Driver Drowsiness Detection Using Computer Vision with Adaptive Methods on Android

• Paulo Roberto Varjal de Melo UPE
• Lucas Maciel Sousa UPE
• Denilson José do Bom Jesus Silva de Lima UPE
• Fernando Buarque de Lima Neto UPE

DOI: https://doi.org/10.5753/eniac.2026.31248

Resumo

Traffic accidents associated with driver drowsiness represent a relevant challenge for road safety. This work presents an Android system for real-time drowsiness detection, with on-device processing, using the smartphone’s front camera. The approach integrates multiple computer vision indicators (EAR, MAR, PERCLOS, blink frequency, blink duration, and yawn frequency), where EAR and MAR drive blink/eye-closure and yawn event detectors whose outputs feed the four fused metrics (PERCLOS, blink frequency, blink duration, and yawn frequency). The system also features user personalization, based on initial calibration and the use of data labeled by the user to adjust individual reference parameters. An evaluation with 40 videos from the UTA-RLDD dataset, corresponding to 20 users, using a temporal protocol, obtained accuracies of 97.1% for the alert state and 98.9% for the drowsy state, demonstrating the technical feasibility of the mobile application.

Referências

Abe, T. (2023). Perclos-based technologies for detecting drowsiness: current evidence and future directions. Sleep Advances: A Journal of the Sleep Research Society, 4.

Albadawi, A., Nigam, A., Guo, W., Alam, M. S., Ouyang, J., and Wang, H. (2022). A review of recent driver drowsiness detection systems using computer vision. Sensors, 22(13):5064.

Arakawa, T. (2021). Trends and future prospects of the drowsiness detection and estimation technology. Sensors, 21(23):7921.

Bajaj, J. S., Kumar, N., and Kaushal, R. K. (2021). Comparative study to detect driver drowsiness. In 2021 International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), pages 678–683, Greater Noida, India.

Baul, S., Rana, M. R., Trisna, N. J., and Alam, F. B. (2025). Development of a real-time driver’s drowsiness detection system using MediaPipe Face Mesh. International Journal of Engineering and Manufacturing (IJEM), 15(5):46–57.

Bergasa, L. M., Nuevo, J., Sotelo, M. A., Barea, R., and López, M. E. (2006). Real-time system for monitoring driver vigilance. IEEE Transactions on Intelligent Transportation Systems, 7(1):63–77.

Bittencourt, L. R. A., Silva, R. S., Santos, R. F., Pires, M. L. N., and Mello, M. T. (2005). Sonolência excessiva. Revista Brasileira de Psiquiatria, 27(Supl I):16–21.

Das, S. and Bhargava, R. (2023). Vision-based fatigue detection in drivers using multi-facial feature fusion. In 2023 15th International Conference on Developments in eSystems Engineering, pages 375–380. IEEE.

Dasgupta, A., Rahman, D., and Routray, A. (2019). A smartphone-based drowsiness detection and warning system for automotive drivers. IEEE Transactions on Intelligent Transportation Systems, 20:4045–4054.

Dinges, D. F., Mallis, M. M., Maislin, G., Powell, J. W., and Grace, R. (1998). Perclos: A valid psychophysiological measure of alertness as assessed by psychomotor vigilance. Technical Report FHWA-MCRT-98-006, Federal Highway Administration (FHWA), Washington, DC.

El-Nabi, S. A., El-Shafai, W., El-Rabaie, E.-S. M., Ramadan, K. F., El-Samie, F. E. A., and Mohsen, S. (2024). Machine learning and deep learning techniques for driver fatigue and drowsiness detection: a review. Multimedia Tools and Applications, 83(3):9441–9477.

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(3):812.

Federal Highway Police (Brazil) (2026). PRF open data. [link]. Accessed: 22 Jun. 2026.

Florez, R., Palomino-Quispe, F., Alvarez, A. B., Coaquira-Castillo, R. J., and Herrera-Levano, J. C. (2024). A real-time embedded system for driver drowsiness detection based on visual analysis of the eyes and mouth using convolutional neural network and mouth aspect ratio. Sensors, 24(19):6261.

Ghoddoosian, R., Galib, M., and Athitsos, V. (2019). A realistic dataset and baseline temporal model for early drowsiness detection. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 178–187, Long Beach, CA, USA.

Google (2022). Model card: MediaPipe Face Mesh V2. [link]. Accessed: 22 Jun. 2026.

Google AI Edge (2025). Face Landmark Detection Guide. [link]. Accessed: 22 Jun. 2026.

Häkkänen, H., Summala, H., Partinen, M., Tiihonen, M., and Silvo, J. (1999). Blink duration as an indicator of driver sleepiness in professional bus drivers. Sleep, 22(6):798–802.

Instituto de Pesquisa Econômica Aplicada (2020). Custos dos acidentes de trânsito no brasil. Technical report, Instituto de Pesquisa Econômica Aplicada, Brasília. [link]. Accessed: 22 Jun. 2026.

Jeong, M., Kim, D., Park, S., and Paik, J. (2022). Drowsy status monitoring system based on face feature analysis. In 2022 International Conference on Electronics, Information, and Communication (ICEIC), pages 1–4, Jeju, Korea, Republic of.

Joshy, A. J. and Hwang, J. T. (2024). PySLSQP: A transparent Python package for the SLSQP optimization algorithm modernized with utilities for visualization and post-processing. Journal of Open Source Software, 9(103):7246.

Kashevnik, A., Lashkov, I., and Gurtov, A. (2020). Methodology and mobile application for driver behavior analysis and accident prevention. IEEE Transactions on Intelligent Transportation Systems, 21(6):2427–2436.

Kolus, A. (2024). A systematic review on driver drowsiness detection using eye activity measures. IEEE Access, 12:97969–97993.

Kraft, D. (1994). Algorithm 733: TOMP—Fortran modules for optimal control calculations. ACM Transactions on Mathematical Software, 20(3):262–281.

Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.-L., Yong, M., Lee, J., Chang, W.-T., Hua, W., Georg, M., and Grundmann, M. (2019). MediaPipe: A framework for perceiving and processing reality. In Third Workshop on Computer Vision for AR/VR at IEEE Computer Vision and Pattern Recognition (CVPR) 2019.

Schleicher, R., Galley, N., Briest, S., and Galley, L. (2008). Blinks and saccades as indicators of fatigue in sleepiness warnings: Looking tired? Ergonomics, 51(7):982–1010.

Singh, N. T., Saurav, Pathak, N., Raizada, A., and Shukla, S. (2023). Real-time driver drowsiness detection system using cascaded convnet framework. In 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS), pages 828–833, Coimbatore, India.

Soukupová, T. and Čech, J. (2016). Real-time eye blink detection using facial landmarks. In Proceedings of the 21st Computer Vision Winter Workshop (CVWW), pages 1–8.

Tamanani, R., Muresan, R., and Al-Dweik, A. (2021). Estimation of driver vigilance status using real-time facial expression and deep learning. IEEE Sensors Letters, 5(5):1–4.

World Health Organization (2024). Global status report on road safety 2023: Country and territory profiles. [link]. Accessed: 22 Jun. 2026.

World Health Organization (2026). Road traffic injuries. [link]. Accessed: 22 Jun. 2026.

Yang, H., Liu, L., Min, W., Yang, X., and Xiong, X. (2021). Driver yawning detection based on subtle facial action recognition. IEEE Transactions on Multimedia, 23:572–583.