Vehicular Security: Drowsy Driver Detection System
Pranavi Pendyala1, Aviva Munshi2, Anoushka Mehra3

1Pranavi Pendyala, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
2Aviva Munshi*, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
3Anoushka Mehra, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.

Manuscript received on June 02, 2021. | Revised Manuscript received on June 09, 2021. | Manuscript published on June 30, 2021. | PP: 206-209 | Volume-10 Issue-5, June 2021. | Retrieval Number:  100.1/ijeat.E27510610521 | DOI: 10.35940/ijeat.E2751.0610521
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Detecting the driver’s drowsiness in a consistent and confident manner is a difficult job because it necessitates careful observation of facial behaviour such as eye-closure, blinking, and yawning. It’s much more difficult to deal with when they’re wearing sunglasses or a scarf, as seen in the data collection for this competition. A drowsy person makes a variety of facial gestures, such as quick and repetitive blinking, shaking their heads, and yawning often. Drivers’ drowsiness levels are commonly determined by assessing their abnormal behaviours using computerised, nonintrusive behavioural approaches. Using computer vision techniques to track a driver’s sleepiness in a non-invasive manner. The aim of this paper is to calculate the current behaviour of the driver’s eyes, which is visualised by the camera, so that we can check the driver’s drowsiness. We present a drowsiness detection framework that uses Python, OpenCV, and Keras to notify the driver when he feels sleepy. We will use OpenCV to gather images from a webcam and feed them into a Deep Learning model that will classify whether the person’s eyes are “Open” or “Closed” in this article. 
Keywords: Abnormal Behaviours, Current Activity, Deep Learning, Facial Behaviour