Analysis of Driver Drowsiness Detection System Based on Landmarks and MediaPipe

  • Fawaidul Badri 1Informatics Department, Universitas Islam Malang
  • Sulistya Umie Ruhmana Sari Department of Tadris Mathematics, Universitas Islam Negeri Maulana Malik Ibrahim Malang
  • Shipun Anuar Bin Hamzah Electrical and Electronic Engineering Department, Universiti Tun Hussein Onn Malaysia
https://doi.org/10.25139/inform.v10i1.9325
Abstract views: 177 , PDF downloads: 93
Keywords: Drowsiness Detection, Landmarks, MediaPipe, Driving Safety, Eye Blink Analysis

Abstract

Driver drowsiness is one of the leading causes of traffic accidents, especially during long-distance journeys. This study developed a detection system based on landmarks and the MediaPipe framework to analyze drowsiness through eye blink duration. The system employs coordinate point initialization using regression trees to accurately detect objects, such as eyes. The research data consists of 30 videos, each lasting 30 seconds, collected from four Trans Java bus drivers. The videos were extracted to identify facial detection histograms and analyzed based on eye blink duration. The testing results showed a detection accuracy of 81% with an error rate of 19% for distances of 10 to 100 cm, while testing with 30 videos achieved an average accuracy of 88.745% and a Mean Squared Error (MSE) of 7.615%. The test results show that CNN outperforms MediaPipe in detecting drowsiness, with a higher average accuracy of 76.79% compared to 73.83% and a lower MSE value of 47.33 compared to 48.27. CNN is also more consistent in handling extreme lighting variations, while MediaPipe excels in processing efficiency, making it suitable for devices with limited resources. This study demonstrates that the landmarks and MediaPipe-based system effectively and innovatively detects drowsiness, offering a solution to improve driver safety during trips.

Author Biography

Fawaidul Badri, 1Informatics Department, Universitas Islam Malang

Academic Qualification:

  • Graduate, Department of Electrical Engineering, Faculty of Industrial Technology ITS Surabaya Indonesia
  • Undergraduate, Computer Science, Universitas Trunojoyo, Indonesia

Field of expertises:

  • Image Processing
  • Vision Computer
  • Artificial Intelligence
  • Pattern Recognition

Scopus (Scopus H-Index= 0)

Google Scholar (Scholar H-Index= 1)

Sinta Profile

 

References

M. A. Mohamed, Y. S. Singh, and N. V. S. R. Reddy, "Driver Drowsiness Detection by Applying Deep Learning Techniques to Sequences of Images," Int. J. of Veh. Technol., vol. 2023, pp. 1-10, Jan. 2023.

X. Li, Y. Zhang, and J. Wang, "Real-Time Machine Learning-Based Driver Drowsiness Detection Using Visual Features," IEEE Trans. Intell. Transp. Syst., vol. 24, no. 4, pp. 987-997, Apr. 2023.

H. Liu and Y. Li, "Driver Drowsiness Detection Using MediaPipe in Python," LearnOpenCV, 2023.

J. T. Gao, X. Li, and Z. Y. Zhang, "IoT-Assisted Automatic Driver Drowsiness Detection through Facial Movement Analysis," IEEE Internet Things J., vol. 10, no. 12, pp. 10003-10011, Dec. 2023.

R. Mohana and P. Sheela, "An Efficient Approach for Detecting Driver Drowsiness Based on Deep Learning," Appl. Sci., vol. 11, no. 8, pp. 441-452, Apr. 2023.

A. R. Verma, R. Singh, and M. B. Roy, "Real-Time Driver Drowsiness Detection with Deep Learning and Eye-Gaze Estimation," IEEE Trans. Comput. Vis. Pattern Recognit., vol. 31, no. 4, pp. 174-182, Mar. 2023.

P. J. Tharun and S. K. Saravanan, "A Robust Approach to Drowsiness Detection Using Facial Expression Recognition," Comp. Vision & Pattern Rec., vol. 15, no. 6, pp. 123-130, Jun. 2023.

A. B. Rajan, T. R. Reddy, and D. B. Pradeep, "Driver Alert System Using Eye Blink and Yawn Detection," Proc. Int. Conf. Pattern Recognit., pp. 195-200, Oct. 2023.

B. Y. Zhuang, M. H. Xu, and L. R. Tan, "Deep Learning for Drowsiness Detection in Driver Assistance Systems," Appl. Neurocomputing, vol. 51, no. 1, pp. 32-39, Jan. 2023.

S. M. Kumar and P. B. Rathi, "Comparative Analysis of Machine Learning Models for Driver Drowsiness Detection," J. Pattern Recognit. Sci., vol. 8, no. 5, pp. 101-110, May 2023.

K. L. Aditya, T. N. Sharma, and R. V. Kumar, "Driver Drowsiness Detection Using Facial Landmark Points and Machine Learning," IEEE Conf. Image Process., pp. 401-409, Mar. 2023.

J. P. Tan, D. K. Chu, and L. G. Zhao, "Facial Landmark Detection for Drowsiness Detection Using Convolutional Neural Networks," IEEE Trans. Bioinformatics, vol. 12, no. 6, pp. 444-453, Jun. 2023.

H. Q. Xin and W. Y. Ma, "Predicting Driver Fatigue Using Deep Learning-Based Facial Analysis," Int. J. Comput. Vision Image Process., vol. 16, no. 4, pp. 101-108, Jul. 2023.

M. X. Liang and Q. L. Liu, "Eye Tracking for Drowsiness Detection: A Real-Time Approach," IEEE Sensors J., vol. 22, no. 3, pp. 1325-1330, Mar. 2023.

Y. P. Zhang, M. T. Wu, and X. Z. Zhang, "Towards Real-Time Driver Drowsiness Detection Using MediaPipe and OpenCV," Sensors, vol. 23, no. 7, pp. 1156-1165, Jul. 2023.

L. P. Zhao, C. M. Chang, and B. P. Choi, "Facial Landmark Analysis for Driver Drowsiness Detection," J. Safety Res., vol. 42, pp. 74-81, Aug. 2023.

M. S. Lee, P. H. K. Wang, and X. M. Chen, "Deep Learning Approaches for Driver Drowsiness Detection Using Image Processing," Appl. Intell., vol. 48, no. 5, pp. 128-139, May 2023.

R. K. Liang and J. H. Yu, "Real-Time Monitoring of Driver Drowsiness Using a Webcam and Facial Landmark Detection," IEEE Access, vol. 10, pp. 23157-23164, Apr. 2023.

T. M. Liu, J. Y. Cheng, and W. Z. Xu, "FaceMesh: A Vision-Based Solution for Real-Time Drowsiness Detection," Pattern Recognit. Lett., vol. 47, pp. 123-130, Mar. 2023.

K. X. Zhao, F. H. Chen, and L. Z. Wei, "Multimodal Drowsiness Detection System Using Facial Landmark Features and EEG Data," Sensors, vol. 23, no. 11, pp. 2519-2530, Nov. 2023.

D. Kurniawan and A. Armansyah, "Classification of Crude Palm Oil Quality Using Artificial Neural Networks Based on Chemical Components," Inf. J. Ilm. Bid. Teknol. Inf. dan Komun., vol. 9, no. 2, pp. 166–170, 2024, doi: 10.25139/inform.v9i2.8433.

F. Eka Khoirunisa and N. Charibaldi, "Effect of Using GLCM and LBP+HOG Feature Extraction on SVM Method in Classification of Human Skin Disease Type," Inf. J. Ilm. Bid. Teknol. Inf. dan Komun., vol. 9, no. 2, pp. 145–150, 2024, doi: 10.25139/inform.v9i2.8275.

A. Sanjaya, E. Setyati, and H. Budianto, "Modeling of Convolutional Neural Network Architecture for Recognizing The Pandava Mask," Inf. J. Ilm. Bid. Teknol. Inf. dan Komun., vol. 5, no. 2, pp. 99–103, 2020.

M. Suyuti and E. Setyati, "Pneumonia Classification of Thorax Images using Convolutional Neural Networks," J. Inf., vol. 5, no. 2, p. 62, 2020, doi: 10.25139/inform.v0i1.2707.

Published
2025-01-06
How to Cite
Badri, F., Ruhmana Sari, S. U., & Bin Hamzah, S. A. (2025). Analysis of Driver Drowsiness Detection System Based on Landmarks and MediaPipe. Inform : Jurnal Ilmiah Bidang Teknologi Informasi Dan Komunikasi, 10(1), 21-28. https://doi.org/10.25139/inform.v10i1.9325
Issue
Vol. 10 No. 1 (2025)
Section
Articles

Copyright (c) 2025 Fawaidul Badri, Sulistya Umie Ruhmana Sari, Shipun Anuar Bin Hamzah

Creative Commons License

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

Authors who publish with Inform: Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal. 

  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.

  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.