APLIKASI ANDROID DETEKSI SUPIR MENGANTUK PADA PENGENDARA MOBIL BERBASIS FACE RECOGNITION

  • Stefanus Wijaya Fakultas Teknik Universitas Surabaya, Raya Kalirungkut, Surabaya 60293
  • Nemuel Daniel Pah Fakultas Teknik Universitas Surabaya, Raya Kalirungkut, Surabaya 60293
  • Rafina Destiarti Ainul Fakultas Teknik Universitas Surabaya, Raya Kalirungkut, Surabaya 60293
Abstract Views: 20 times
PDF Downloads: 27 times
Keywords: drowsiness detection, android, haar-cascade classifier, deteksi kantuk, android, haar-cascade classifier

Abstract

Abstract—Humans have always developed technology to make life easier. One of the technological developments made is land transportation. In the development of land transportation is also accompanied by an increase in the accident rate of drivers due to drowsiness. This drowsiness detection system is made using an Android-based smartphone where this technology is almost used in various walks of life so that it can help to provide direct warnings to drivers who are drowsy. The system uses Haar-Cascade Classifier to detect faces and eyes and utilizes the training model to determine whether the person is sleepy or not. System development using Android Studio with Java and Python programming languages. Based on system testing on 9 different faces with 120 frame samples per face, with 40 cm in distance, and an angle of 20⁰, the accuracy result is 85% during the day with a light intensity of 725 lux.

Keywords: drowsiness detection, android, haar-cascade classifier

 

Abstrak— Manusia selalu mengembangkan teknologi untuk mempermudah hidupnya. Salah satu perkembangan teknologi yang dibuat adalah transportasi darat. Dalam perkembangan transportasi darat ini juga ditemani dengan bertambahnya tingkat kecelakaan para pengemudi akibat mengantuk. Sistem pendeteksi kantuk ini dibuat dengan menggunakan smartphone berbasis Android dimana teknologi ini hampir digunakan diberbagai lapisan masyarakat sehingga dapat membantu untuk memberikan peringatan secara langsung pada pengemudi yang sedang mengantuk. Sistem yang dibuat menggunakan Haar-Cascade Classifier untuk mendeteksi wajah dan juga mata dan memanfaatkan model hasil pelatihan untuk menentukan apakah orang tersebut sedang mengantuk atau tidak. Pembuatan sistem dengan menggunakan Android Studio dengan bahasa pemrograman Java dan Python. Berdasarkan pengujian sistem pada 9 wajah berbeda dengan 120 sampel frame per wajah, jarak 40 cm, dan sudut 20⁰ mendapatkan hasil akurasi sebesar 85% pada siang hari dengan intensitas cahaya sebesar 725 lux.

Kata kunci: deteksi kantuk, android, haar-cascade classifier

Downloads

Download data is not yet available.

References

Albadawi, Y., Takruri, M., & Awad, M. (2022). A Review of Recent Developments in Driver Drowsiness Detection Systems. Sensors, 22(5), 1–41. https://doi.org/10.3390/s22052069
ASGHAR, M. H. (2022). OACE - Open and Close Eyes Dataset. Kaggle. https://www.kaggle.com/datasets/muhammadhananasghar/oace-open-and-close-eyes- dataset
Behera, G. S. (2020). Face Detection with Haar Cascade. Towards Data Science. https://towardsdatascience.com/face-detection-with-haar-cascade-727f68dafd08
Databoks. (2018). Sepanjang 2017 Terjadi 98 Ribu Kali Kecelakaan Lalu Lintas. Databoks. https://databoks.katadata.co.id/datapublish/2018/09/21/sepanjang-2017-terjadi-98- ribu-kali-kecelakaan-lalu-lintas
Encyclopedia.com. (n.d.). Facial Recognition. Retrieved June 22, 2022, from https://www.encyclopedia.com/science/encyclopedias-almanacs-transcripts-and- maps/facial-recognition
Ghoddoosian, R., Galib, M., & Athitsos, V. (2019). A realistic dataset and baseline temporal model for early drowsiness detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2019-June, 178–187. https://doi.org/10.1109/CVPRW.2019.00027
Petrellis, N., Zogas, S., Christakos, P., Mousouliotis, P., Keramidas, G., Voros, N., & Antonopoulos, C. (2021). Software Acceleration of the Deformable Shape Tracking Application: How to eliminate the Eigen Library Overhead. ACM International Conference Proceeding Series, November, 51–57. https://doi.org/10.1145/3501774.3501782
Runtsch, R. (2022). The Most Popular Computer Programming Languages of 2022. Medium. https://rruntsch.medium.com/most-popular-computer-programming-languages-in-2022- 23e0f523391
Samat, S. (2022). Living in a multi-device world with Android. https://blog.google/products/android/io22-multideviceworld/
Published
2023-11-30
Issue
Vol. 12 No. 1 (2023): Calyptra : Jurnal Ilmiah Mahasiswa Universitas Surabaya (November)
Section
BIDANG TEKNIK
Copyright (c) 2023 THE AUTHOR(S) Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons License

  • Articles published in CALYPTRA are licensed under a Creative Commons Attribution-ShareAlike 4.0 International license. You are free to copy, transform, or redistribute articles for any lawful purpose in any medium, provided you give appropriate credit to the original author(s) and the journal, link to the license, indicate if changes were made, and redistribute any derivative work under the same license.
  • Copyright on articles is retained by the respective author(s), without restrictions. A non-exclusive license is granted to CALYPTRA to publish the article and identify itself as its original publisher, along with the commercial right to include the article in a hardcopy issue for sale to libraries and individuals.
  • By publishing in CALYPTRA, authors grant any third party the right to use their article to the extent provided by the Creative Commons Attribution-ShareAlike 4.0 International license.