Sistem Deteksi Kantuk Pengemudi Berbasis Dlib Facial Landmark dan Rasio Kedipan Mata Menggunakan Opencv Secara Real-Time
Keywords:
Computer Vision, Driver Monitoring, Facial Landmark, Kantuk, Rasio Kedipan MataAbstract
Kecelakaan lalu lintas akibat kondisi mengantuk saat berkendara merupakan permasalahan keselamatan yang serius dan belum terselesaikan secara tuntas. Penelitian ini mengimplementasikan sistem deteksi kantuk pengemudi secara real-time berbasis kecerdasan buatan dengan memanfaatkan OpenCV untuk akuisisi video dari webcam dan pustaka Dlib untuk ekstraksi 68 titik facial landmark. Kontribusi utama penelitian ini adalah pengembangan sistem tiga-kelas (active, drowsy, sleep) menggunakan mekanisme pencacah frame dengan ambang batas empat frame berturut-turut, yang beroperasi tanpa GPU khusus disertai alarm audio otomatis. Berbeda dengan penelitian terdahulu yang umumnya hanya membedakan dua kondisi, sistem ini menambahkan kelas 'active' sebagai konfirmasi eksplisit kondisi pengemudi yang waspada. Pengujian terhadap 30 percobaan menghasilkan akurasi 90%, recall rata-rata 0,90, dan rata-rata waktu respons alarm 0,65 detik. Hasil ini menunjukkan bahwa pendekatan berbasis rasio keterbukaan mata dan pencacah frame efektif sebagai prototipe sistem deteksi kantuk ringan syang dapat direproduksi pada perangkat komputasi konvensional.
Downloads
References
[1] World Health Organization, "Global Status Report on Road Safety 2023," WHO Press, Geneva, 2023.
[2] Pusiknas Bareskrim Polri, "Statistik Kecelakaan Lalu Lintas," Kepolisian Negara Republik Indonesia, 2022. [Online]. Available: https://pusiknas.polri.go.id/laka_lantas
[3] A. A. Doudou, A. Bouabdallah, and V. Berge-Cherfaoui, "Driver Drowsiness Measurement Technologies: Current Research, Market Solutions and Challenges," Int. J. Intell. Transp. Syst. Res., vol. 18, no. 2, pp. 297–319, 2020.
[4] A. Sahayadhas, K. Sundaraj, and M. Murugappan, "Detecting Driver Drowsiness Based on Sensors: A Review," Sensors, vol. 12, no. 12, pp. 16937–16953, 2012.
[5] M. Ramzan, H. U. Khan, S. M. Awan, A. Ismail, M. Ilyas, and A. Mahmood, "A Survey on State-of-the-Art Drowsiness Detection Techniques," IEEE Access, vol. 7, pp. 61904–61919, 2019. DOI: 10.1109/ACCESS.2019.2914373
[6] T. Soukupova and J. Cech, "Real-time Eye Blink Detection Using Facial Landmarks," in Proc. 21st Comput. Vis. Winter Workshop, 2016, pp. 1–8.
[7] M. Ngxande, J.-R. Tapamo, and M. Burke, "Driver Drowsiness Detection Using Behavioral Measures and Machine Learning Techniques: A Review of State-of-Art Techniques," in Proc. 2017 Pattern Recognit. Assoc. South Africa Robot. Mechatronics (PRASA-RobMech), 2017, pp. 156–161. DOI: 10.1109/RoboMech.2017.8261140
[8] R. Jabbar, M. Shinoy, M. Kharbeche, K. Al-Khalifa, M. Krichen, and K. Barkaoui, "Driver Drowsiness Detection Model Using Convolutional Neural Networks Techniques for Android Application," in Proc. IEEE Int. Conf. Informatics, IoT, and Enabling Technol. (ICIoT), 2020, pp. 687–692. DOI: 10.1109/ICIoT48696.2020.9089594
[9] R. M. Nurhakim and J. Nabilah, "Sleep Detector App – Gen-Z Application Based," GitHub, 2022. [Online]. Available: https://github.com/romeoalphamiqe/si_paling_orbit
[10] G. Bradski and A. Kaehler, Learning OpenCV 4, 2nd ed. Sebastopol: O'Reilly Media, 2019.
[11] D. E. King, "Dlib-ml: A Machine Learning Toolkit," J. Mach. Learn. Res., vol. 10, pp. 1755–1758, 2009.
[12] A. Rosebrock, "Detect Eyes, Nose, Lips, and Jaw with Dlib, OpenCV, and Python," PyImageSearch, 2017.
[13] C. Sagonas, G. Tzimiropoulos, S. Zafeiriou, and M. Pantic, "300 Faces in-the-Wild Challenge," in Proc. IEEE ICCVW, 2013, pp. 397–403.
[14] Y. Albadawi, M. Takruri, and M. Awad, "A Review of Recent Developments in Driver Drowsiness Detection Systems," Sensors, vol. 22, no. 5, art. 2069, 2022. DOI: 10.3390/s22052069
Downloads
Published
Issue
Section
License
Copyright (c) 2026 M Ikhsan, Siti Nurjanah, Dila Marta Putri, Ika Mayla Sari, Hudaya Muna Putra, Ririn Violina, Radinal Dwiki Novendra, Yoan Purbolingga (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
