Research on optimization algorithm of abnormal driving behavior detection based on PFLD

Jing He; Chen Dong; YuTing Di; JiaHeng An; JiaXing Gao; ZhiJiang Liu

doi:10.1117/12.2680956

8 June 2023 Research on optimization algorithm of abnormal driving behavior detection based on PFLD

Jing He, Chen Dong, YuTing Di, JiaHeng An, JiaXing Gao, ZhiJiang Liu

Proceedings Volume 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023); 127074Q (2023) https://doi.org/10.1117/12.2680956
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 2023, Changsha, China

Abstract

Driver's fatigue driving and mood are two important factors that cause traffic accidents, and with the widespread use of mobile devices, it is of significant research value to detect driver's abnormal driving behavior on the mobile terminal. In this paper, the PFLD model is used on mobile to obtain face keypoints and improve the EAR by fusing binocular opening and closing degree to detect abnormal driving behavior such as fatigue and mood. Fatigue detection integrates the improved EAR, yawning duration, head pitch angle and other multiple features to determine, which mainly includes the process of extracting the driver's both eyes and mouth features through the PFLD model, monitoring the driver's heart rate and head distance with Internet of Things devices, constructing feature vectors and using SVM to determine driving fatigue. The threshold parameters are selected by calculating the five-dimensional features of the face, and the driver's mood is detected based on KNN. Through experiments, the driver fatigue detection accuracy is about 90% and the mood recognition accuracy is up to 96%.

Citation Download Citation

Jing He, Chen Dong, YuTing Di, JiaHeng An, JiaXing Gao, and ZhiJiang Liu "Research on optimization algorithm of abnormal driving behavior detection based on PFLD", Proc. SPIE 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 127074Q (8 June 2023); https://doi.org/10.1117/12.2680956

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Head

Heart

Detection and tracking algorithms

Education and training

Facial recognition systems

Data modeling

Eye models

Show All Keywords

Keywords/Phrases

Search In:

Publication Years