DETEKSI KANTUK PADA PENGEMUDI BUS TRANS METRO BANDUNG DENGAN PENDEKATAN RUMUS EYE ASPECT RATIO
Abstract
Kecelakaan lalu lintas merupakan kejadian yang paling umum terjadi di dunia, terutama Indonesia. Kecelakaan lalu lintas banyak disebabkan oleh beberapa faktor, salah satunya yaitu rasa kantuk pengemudi. Rasa kantuk pengemudi sering timbul ketika pengemudi mulai kelelahan, maupun ketika perjalanan terasa membosankan seperti perjalanan jauh maupun ketika terlalu lama berada dalam kemacetan. Pada saat ini, belum banyak diaplikasikan sistem pendeteksi rasa kantuk pengemudi kendaraan. Pada perjalanan jauh, pengemudi bus harus selalu ditemani seorang ‘kernet’ atau pembantu pengemudi saat perjalanan, yang kurang efektif karena jika ‘kernet’ tersebut tertidur maka tidak ada yang memantau rasa kantuk pengemudi. Eye Aspect Ratio (EAR) bekerja dengan menghitung jarak Euclidean antar 6 titik facial landmarks pada masing-masing mata. Akurasi sistem akan diuji dengan mengakuisisi wajah pengemudi bus TMB. Keakuratan sistem akan didapatkan jika pengemudi terdeteksi mengantuk. Dari hasil pengujian, didapatkan nilai threshold EAR terbaik yaitu x dengan akurasi sistem x%. Setelah dilakukan pengujian akurasi, dilanjutkan dengan mencoba deteksi secara real-time. Hasilnya, posisi wajah dan intensitas cahaya berpengaruh terhadap pendeteksian.
Kata kunci: deteksi kantuk, eye aspect ratio, facial landmarks, real-time, Trans Metro Bandung (TMB).
References
National Highway Traffic Safety Administration, "Traffic Safety Facts", 2017.
B. Sikka, Elements of Deep Learning for Computer Vision, First. New Delhi: BPB Publications, 2021.
J. Howse and J. Minichino, Learning OpenCV 4 Computer Vision with Python 3, Third. London, UK: Packt Publishing, 2020.
V. Kazemi and J. Sullivan, "One millisecond face alignment with an ensemble of regression trees," in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Sep. 2014, pp. 1867-1874. doi: 10.1109/CVPR.2014.241.
G. Prihartanto, "Implementasi Sistem Pendeteksi Kantuk pada Pengemudi menggunakan Metode Dlib", Repsitory.telkomuniversity.ac.id, 2019.
Z. H. Feng, J. Kittler, M. Awais, P. Huber, and X. J. Wu, "Face Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wild," in IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Aug. 2017, vol. 2017-July, pp. 2106-2111. doi: 10.1109/CVPRW.2017.262.
A. Saeed, A. Al-Hamadi, and A. Ghoneim, "Head Pose Estimation on Top of Haar-Like Face Detection: A Study Using the Kinect Sensor," Sensors (Switzerland), vol. 15, no. 9, pp. 20945-20966, Aug. 2015, doi: 10.3390/s150920945.
C. Dewi, R. C. Chen, X. Jiang, and H. Yu, "Adjusting Eye Aspect Ratio for Strong Eye Blink Detection Based on Facial Landmarks," PeerJ Comput Sci, vol. 8, Apr. 2022, doi: 10.7717/peerj-cs.943.
A. Kuwahara, K. Nishikawa, R. Hirakawa, H. Kawano, and Y. Nakatoh, "Eye fatigue estimation using blink detection based on Eye Aspect Ratio Mapping(EARM)," Cognitive Robotics, vol. 2, pp. 50-59, 2022, doi: 10.1016/j.cogr.2022.01.003.
M. Cakar, K. YILDIZ, and O. DEMIR, "Thumbnail Selection with Convolutional Neural Network Based on Emotion Detection," International Journal of Advances in Engineering and Pure Sciences, Dec. 2021, doi: 10.7240/jeps.900561.
B. Fernando, A. Sridhar, S. Talebi, J. Waczak, and D. J. Lary, "Unsupervised Blink Detection Using Eye Aspect Ratio Values," Mar. 2022, doi: 10.20944/preprints202203.0200.v1.
H. Dalianis, Clinical text mining: Secondary use of electronic patient records. Springer International Publishing, 2018. doi: 10.1007/978-3-319-78503-5.
Downloads
Additional Files
Published
Issue
Section
License
Authors who publish with this journal agree to the following terms:
(1) Copyright of the published articles will be transferred to the journal as the publisher of the manuscripts. Therefore, the author confirms that the copyright has been managed by the publisher.
(2) Publisher of TELKATTKA is Openlibrary Telkom University
(3) The copyright follows Creative Commons Attribution–ShareAlike License (CC BY SA): This license allows to Share — copy and redistribute the material in any medium or format, Adapt — remix, transform, and build upon the material, for any purpose, even commercially.
