High Accuracy Driver Identification and Status Monitoring System Research

In this paper a driver's identity authentication and condition monitoring system will be proposed, which mainly includes two parts: identity authentication and status monitoring. The driver's facial features are extracted by the convolutional neural network, and then the feature dimensions...

Full description

Saved in:
Bibliographic Details
Published inJournal of physics. Conference series Vol. 1486; no. 4; pp. 42013 - 42021
Main Author Yuan, Xiaohan
Format Journal Article
LanguageEnglish
Published Bristol IOP Publishing 01.04.2020
Subjects
Artificial neural networks
Condition monitoring
Feature extraction
Monitoring systems
Physics
Real time
Online AccessGet full text

Cover

More Information
Summary:In this paper a driver's identity authentication and condition monitoring system will be proposed, which mainly includes two parts: identity authentication and status monitoring. The driver's facial features are extracted by the convolutional neural network, and then the feature dimensions are compressed to reduce calculation. All the vectors composed of these features will be matched with the face database in the local library, and only matched person is able to start the car. After authentication a camera will collect images of the face as well as its surroundings in real time. Later features are extracted, the vectors composed of these features are used to iteratively update the parameters of Bayesian classifier, thereby following the face position in real time, and according to the track of face motion determines whether the driving state is safe.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1486/4/042013