One of the most prevalent causes of fatal crashes that result in serious injuries or fatalities as well as major financial costs for victims, families, and society as a whole is fatigued driving. As a result of microsleeps, a fatigued driver poses a significantly greater risk to other road users than a fast driver. Scientists and firms in the automotive industry are working hard to find remedies to this challenge. In this paper, neural network-based approaches are used to identify short-term sleep and fatigue. Preventing road crashes caused by fatigued motorists may be as simple as triggering an alarm. Fatigue can be detected using a variety of techniques. The accuracy of classifying sleepiness was improved in this study by using camera-detected features of the face and a Convolutional Neural Network (CNN). As the system has been planted into portable smart device, it could be widely used for driving fatigue detection in daily life.
An Efficient Detection of Driver Tiredness and Fatigue using Deep Learning
2022-11-25
461978 byte
Conference paper
Electronic Resource
English
Tackling driver tiredness: raising awareness, reducing risk
British Library Conference Proceedings | 2004
|Computing driver tiredness and fatigue in automobile via eye tracking and body movements
BASE | 2022
|VEHICLE WITH A SAFETY SYSTEM INVOLVING PREDICTION OF DRIVER TIREDNESS
European Patent Office | 2018
|Vehicle with a safety system involving prediction of driver tiredness
European Patent Office | 2016
|VEHICLE WITH A SAFETY SYSTEM INVOLVING PREDICTION OF DRIVER TIREDNESS
European Patent Office | 2016