Drowsy Driver Detection using Visual Behavior with Machine Learning

  • Syeda Misba Fathima , B. Dilip Kumar Reddy, G.Harith
Keywords: eye opening ratio, mouth aspect ratio, SVM etc

Abstract

One of the leading causes of traffic accidents and deaths is drowsy driving. As a result, detecting and indicating driver weariness is an important study subject. The majority of traditional techniques are vehicle-based, behavioral-based, or physiological-based. Some approaches are invasive and distract the driver, while others necessitate the use of pricey sensors and data processing. As a result, a low-cost, real-time driver drowsy detection system with adequate accuracy is built in this work. A camera records the video in the created system, and image processing algorithms is used to recognise the driver's face in each frame. Facial landmarks are pointed on the face, the eye opening ratio and mouth aspect ratio are computed, and tiredness is recognised using established adaptive thresholding based on their values. Offline implementations are made on machine learning algorithms. Support Vector Machine-based classification has a sensitivity of 95.58 percent and a specificity of 100 percent.

Published
2021-08-18
How to Cite
G.Harith, S. M. F. , B. D. K. R. (2021). Drowsy Driver Detection using Visual Behavior with Machine Learning. Design Engineering, 9269- 9278. Retrieved from http://thedesignengineering.com/index.php/DE/article/view/3497
Section
Articles