Edge-VisionGuard: A Lightweight Signal-Processing and AI Framework for Driver State and Low-Visibility Hazard Detection
Source abstract
Abstract
Driving safety under low-visibility or distracted conditions remains a critical challenge for intelligent transportation systems. This paper presents Edge-VisionGuard, a lightweight framework that integrates signal processing and edge artificial intelligence to enhance real-time driver monitoring and hazard detection. The system fuses multi-modal sensor data—including visual, inertial, and illumination cues—to jointly estimate driver attention and environmental visibility. A hybrid temporal–spatial feature extractor (TS-FE) is introduced, combining convolutional and B-spline reconstruction filters to improve robustness against illumination changes and sensor noise. To enable deployment on resource-constrained automotive hardware, a structured pruning and quantization pipeline is proposed. Experiments on synthetic VR-based driving scenes demonstrate that the full-precision model achieves 89.6% driver-state accuracy (F1 = 0.893) and 100% visibility accuracy, with an average inference latency of 16.5 ms. After 60% parameter reduction and short fine-tuning, the pruned model preserves 87.1% accuracy (F1 = 0.866) and <3 ms latency overhead. These results confirm that Edge-VisionGuard maintains near-baseline performance under strict computational constraints, advancing the integration of computer vision and Edge AI for next-generation safe and reliable driving assistance systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Advanced Neural Network Applications · Advanced Optical Sensing Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Engineering Department and IEETA, University of Trás-os-Montes e Alto Douro, Quinta de Prados, 5000-801 Vila Real, Portugal
Engineering Department and Center ALGORITMI, University of Trás-os-Montes e Alto Douro, Quinta de Prados, 5000-801 Vila Real, Portugal
Engineering Department and INESC-TEC, University of Trás-os-Montes e Alto Douro, Quinta de Prados, 5000-801 Vila Real, Portugal
References (36)
Show source-provided references
1. Drowsiness Mitigation Through Driver State Monitoring Systems: A Scoping Review10.1177/00187208231208523 ↗
2. Beigi, S.A., and Park, B.B. (2025). Impact of Critical Situations on Autonomous Vehicles and Strategies for Improvement. Future Transp., 5.10.3390/futuretransp5020039 ↗
3. Technologies for Detecting and Monitoring Drivers’ States: A Systematic Review10.1016/j.heliyon.2024.e39592 ↗
4. Visconti, P., Rausa, G., Del-Valle-Soto, C., Velázquez, R., Cafagna, D., and De Fazio, R. (2025). Innovative Driver Monitoring Systems and On-Board-Vehicle Devices in a Smart-Road Scenario Based on the Internet of Vehicle Paradigm: A Literature and Commercial Solutions Overview. Sensors, 25.10.3390/s25020562 ↗
5. Attentional Warnings Caused by Driver Monitoring Systems: How Often Do They Appear and How Well Are They Understood?10.1016/j.aap.2024.107684 ↗
6. Xu, C., and Sankar, R. (2024). A Comprehensive Review of Autonomous Driving Algorithms: Tackling Adverse Weather Conditions, Unpredictable Traffic Violations, Blind Spot Monitoring, and Emergency Maneuvers. Algorithms, 17.10.3390/a17110526 ↗
7. Rahmani, S., Rieder, S., Gelder, E.d., Sonntag, M., Mallada, J.L., Kalisvaart, S., Hashemi, V., and Calvert, S.C. (2024). A Systematic Review of Edge Case Detection in Automated Driving: Methods, Challenges and Future Directions. arXiv.
8. Li, X., Chen, J., Sun, Y., Lin, N., Hawbani, A., and Zhao, L. (2024). YOLO-Vehicle-Pro: A Cloud-Edge Collaborative Framework for Object Detection in Autonomous Driving under Adverse Weather Conditions. arXiv.
9. Dipert, B. (2025, December 12). ADAS in 2024: Don’t Expect Clarity on Autonomy and Safety. Edge AI Vision Alliance. Available online: https://www.edge-ai-vision.com/2024/01/adas-in-2024-dont-expect-clarity-on-autonomy-and-safety/.
10. (2025, October 30). The Rise of Edge AI in Automotive | McKinsey. Available online: https://www.mckinsey.com/industries/semiconductors/our-insights/the-rise-of-edge-ai-in-automotive?utm_source=chatgpt.com.
11. Shankar, V. (2024, January 23–24). Edge AI: A Comprehensive Survey of Technologies, Applications, and Challenges. Proceedings of the 2024 1st International Conference on Advanced Computing and Emerging Technologies (ACET), Ghaziabad, India.10.1109/ACET61898.2024.10730112 ↗
12. CloudAIBus: A Testbed for AI Based Cloud Computing Environments10.1007/s10586-024-04562-9 ↗
13. (2025, October 30). Automotive Edge AI Accelerators Market Size, 2025–2034 Report. Available online: https://www.gminsights.com/industry-analysis/automotive-edge-ai-accelerators-market.
14. Ma, Y., Sanchez, V., Nikan, S., Upadhyay, D., Atote, B., and Guha, T. (2023, January 18–19). Robust Multiview Multimodal Driver Monitoring System Using Masked Multi-Head Self-Attention. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada.10.1109/CVPRW59228.2023.00260 ↗
15. (2014). Road Vehicles—Measurement of Driver Visual Behaviour with Respect to Transport Information and Control Systems (Standard No. ISO 15007).
16. Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00140 ↗
17. Ma, N., Zhang, X., Zheng, H.-T., and Sun, J. (2018, January 8–14). ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01264-9_8 ↗
18. Tan, M., and Le, Q.V. (2019, January 9–15). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA. PMLR 97:6105-6114.
19. (2025, October 30). ISO/WD 26262-6. Available online: https://www.iso.org/standard/90025.html.
20. Scalable Intrusion Detection in IoT Networks Via Property Testing and Federated Edge AI10.1109/ACCESS.2025.3603937 ↗
21. Abtahi, S., Omidyeganeh, M., Shirmohammadi, S., and Hariri, B. (2014, January 19–21). YawDD: A Yawning Detection Dataset. Proceedings of the 5th ACM Multimedia Systems Conference, Singapore.10.1145/2557642.2563678 ↗
22. Essahraui, S., Lamaakal, I., El Hamly, I., Maleh, Y., Ouahbi, I., El Makkaoui, K., Filali Bouami, M., Pławiak, P., Alfarraj, O., and Abd El-Latif, A.A. (2025). Real-Time Driver Drowsiness Detection Using Facial Analysis and Machine Learning Techniques. Sensors, 25.10.3390/s25030812 ↗
23. (2025, October 30). Nthuddd2. Available online: https://www.kaggle.com/datasets/banudeep/nthuddd2.
24. Getting to Know Low-light Images with The Exclusively Dark Dataset10.1016/j.cviu.2018.10.010 ↗
25. Gupta, R. (2025, October 30). BDD100K: A Large-Scale Diverse Driving Video Database. Available online: http://bair.berkeley.edu/blog/2018/05/30/bdd/.
26. (2025, December 12). Gdiazderada DMD—Driving Monitoring Dataset. DMD Dataset. Available online: https://dmd.vicomtech.org/.
27. Ortega, J.D., Kose, N., Cañas, P., Chao, M.-A., Unnervik, A., Nieto, M., Otaegui, O., and Salgado, L. (2020, January 23–28). DMD: A Large-Scale Multi-Modal Driver Monitoring Dataset for Attention and Alertness Analysis. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-66823-5_23 ↗
28. (2025, December 12). Vicomtech/DMD-Driver-Monitoring-Dataset. Available online: https://github.com/Vicomtech/DMD-Driver-Monitoring-Dataset.
29. Martin, M. (2025, October 30). The Drive and Act Dataset. Available online: https://driveandact.com/.
30. Martin, M., Roitberg, A., Haurilet, M., Horne, M., ReiB, S., Voit, M., and Stiefelhagen, R. (November, January 27). Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea. Available online: https://driveandact.com/publication/2019_iccv_drive_and_act/.10.1109/ICCV.2019.00289 ↗
31. Look Both Ways: Self-Supervising Driver Gaze Estimation and Road Scene Saliency10.1007/978-3-031-19778-9_8 ↗
32. Eraqi, H. (2025, October 30). Distracted Driver Dataset. Available online: http://heshameraqi.github.io/distraction_detection.
33. (2025, October 30). AUC Distracted Driver Dataset_V1. Available online: https://www.kaggle.com/datasets/tejakalepalle/auc-distracted-driver-dataset-v1.
34. Kairouz, P., McMahan, H.B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A.N., Bonawitz, K., Charles, Z., Cormode, G., and Cummings, R. (2021). Advances and Open Problems in Federated Learning. arXiv.10.1561/9781680837896 ↗
35. European Union (2024). Regulation (EU) 2024/1684 of the European Parliament and of the Council of 13 June 2024 Laying Down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act), Official Journal of the European Union.
36. (2023). Information Technology—Artificial Intelligence—Guidance on Risk Management (Standard No. ISO/IEC 23894:2023).