Vehicle Discrimination Using a Combined Multiple Features Based on Vehicle Face

Wang, Yingnan; Li, Hong; Kirui, Clement; Zhang, Wei

doi:10.1007/978-3-642-38466-0_56

Search citation statements

Order By: Relevance

Paper Sections

Select...

The Vehicular Features-based Techniques1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2016

2022

Publication Types

Select...

Article2

Other1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section aims to overview the various methods and approaches used to detect drowsiness. The first method was previously employed based on driving patterns, depending on vehicle characteristics, road environment, and driving abilities [12]. Disturbances in either lateral or lane position, or changes in steering wheel movement, should be recorded to derive the driver's driving pattern.…”

Section: The Vehicular Features-based Techniquesmentioning

confidence: 99%

Modern Drowsiness Detection in Deep Learning: A review

Jasim,

Abdul Hassan

2022

J. Al-Qadisiyah Comp. Sci. Math.

View full text Add to dashboard Cite

Recent statistics show that drowsiness is now more of a factor in some car accidents than alcohol. So numerous monitoring systems have been developed to reduce, and accidents eliminate these events. Drowsiness detection systems are plentiful, but it isn't clear which one is the most effective. This review paper will address the following issues: firstly, determining the extracted features, whether behavioral-based, physiological-based, or vehicle-based, which are used to detect driver drowsiness; secondly, focusing on using deep learning to detect driver drowsiness. Finally, concluding from this study that the hybrid-based features should be used Because it gives strength in determining the drowsiness of the driver.

show abstract

Section: The Vehicular Features-based Techniquesmentioning

confidence: 99%