The fatigue driving detection method based on deep learning

Songqi Yang; Tiantian Liang; Yinping Shao

doi:10.1117/12.3033717

13 June 2024 The fatigue driving detection method based on deep learning

Songqi Yang, Tiantian Liang, Yinping Shao

Proceedings Volume 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024); 131806C (2024) https://doi.org/10.1117/12.3033717
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 2024, Guangzhou, China

Abstract

This article proposes an improved method for fatigue driving detection using the YOLOv5 algorithm, employing three techniques: Global Attention Mechanism (GAM), MPDIoU loss function, and Receptive Field Block (RFB). The core of this approach is to enhance the YOLOv5 algorithm's ability to recognize driver fatigue status, particularly through more accurate analysis of facial expressions and body language. The Global Attention Mechanism (GAM) weights key regions in the image, improving the algorithm's attention to driver facial features and, therefore, more accurately capturing subtle facial expressions related to fatigue. The MPDIoU loss function further optimizes the algorithm's training process, enhancing the model's ability to locate and recognize complex facial features. The introduction of Receptive Field Blocks (RFB) mimics the processing methods of the human visual system, improving the recognition of key features of fatigue driving behavior, such as eye closure, head position, and posture changes. This method has been tested and validated in various driving scenarios. The results demonstrate that, compared to the traditional YOLOv5 algorithm, this improved approach exhibits higher accuracy and reliability in fatigue driving detection.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Songqi Yang, Tiantian Liang, and Yinping Shao "The fatigue driving detection method based on deep learning", Proc. SPIE 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 131806C (13 June 2024); https://doi.org/10.1117/12.3033717

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