Detecting driver drowsiness by combining Viola-Jones image processing method and image landmarks detection

Articles in Press

Document Type : Research Article

Authors

1 Civil Engineering Dep

2 University of zanjan

3 Imam Khomeini Int. University

Abstract

Fatigue is one of the main causes of traffic accidents which leads to the death of many people on the roads every year. Several methods have been developed to detect the level of fatigue, one of which is intelligent fatigue detection and the use of various parameters in a long time and based on driving history. This advantage leads to the detection of fatigue in the early stages and activating the alarm before the accident happens. In this paper, a new method is applied to detect drowsiness from video frames using the YawDD database. The operation of the proposed system is based on the tracking of facial landmarks extracted from video frames. The purpose of this paper is to detect drowsiness from facial expressions. By extracting and tracking key points, facial expressions such as normal or sleepy can be detected. First, the initial position of the face is determined and then the key points are extracted using Viola-Jones and SIFT algorithms respectively. This method is capable of detecting the driver's drowsiness with good accuracy.

Keywords

Main Subjects

Amirkabir Journal of Civil Engineering

Articles in Press, Accepted Manuscript
Available Online from 06 April 2025

Files

Share

How to cite

Statistics