Authors :
Sowntharya Lakshmi B; Deepika A; Sree Madhumitha J; Nandhini R; Suhana Nafais A
Volume/Issue :
Volume 8 - 2023, Issue 5 - May
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://rb.gy/1vhrc
DOI :
https://doi.org/10.5281/zenodo.7964574
Abstract :
Driver drowsiness detection and alert
generating system is a form of artificial intelligence that
practices machine learning algorithms to detect signs of
drowsiness in drivers. This technology typically involves
sensors such as cameras, microphones, and
accelerometers that track the driver’s behaviours, such
as head position, eye movement, and yawning, and then
use machine learning algorithms to detect patterns of
drowsiness. The technology can then alert the driver if
they are at risk of dozing off, helping to reduce the risk
of accidents or dangerous driving behaviour. A machinelearning approach to detect drowsiness in drivers using
facial landmarks. The planned system uses a
convolutional neural network (CNN) to observe the
facial features of a driver in real-time and then compares
them with a set of predefined features associated with
drowsiness. The system can then alert the driver of their
drowsiness by sounding an alarm or displaying a
warning message. The planned method can be used in
various applications, such as driver assistance systems,
autonomous vehicle systems, and public safety systems.
Lastly, we outline the issues that current systems
confront and discuss the associated research prospects.
Keywords :
Machine Learning, Autonomous Vehicle Technology, Yawn Detection, Driver Drowsiness Detection, Image-Based Measures.
Driver drowsiness detection and alert
generating system is a form of artificial intelligence that
practices machine learning algorithms to detect signs of
drowsiness in drivers. This technology typically involves
sensors such as cameras, microphones, and
accelerometers that track the driver’s behaviours, such
as head position, eye movement, and yawning, and then
use machine learning algorithms to detect patterns of
drowsiness. The technology can then alert the driver if
they are at risk of dozing off, helping to reduce the risk
of accidents or dangerous driving behaviour. A machinelearning approach to detect drowsiness in drivers using
facial landmarks. The planned system uses a
convolutional neural network (CNN) to observe the
facial features of a driver in real-time and then compares
them with a set of predefined features associated with
drowsiness. The system can then alert the driver of their
drowsiness by sounding an alarm or displaying a
warning message. The planned method can be used in
various applications, such as driver assistance systems,
autonomous vehicle systems, and public safety systems.
Lastly, we outline the issues that current systems
confront and discuss the associated research prospects.
Keywords :
Machine Learning, Autonomous Vehicle Technology, Yawn Detection, Driver Drowsiness Detection, Image-Based Measures.
