This paper is published in Volume-5, Issue-2, 2019
Area
Computer Vision
Author
Madhu
Co-authors
Khushboo Mishra, Shubham Karki, S. R. Dhore
Org/Univ
Army Institute of Technology, Pune, Maharashtra, India
Pub. Date
08 March, 2019
Paper ID
V5I2-1176
Publisher
Keywords
Computer vision, Real-time processing, Motion detection, Facial landmark detection, Eye Aspect Ratio, Severity score

Citationsacebook

IEEE
Madhu, Khushboo Mishra, Shubham Karki, S. R. Dhore. A non-intrusive approach for drowsy and drunk driving using computer vision techniques, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Madhu, Khushboo Mishra, Shubham Karki, S. R. Dhore (2019). A non-intrusive approach for drowsy and drunk driving using computer vision techniques. International Journal of Advance Research, Ideas and Innovations in Technology, 5(2) www.IJARIIT.com.

MLA
Madhu, Khushboo Mishra, Shubham Karki, S. R. Dhore. "A non-intrusive approach for drowsy and drunk driving using computer vision techniques." International Journal of Advance Research, Ideas and Innovations in Technology 5.2 (2019). www.IJARIIT.com.

Abstract

This paper presents a holistic, non-intrusive approach for drunk and drowsy detection of the driver using computer vision techniques of facial landmark detection and motion detection. The driver's continuous real-time video feed is observed with the help of a smartphone camera. A single scalar quantity, Eye Aspect Ratio (EAR) which characterizes persistent eye blinks continuously analyses this feed. Simultaneously the system checks the body and the head movements using the differential imaging technique, which operates in real-time. A severity score indicating the fitness to drive is generated cumulatively using both methods. The driver is notified with the sound of an alarm if the results are positive based on a threshold value of the severity score.