A detection model for driver's unsafe states based on real-time face-vision

The auto industry has developed fast in the last 100 years. Although it brings us convenience, more and more traffic accidents are happening every day. There are many factors which can cause a car accident. Based on the record of a large number of accidents, fatigue is one of the most important fact...

Full description

Saved in:
Bibliographic Details
Main Authors: Fangwen Zhai, Zehong Yang, Yixu Song, Hongbiao Ma
Format: Conference Proceeding
Language:English
Subjects:
computer vision
Face detection
Fatigue
fatigue monitoring
gaze detection
Laboratories
Mouth
Object detection
Real time systems
Road accidents
unsafe driving
US Department of Transportation
Vehicle driving
Vehicle safety
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The auto industry has developed fast in the last 100 years. Although it brings us convenience, more and more traffic accidents are happening every day. There are many factors which can cause a car accident. Based on the record of a large number of accidents, fatigue is one of the most important factors. Additionally, driver's distraction and conversations with passengers during driving can lead to serious results. In this paper, a real-time vision-based model is proposed for monitoring driver's unsafe states, including fatigue state, distraction state and talking state, etc. By analyzing driver's real-time face vision, a method for detecting driver's fatigue, distraction and talking states is given. Also, the model is its extreme high speed and very simple equipment. It can run at about 20 frames per second in video with 640*480 resolutions on a normal computer platform.
ISSN:2156-0110
DOI:10.1109/IASP.2010.5476145