically routes detected plates to an in-memory resident cache, local Tesseract OCR, or cloud OCR based on recognition confidence and recent vehicle history, while the VBPS maintains vehicle profiles and evaluates temporal and frequency based behavioural features to generate five adaptive gate decisions instead of a binary allow/deny response. Gate control and monitoring communications are secured using MQTT over TLS 1.2 with AES-256-GCM encryption and mutual certificate authentication. Experimental evaluation of the deployed prototype achieved 97.3% detection mAP, a 61% cache hit rate, a 96.7% reduction in cloud API usage, and a weighted average processing latency of 749 ms. The false denial rate decreased from 51.3% in the evaluated baseline configurations to 3.6% with the behaviour aware system, while the VBPS achieved 100% precision across the evaluated structured temporal and behavioral anomaly scenarios and satisfied all 12 evaluated access control requirements. Furthermore, four security tests covering unauthorized clients, message interception, replay attacks, and command integrity were successfully passed. These findings demonstrate the feasibility of combining hybrid ALPR, behaviour aware access control, and secure IoT communication on constrained residential hardware, while identifying the need for larger real-world datasets and further optimization of end-to-end latency.

Automatic License Plate Recognition (ALPR), edge computing, cloud computing, Internet of Things (IoT), smart gate

1. Al-Batat et al., “An end-to-end automated license plate recognition system using YOLO based vehicle and license plate detection with vehicle classification,” Sensors, vol. 22, no. 23, 2022. [Google Scholar] [Crossref]

2. Al-Batat et al., work on constrained edge ALPR optimization, Journal of Real-Time Image Processing, 2022. [Google Scholar] [Crossref]

3. Al-Hasan et al., work on enhanced YOLO-based automatic number plate recognition, Technologies, 2024. [Google Scholar] [Crossref]

4. Al-Hasan et al., work on robust CNN-based automatic number plate recognition under challenging environmental conditions, Sensors, 2024. [Google Scholar] [Crossref]

5. Leng et al., work on hybrid/cloud-assisted ALPR processing and latency/cloud-utilization optimization, 2023. [Google Scholar] [Crossref]

6. Cabanillas Rodríguez et al., “DEBAC” behavioral/trust-based access-control work, EuCNC, 2025. [Google Scholar] [Crossref]

7. Cabanillas et al., work on behavioral anomaly detection and access control, Future Generation Computer Systems, 2025. [Google Scholar] [Crossref]

8. Duong et al., deep-learning anomaly-detection survey and vehicle/behavioral anomaly literature, Sensors, 2023. [Google Scholar] [Crossref]

9. Farhadighalati et al., systematic work on behavioral and access-control requirements, IEEE Access, 2025. [Google Scholar] [Crossref]

10. Janati and Messaoudi, behavior-based intrusion/anomaly detection using frequency, timing, and deviation signals, International Journal of Advanced Computer Science and Applications, 2025. [Google Scholar] [Crossref]

11. Kaveh et al., hybrid time-series/anomaly detection approach, Symmetry, 2025. [Google Scholar] [Crossref]

12. Landauer et al., review of time-series methods for anomaly detection, International Journal of Information Security, 2025. [Google Scholar] [Crossref]

13. Pathirannahalage et al., real-time surveillance and anomaly-detection architecture, Multimedia Tools and Applications, 2024. [Google Scholar] [Crossref]

14. Vardakis et al., analysis of security vulnerabilities in smart-home and IoT systems, 2024. [Google Scholar] [Crossref]

15. Zia et al., transformer/adversarial approaches to anomaly detection on constrained IoT devices, Electronics, 2025. [Google Scholar] [Crossref]

16. Tao et al., work on robust/optimized ALPR processing under challenging image conditions, 2024. [Google Scholar] [Crossref]

17. Zhang et al., work addressing image degradation and robustness in ALPR, 2024. [Google Scholar] [Crossref]

18. Elmetwally et al., real-time abnormal-event detection using temporal video information, Multimedia Tools and Applications, 2024. [Google Scholar] [Crossref]