Driver’s Drowsiness Detection Using Dlib and IoT

Author(s): Prasanna Lakshmi Kompalli*, Padma Vallakati, Ganapathi Raju Nadimpalli, Vinod Mahesh Jain, Samuel Annepogu

Journal Name: International Journal of Sensors, Wireless Communications and Control

Volume 11 , Issue 7 , 2021


Become EABM
Become Reviewer
Call for Editor

Graphical Abstract:


Abstract:

Background: Road accidents are a major cause of deaths worldwide. This is enormously due to fatigue, drowsiness, and microsleep of the drivers. This does not just risk the life of the driver and co-passengers but also a great threat to the vehicles and humans moving around that vehicle.

Methods: Research, online content, and previously published papers related to drowsiness are reviewed. Using the facial landmarks in DAT file, the prototype locates and identifies the eye coordinates, and then calculates Eye Aspect Ratio (EAR). The EAR indicates whether the driver is drowsy or not based on the result of various sensors that get activated, such as an alarm generator, LED indicators, LCD message scroll, message sent to the owner, and the engine that gets locked.

Results: The prototype is able to locate eyes in the frame and detect whether the person is sleepy or not. Whenever the person is feeling drowsy, an alarm is generated in the cabinet, and afterward , LED indicators will start glowing, messaging will be scrolling at the rear part of the vehicle so that other vehicles and humans get cautioned. After this, the vehicle slows down, and the engine gets locked.

Conclusion: This prototype will help in the reduction of road accidents due to human intervention. It is not only helpful to the person who installs it in their vehicle but also for the other vehicles and humans moving around it.

Keywords: IoT, face detection, drowsiness detection, fatigue identification, sensors, raspberry pi, alert system, eye aspect ratio.

Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 11
ISSUE: 7
Year: 2021
Published on: 18 December, 2020
Page: [725 - 732]
Pages: 8
DOI: 10.2174/2210327910666201218162536
Price: $25

Article Metrics

PDF: 232