A Systematic Review on Driver Drowsiness Detection Using Eye Activity Measures

Abstract

Driver drowsiness is a major contributor to road traffic accidents. A system capable of detecting drowsiness and consequently warning drivers at an early stage could significantly reduce the number of drowsiness-related road accidents. Although different measures can indicate driver drowsiness, eye activity measures are known to indicate drowsiness in the early stages. This study systematically reviewed empirical studies (with reported performance measures) on driver drowsiness detection (DDD) systems that use eye activities to indicate drowsiness. The objective of this review was to provide researchers and practitioners with in-depth information on DDD systems based on eye activities. Forty-one studies were identified using the preferred reporting items for systematic reviews and meta-analyses methodology. This review investigated various eye activity measures of drowsiness and provides a classification scheme for these measures. In addition, the current technologies used to measure eye activity were examined and a classification scheme for these technologies was formulated. Further, the decision-making algorithms used to classify and predict drowsiness states were investigated using their associated performance measures. Finally, future insights and ideas for utilizing eye activity measures to detect drowsiness at an early stage were discussed. This study forms the basis for future research and development of DDD using eye activities.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 38 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.