A Multi-Cue Spatiotemporal Model for Real-Time Driver Drowsiness Detection

DOI

10.2991/978-94-6239-707-1_25How to use a DOI?

Keywords

Driver drowsiness; Multi-cue; Driver fatigue

Abstract

Driver drowsiness is a critical and persistent concern on modern roadways, and most of the accidents due to drowsiness can be avoided by detecting them in time. Previous works mostly rely on either a single-parameter cue, like thresholds on blink frequency or eye aspect ratio, or head-pose deviations. However, such isolated features often fail when these channels are subjected to real-world challenges like changes in illuminations, occlusions, and differences in individual behavior. This paper investigates early behavioral clues that indicate the onset of drowsiness in real-time to warn the driver well before attention decreases or control is lost. In this paper, we proposed a lightweight multi-cue detection model that overcomes single-feature dependency. The proposed method fuses MediaPipe Face Mesh with robust indicators, Temporal Landmark-based Eye Aspect Ratio for illumination-aware eye aspect analysis, Blink Morphology withClosed-eye State Index and Head Pose and Spatial Dynamics. The fusion of this cue significantly enhances reliability under diverse driving scenarios, including low lighting and dynamic head movement.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sneha Barmaiya
AU  - Aman Kumar Patel
AU  - Megha Patidar
AU  - Anand Singh Jalal
PY  - 2026
DA  - 2026/06/18
TI  - A Multi-Cue Spatiotemporal Model for Real-Time Driver Drowsiness Detection
BT  - Proceedings of the International Conference on Recent Advances in Intelligent and Sustainable Technologies (RAIST 2026)
PB  - Atlantis Press
SP  - 288
EP  - 298
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-707-1_25
DO  - 10.2991/978-94-6239-707-1_25
ID  - Barmaiya2026
ER  -