Fatigue driving detection model based on multi-feature fusion and semi-supervised active learning

Fatigue driving is one of the main factors of traffic accidents and there are many research efforts focusing on fatigue driving detection. With the extensive use of on-board sensors, a huge number of unlabelled driving data can be easily collected, however, it is a costly and laborious work to annot...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IET intelligent transport systems Jg. 13; H. 9; S. 1401 - 1409
Hauptverfasser: Li, Xu, Hong, Lin, Wang, Jian-chun, Liu, Xiang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: The Institution of Engineering and Technology 01.09.2019
Schlagworte:
authors
costly work
efficient fatigue driving detection model
facial features
fatigue
laborious work
learning (artificial intelligence)
novel fatigue
Research Article
rest data
road safety
semantic labels
semisupervised active learning algorithm
steering features
unlabelled driving data
laborious work
efficient fatigue driving detection model
road safety
facial features
semantic labels
semisupervised active learning algorithm
fatigue
costly work
novel fatigue
steering features
rest data
learning (artificial intelligence)
unlabelled driving data
authors
ISSN:1751-956X, 1751-9578
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Fatigue driving is one of the main factors of traffic accidents and there are many research efforts focusing on fatigue driving detection. With the extensive use of on-board sensors, a huge number of unlabelled driving data can be easily collected, however, it is a costly and laborious work to annotate semantic labels for these data manually, posing some difficulties to detect fatigue driving with these data. In this work, the authors propose a novel fatigue driving detection model based on multi-feature fusion and semi-supervised active learning. In the authors’ model, the steering features of the vehicle and the facial features of the driver are fused to improve the accuracy and stability of the model. Semi-supervised active learning algorithm allows us to make semantic labels for only a small number of data that can be propagated to the rest data, and help us establish an efficient fatigue driving detection model with automatic label propagation. Some experiments are conducted to validate their model, the results show that the accuracy is 86.25%, which proves the effectiveness of the fatigue driving detection model.
ISSN:1751-956X
1751-9578
DOI:10.1049/iet-its.2018.5590