This paper is published in Volume-6, Issue-4, 2020
Area
Computer Vision
Author
Anjaneya Turai
Org/Univ
Symbiosis Skills and Professional University, Pune, Maharashtra, India
Pub. Date
18 July, 2020
Paper ID
V6I4-1205
Publisher
Keywords
Don't Sleep, Drowsiness Detection Tool, Drowsiness, Road Accidents, Eye Aspect Ratio

Citationsacebook

IEEE
Anjaneya Turai. Don’t Sleep – Drowsiness Detection Tool, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Anjaneya Turai (2020). Don’t Sleep – Drowsiness Detection Tool. International Journal of Advance Research, Ideas and Innovations in Technology, 6(4) www.IJARIIT.com.

MLA
Anjaneya Turai. "Don’t Sleep – Drowsiness Detection Tool." International Journal of Advance Research, Ideas and Innovations in Technology 6.4 (2020). www.IJARIIT.com.

Abstract

An important application for machine vision and image processing can be the driver's recovery program because of its high importance. In recent years a number of research works have been reported in the literature in this field. In this paper, in contrast to the conventional tone detection methods, which are based on eye regions alone, we have used facial expressions to detect drowsiness. There are many challenges that involve pull detection systems. Some of the important issues are: changes in stiffness due to lighting conditions, the presence of glasses and beards on a person's face. For this project, I propose and implement an infrared light-based hardware system and can be used to solve these problems. In the proposed method, following the acquisition step of the face, the most important face elements and considered to be the most effective, are extracted and tracked in the video sequence frames. The system is monitored and performed locally. Every year more and more people lose their lives because of fatal road accidents worldwide and hot driving is one of the leading causes of road accidents and deaths. Exhaustion and poor sleep in the most common driving sources are the cause of major accidents. However, the first signs of fatigue may appear before the emergence of a crisis and therefore, the diagnosis of driver fatigue and its identification is a topic of further research. Most traditional methods of getting sleep are based on behavioral behavior while some are less confusing and may distract motorists, while others require expensive sensors. So, in this paper, a light weight, driver-specific death detection system was developed and implemented in the Android app. The program records videos and recognizes the face of the driver in all sectors using image printing techniques. The system can detect facial expressions, including the Eye Aspect Ratio (EAR) to detect driver drowsiness based on a changing threshold. Machine learning algorithms were employed to test the performance of the proposed method.