Detection of the Tiredness Level of Drivers Using Machine Vision Techniques

Abstract

This paper presents a machine vision system to detect fatigue in drivers based on the percentage of closing eyes and detection of yawning and nodding. The system outputs are no fatigue, alarm and critical stage (fatigue). The characteristics are extracted from videos by using image processing techniques such as histogram analysis and color spaces. The decision on the tiredness level is the result of a combination of extracted characteristics. The global performance achieved in characteristic extraction is about 90% and 86% for classification, the processing time to produce a response is close to 40 ms.