Driver State Monitoring Using Pose Estimation: Detecting Fatigue, Stress, and Emotional States for Safer Roads
Driving under fatigue, stress, or emotional impairment poses significant risks to road safety.This paper proposes a custom pose estimation framework designed to detect driver states, such as fatigue and stress, by analyzing body posture, head pose, and gesture dynamics.Using a novel deep learning approach trained on diverse driving scenarios, the model identifies physiological and behavioral markers associated with impaired states.Unlike existing methods, this system integrates pose estimation with emotional and movement analysis, enabling robust performance in challenging conditions, including poor lighting and occlusions.
Authors
- Andi Prademon Yunus (ORCID: https://orcid.org/0000-0002-1185-5763)
- Shady Mohamed (ORCID: https://orcid.org/0000-0002-8851-1635)
- Xinjie Deng
- Takao Ito (ORCID: https://orcid.org/0000-0001-6224-5204)
- Yit Hong Choo (ORCID: https://orcid.org/0000-0002-2490-1925)
- Hao Feng Chan
- Zheng Cai (ORCID: https://orcid.org/0009-0002-1775-5752)
- Dexter Sing Fong Leong
- Wui Chung Alton Chau
Institutions
- Hiroshima University (JP)
- Deakin University (AU)
- Telkom University (ID)
Publication Details
- Journal
- Proceedings of International Conference on Artificial Life and Robotics
- Published
- 2025-02-13
- DOI
- https://doi.org/10.5954/icarob.2025.os26-1
- Primary Topic
- Sleep and Work-Related Fatigue
- Type
- article
- Field-Weighted Citation Impact
- 0.00