Learning based Driver Drowsiness Detection Model

Abstract

Drivers drive for long hours which deteriorates their health. Due to this, the drivers are often tired and often on the verge of fatigue. This leads them to have bursts of microsleep i.e. a interim episode of sleepiness which may last for a fraction of a second or up to 30 seconds, where the victim fails to react to some stimulus from the environment and becomes unconscious. As a result of this, road accidents have become a common occurrence globally. The purpose of this paper is to devise a way to alert drowsy drivers while driving. This study attempted to address the issue by creating a module i.e. drowsy eyes detection. Using 68 key points, we devised a new detection approach for facial regions. After that we use these facial regions as a key point to evaluate the driver's state. The accuracy was up to 92.5%.

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 — 79 citations exist upstream.

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