Drowsiness Detection using YOLOv12
DOI:
https://doi.org/10.32664/j-intech.v14i01.2212Keywords:
Computer Vision, Drowsiness Detection, Embedded Systems, Real-Time Object Detection, YOLOv12Abstract
Drowsiness poses significant risks in safety-critical activities such as driving, industrial operations, and online learning. While advanced deep learning models (e.g., CNN-LSTM hybrids) achieve high accuracy in driver drowsiness detection, they often require substantial computational resources, limiting deployment on embedded or resource-constrained devices. This study addresses the research gap in lightweight, real-time, non-invasive drowsiness detection by developing an embeddable library using YOLOv12, an attention-centric single-stage detector known for balancing speed and accuracy. The model was trained on a custom dataset of 2312 video frame sequences (1011 "awake" and 1301 "drowsy" states, captured from varied angles under consistent lighting), augmented with standard techniques (e.g., brightness/contrast adjustments, flips, and rotations) to enhance generalization. It was evaluated through 80 real-time trials across multiple subjects. Performance metrics include accuracy of 93%, precision of 0.94, recall of 0.91, and F1-score of 0.93. The system detects drowsiness via facial bounding boxes followed by state classification (integrating eye/mouth aspect ratios) in real time. The main contribution is a proof-of-concept YOLOv12-based approach for non-invasive drowsiness monitoring, offering faster inference suitable for embedded applications (e.g., vehicle systems, meeting tools, or industrial safety) compared to heavier hybrid models. Limitations include some remaining sensitivity to extreme lighting/angles and dataset scale; future work will expand datasets, incorporate multi-modal cues, and further test robustness in diverse real-world conditions.
References
[1] A. Ritonga, S. Iskandar Al Idrus, and D. Yandra Niska, “Application of the K-Nearest Neighbor (K-NN) Algorithm for Detecting Banana Harvest Feasibility,” J. Inf. Technol. Accredit. Sinta, vol. 4, 2025.
[2] D. S. Deswita Indriani, K. S. Saputra, S. Iskandar Al Idrus, and A. Perdana, “Identification of Palm Oil Fresh Fruit Bunches Worth Selling with K-Nearest Neighbors Algorithm,” J. Inf. Technol. Accredit. Sinta, vol. 4, 2025.
[3] E. Muhammad Atsir and A. Arum Sari, “Traffic Accident Severity Classification System Using Random Forest Algorithm,” J. Inf. Technol. Accredit. Sinta, vol. 4, 2025, [Online]. Available: https://www.kaggle.com/datasets/saurabhshahane/road-traffic-accidents.
[4] A. Anggit Purnawan and S. D. Sancoko, “Design and Implementation of FitSphere as an Android Application for Gym Membership Management at Chain Gym,” J. Inf. Technol. Accredit. Sinta, vol. 4, 2025.
[5] B. A. Wisesa et al., “Preventive Attendance Record using Photo from Mobile Phone and Printed Paper using CNN,” J. Inf. Technol. Accredit. Sinta, vol. 4, 2025.
[6] B. A. Wisesa, W. Andriyani, and B. D. P. Purnomosidi, “Usage of LSTM Method on Hand Gesture Recognition for Easy Learning of Sign Language Based on Desktop Via Webcam,” in 2022 5th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 148–153. doi: 10.1109/ISRITI56927.2022.10053076.
[7] B. A. Wisesa, W. Andriyani, T. Suprawoto, and Hamdani, “Development of Learning Media for the Deaf Using a Webcam,” in 2022 5th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 160–165. doi: 10.1109/ISRITI56927.2022.10052934.
[8] H. Harb, “An Efficient Drowsiness Detection Framework for Improving Driver Safety Through Supervised Learning Models,” World Electr. Veh. J., vol. 16, no. 11, Nov. 2025, doi: 10.3390/wevj16110620.
[9] M. Gomaa, R. Mahmoud, and A. Sarhan, “A CNN-LSTM-based Deep Learning Approach for Driver Drowsiness Prediction,” J. Eng. Res., vol. 6, Aug. 2022, doi: 10.21608/erjeng.2022.141514.1067.
[10] P. Mukherjee and A. Roy, “A novel deep learning‐based technique for driver drowsiness detection,” Hum. Factors Ergon. Manuf. Serv. Ind., vol. 34, Sep. 2024, doi: 10.1002/hfm.21056.
[11] S. Ebrahimian, A. Nahvi, M. Tashakori, H. Salmanzadeh, O. Mohseni, and T. Leppänen, “Multi-Level Classification of Driver Drowsiness by Simultaneous Analysis of ECG and Respiration Signals Using Deep Neural Networks,” Int. J. Environ. Res. Public Health, vol. 19, no. 17, Sep. 2022, doi: 10.3390/ijerph191710736.
[12] M. Ahmed, S. Masood, M. Ahmad, and A. Abd El-Latif, “Intelligent Driver Drowsiness Detection for Traffic Safety Based on Multi CNN Deep Model and Facial Subsampling,” IEEE Trans. Intell. Transp. Syst., vol. PP, pp. 1–10, Dec. 2021, doi: 10.1109/TITS.2021.3134222.
[13] Y. Tian, Q. Ye, and D. Doermann, “YOLOv12: Attention-Centric Real-Time Object Detectors,” Cornelll Univ., vol. 1, Feb. 2025, [Online]. Available: http://arxiv.org/abs/2502.12524
[14] C. Xu, W. Huang, J. Liu, and L. Li, “Detecting Driver Drowsiness Using Hybrid Facial Features and Ensemble Learning,” Inf., vol. 16, no. 4, Apr. 2025, doi: 10.3390/info16040294.
[15] S. Chen, Z. Wang, and W. Chen, “Driver drowsiness estimation based on factorized bilinear feature fusion and a long-short-term recurrent convolutional network,” Inf., vol. 12, no. 1, pp. 1–15, Jan. 2021, doi: 10.3390/info12010003.
[16] S. Hosamani and S. Nandyal, “An ensemble learning model for driver drowsiness detection and accident prevention using the behavioral features analysis,” Int. J. Intell. Comput. Cybern., vol. ahead-of-print, Oct. 2021, doi: 10.1108/IJICC-07-2021-0139.
[17] B. Akrout and S. Fakhfakh, “How to Prevent Drivers before Their Sleepiness Using Deep Learning-Based Approach,” Electron., vol. 12, no. 4, Feb. 2023, doi: 10.3390/electronics12040965.
[18] V. Ch, U. S. Reddy, and V. KishoreKolli, “Deep CNN: A Machine Learning Approach for Driver Drowsiness Detection Based on Eye State,” Rev. d’Intelligence Artif., vol. 33, pp. 461–466, Dec. 2019, doi: 10.18280/ria.330609.
[19] S. H. Al-Gburi et al., “EffRes-DrowsyNet: A Novel Hybrid Deep Learning Model Combining EfficientNetB0 and ResNet50 for Driver Drowsiness Detection,” Sensors, vol. 25, no. 12, Jun. 2025, doi: 10.3390/s25123711.
[20] A. Sedik, M. Marey, and H. Mostafa, “An Adaptive Fatigue Detection System Based on 3D CNNs and Ensemble Models,” Symmetry (Basel)., vol. 15, no. 6, Jun. 2023, doi: 10.3390/sym15061274.
[21] S. Sheykhivand, T. Y. Rezaii, S. Meshgini, S. Makoui, and A. Farzamnia, “Developing a Deep Neural Network for Driver Fatigue Detection Using EEG Signals Based on Compressed Sensing,” Sustain., vol. 14, no. 5, Mar. 2022, doi: 10.3390/su14052941.
[22] E. Quiles-Cucarella, J. Cano-Bernet, L. Santos-Fernández, C. Roldán-Blay, and C. Roldán-Porta, “Multi-Index Driver Drowsiness Detection Method Based on Driver’s Facial Recognition Using Haar Features and Histograms of Oriented Gradients,” Sensors, vol. 24, no. 17, Sep. 2024, doi: 10.3390/s24175683.
[23] S. Essahraui et al., “Real-Time Driver Drowsiness Detection Using Facial Analysis and Machine Learning Techniques,” Sensors, vol. 25, no. 3, Feb. 2025, doi: 10.3390/s25030812.
[24] Y. Albadawi, M. Takruri, and M. Awad, “A Review of Recent Developments in Driver Drowsiness Detection Systems,” Mar. 01, 2022, MDPI. doi: 10.3390/s22052069.
[25] H. U. R. Siddiqui et al., “Non-invasive driver drowsiness detection system,” Sensors, vol. 21, no. 14, Jul. 2021, doi: 10.3390/s21144833.
[26] Y. Ed-Doughmi, N. Idrissi, and Y. Hbali, “Real-time system for driver fatigue detection based on a recurrent neuronal network,” J. Imaging, vol. 6, no. 3, 2020, doi: 10.3390/jimaging6030008.
[27] S. Nandyal and Sharanabasappa, “Deep ResNet 18 and enhanced firefly optimization algorithm for on-road vehicle driver drowsiness detection,” J. Auton. Intell., vol. 7, no. 3, 2024, doi: 10.32629/jai.v7i3.975.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 J-INTECH
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
