Drowsiness Detection in Drivers Using Facial Feature Analysis
Source abstract
Abstract
Drowsiness has been recognized as a leading factor in road accidents worldwide. Despite considerable research in this area, this paper aims to improve the precision of drowsiness detection specifically for long-haul travel by employing the Dlib-based facial feature detection algorithm. This study proposes two algorithms: a static and adaptive frame threshold. Both approaches utilize eye closure ratio (ECR) and mouth aperture ratio (MAR) parameters to determine the driver’s level of drowsiness. The static threshold method issues a warning when the ECR and/or MAR values reach specific thresholds. In this method, the ECR threshold is established at 0.15 and the MAR threshold at 0.4. The static threshold method demonstrated an accuracy of 89.4% and a sensitivity of 96.5% using 1000 images. The adaptive frame threshold algorithm uses a counter to monitor the number of consecutive frames that meet the drowsiness criteria before triggering a warning. Additionally, the number of consecutive frames required is adjusted dynamically over time to enhance detection accuracy and more accurately indicate a state of drowsiness. The adaptive frame threshold algorithm was tested using four 30 min videos, from a publicly available dataset achieving a maximum accuracy of 98.2% and a sensitivity of 64.3% with 500 images.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sleep and Work-Related Fatigue · Ergonomics and Musculoskeletal Disorders · Traffic and Road Safety
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, Louisiana State University, Baton Rouge, LA 70803, USA
Department of Electrical and Computer Engineering, Southern University and A&M College, Baton Rouge, LA 70807, USA
College of Information Technology, University of Bahrain, Zallaq 1054, Bahrain
Funding
Louisiana Transportation Research Center
References (40)
Show source-provided references
1. Essel, E., Lacy, F., Elmedany, W., Albalooshi, F., and Ismail, Y. (2022, January 25–26). Driver drowsiness detection using fixed and dynamic thresholding. Proceedings of the 2022 International Conference on Data Analytics for Business and Industry (ICDABI), IEEE, online.10.1109/ICDABI56818.2022.10041670 ↗
2. A survey on drowsiness detection techniques?
3. Ganguly, B., Dey, D., and Munshi, S. (2022, January 26–27). An Integrated System for Drivers’ Drowsiness Detection Using Deep Learning Frameworks. Proceedings of the 2022 IEEE VLSI Device Circuit and System (VLSI DCS), Kolkata, India.10.1109/VLSIDCS53788.2022.9811442 ↗
4. Choudhary, Y., Aggarwal, A., and Agarwal, A. (2022, January 23–25). Detecting Drivers’ Drowsiness using Haar Cascade Classifier. Proceedings of the 2022 9th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India.10.23919/INDIACom54597.2022.9763192 ↗
5. Neeraja, P., Kumar, R.G., Kumar, M.S., Liyakat, K.K.S., and Vani, M.S. (2024, January 9–10). DL-Based Somnolence Detection for Improved Driver Safety and Alertness Monitoring. Proceedings of the 2024 IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT), Greater Noida, India.10.1109/IC2PCT60090.2024.10486714 ↗
6. Yogesh, R., Ritheesh, V., Reddy, S., and Rajan, R.G. (2022, January 15–16). Driver Drowsiness Detection and Alert System using YOLO. Proceedings of the 2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), Chennai, India.
7. Agarkar, A.S., Gandhiraj, R., and Panda, M.K. (2023, January 5–6). Driver Drowsiness Detection and Warning using Facial Features and Hand Gestures. Proceedings of the 2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN), Vellore, India.10.1109/ViTECoN58111.2023.10157233 ↗
8. Amidei, A., Poli, A., Iadarola, G., Tramarin, F., Pavan, P., Spinsante, S., and Rovati, L. (2022, January 4–6). Driver Drowsiness Detection based on Variation of Skin Conductance from Wearable Device. Proceedings of the 2022 IEEE International Workshop on Metrology for Automotive (MetroAutomotive), Modena, Italy.10.1109/MetroAutomotive54295.2022.9854871 ↗
9. Prasath, N., Sreemathy, J., and Vigneshwaran, P. (2022, January 25–26). Driver Drowsiness Detection Using Machine Learning Algorithm. Proceedings of the 2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India.10.1109/ICACCS54159.2022.9785167 ↗
10. Ananthi, S., Sathya, R., Vaidehi, K., and Vijaya, G. (2023, January 17–19). Drivers Drowsiness Detection using Image Processing and I-Ear Techniques. Proceedings of the 2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India.10.1109/ICICCS56967.2023.10142501 ↗
11. Fusion of EEG and Eye Blink Analysis for Detection of Driver Fatigue10.1109/TNSRE.2023.3267114 ↗
12. Intelligent Driver Drowsiness Detection for Traffic Safety Based on Multi CNN Deep Model and Facial Subsampling10.1109/TITS.2021.3134222 ↗
13. Internet-of-Things-Assisted Artificial Intelligence-Enabled Drowsiness Detection Framework10.1109/LSENS.2023.3289143 ↗
14. IoT-Based Non-Intrusive Automated Driver Drowsiness Monitoring Framework for Logistics and Public Transport Applications to Enhance Road Safety10.1109/ACCESS.2023.3244008 ↗
15. Guria, M., and Bhowmik, B. (2022, January 25–27). IoT-Enabled Driver Drowsiness Detection Using Machine Learning. Proceedings of the 2022 Seventh International Conference on Parallel, Distributed and Grid Computing (PDGC), Solan, India.10.1109/PDGC56933.2022.10053235 ↗
16. Learning Multimodal Representations for Drowsiness Detection10.1109/TITS.2021.3105326 ↗
17. Guo, Z., Wang, G., Zhou, M., and Li, G. (2022, January 28–30). Monitoring and Detection of Driver Fatigue from Monocular Cameras Based on Yolo v5. Proceedings of the 2022 6th CAA International Conference on Vehicular Control and Intelligence (CVCI), Nanjing, China.10.1109/CVCI56766.2022.9964752 ↗
18. Simultaneous Eye Blink Characterization and Elimination from Low-Channel Prefrontal EEG Signals Enhances Driver Drowsiness Detection10.1109/JBHI.2021.3096984 ↗
19. Two-Stream Spatial–Temporal Graph Convolutional Networks for Driver Drowsiness Detection10.1109/TCYB.2021.3110813 ↗
20. RF-DCM: Multi- Granularity Deep Convolutional Model Based on Feature Recalibration and Fusion for Driver Fatigue Detection10.1109/TITS.2020.3017513 ↗
21. Privacy-Preserving Federated Transfer Learning for Driver Drowsiness Detection10.1109/ACCESS.2022.3192454 ↗
22. Isotropic Self-Supervised Learning for Driver Drowsiness Detection with Attention-Based Multimodal Fusion10.1109/TMM.2021.3128738 ↗
23. High-Fidelity Machine Learning Techniques for Driver Drowsiness Detection
24. Abtahi, S., Omidyeganeh, M., Shirmohammadi, S., and Hariri, B. (2014, January 19–21). YawDD: A Yawning Detection Dataset. Proceedings of the ACM Multimedia Systems, Singapore.10.1145/2557642.2563678 ↗
25. Mehta, S., Mishra, P., Bhatt, A.J., and Agarwal, P. (2019, January 15–17). AD3S: Advanced Driver Drowsiness Detection System using Machine Learning. Proceedings of the 2019 Fifth International Conference on Image Information Processing (ICIIP), Shimla, India.10.1109/ICIIP47207.2019.8985844 ↗
26. Cech, J., and Soukupova, T. (2016). Real-Time Eye Blink Detection using Facial Landmarks. Comput. Sci., 1–8.
27. Gupta, I., Garg, N., Aggarwal, A., Nepalia, N., and Verma, B. (2018, January 2–4). Real-Time Driver’s Drowsiness Monitoring Based on Dynamically Varying Threshold. Proceedings of the 2018 11th International Conference on Contemporary Computing (IC3) 2018, Noida, India.10.1109/IC3.2018.8530651 ↗
28. Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., and Pantic, M. (2013, January 2–8). 300 Faces in-the-Wild Challenge: The first facial landmark localization Challenge. Proceedings of the IEEE Int’l Conf. on Computer Vision (ICCV-W), 300 Faces in-the-Wild Challenge (300-W), Sydney, Australia.10.1109/ICCVW.2013.59 ↗
29. Bhope, R.A. (2019, January 18–19). Computer Vision-based drowsiness detection for motorized vehicles with Web Push Notifications. Proceedings of the 2019 4th International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU), Ghaziabad, India.10.1109/IoT-SIU.2019.8777652 ↗
30. Kumar, A., and Patra, R. (2018, January 28–29). Driver drowsiness monitoring system using visual behavior and machine learning. Proceedings of the 2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), Penang, Malaysia.10.1109/ISCAIE.2018.8405495 ↗
31. (2022, February 28). Uber to Require a 6-Hour Break for Every 12 Hours of Driving in the U.S. Available online: https://techcrunch.com/2018/02/12/uber-to-require-a-6-hour-break-for-every-12-hours-of-driving-in-the-u-s/.
32. Ghoddoosian, R., Galib, M., and Athitsos, V. (2019, January 17–18). A realistic dataset and baseline temporal model for early drowsiness detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.10.1109/CVPRW.2019.00027 ↗
33. Yawning in Diseases10.1159/000228262 ↗
34. (2022, March 16). Average Duration of a Single Eye Blink–human Homo Sapiens–BNID 100706. Available online: https://bionumbers.hms.harvard.edu/bionumber.aspx?id=100706&ver=4.
35. Munoz, G. (2022, March 16). How Fast Is a Blink of an Eye?. sciencing.com., Available online: https://sciencing.com/fast-blink-eye-5199669.html.
36. Cost-Optimized Cloud Resource Management for Video Streaming: ARIMA Predictive Approach10.1007/s10586-023-04135-2 ↗
37. Cost Minimization of Cloud Services for On-Demand Video Streaming10.1007/s42979-022-01140-x ↗
38. Obaidan, H.B., Hussain, M., and AlMajed, R. (2024). EEG_DMNet: A Deep Multi-Scale Convolutional Neural Network for Electroencephalography-Based Driver Drowsiness Detection. Electronics, 13.10.3390/electronics13112084 ↗
39. Krishna, G.S., Kundrapu, S., and Jai, V. (2022). Vision transformers and YoloV5 based driver drowsiness detection framework. arXiv.
40. Vehicle driver drowsiness detection method using wearable EEG based on convolution neural network10.1007/s00521-021-06038-y ↗