Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cutting-Edge Detection of Fatigue in Drivers: A Comparative Study of Object Detection Models

Amelia Jones

TL;DR

Experimental results demonstrate that YOLOv8 offers superior performance, balancing accuracy with speed, and suggests a roadmap for enhancing real-time detection of fatigue-related behavior in drivers.

Abstract

This research delves into the development of a fatigue detection system based on modern object detection algorithms, particularly YOLO (You Only Look Once) models, including YOLOv5, YOLOv6, YOLOv7, and YOLOv8. By comparing the performance of these models, we evaluate their effectiveness in real-time detection of fatigue-related behavior in drivers. The study addresses challenges like environmental variability and detection accuracy and suggests a roadmap for enhancing real-time detection. Experimental results demonstrate that YOLOv8 offers superior performance, balancing accuracy with speed. Data augmentation techniques and model optimization have been key in enhancing system adaptability to various driving conditions.

Cutting-Edge Detection of Fatigue in Drivers: A Comparative Study of Object Detection Models

TL;DR

Experimental results demonstrate that YOLOv8 offers superior performance, balancing accuracy with speed, and suggests a roadmap for enhancing real-time detection of fatigue-related behavior in drivers.

Abstract

This research delves into the development of a fatigue detection system based on modern object detection algorithms, particularly YOLO (You Only Look Once) models, including YOLOv5, YOLOv6, YOLOv7, and YOLOv8. By comparing the performance of these models, we evaluate their effectiveness in real-time detection of fatigue-related behavior in drivers. The study addresses challenges like environmental variability and detection accuracy and suggests a roadmap for enhancing real-time detection. Experimental results demonstrate that YOLOv8 offers superior performance, balancing accuracy with speed. Data augmentation techniques and model optimization have been key in enhancing system adaptability to various driving conditions.

Paper Structure

This paper contains 16 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background and Importance
  3. Objectives
  4. Related Work
  5. Fatigue Detection Techniques
  6. YOLO Models in Object Detection
  7. Methodology
  8. Dataset Preparation
  9. Model Architectures
  10. Training and Optimization
  11. Results and Analysis
  12. Loss Curves
  13. Precision, Recall, and mAP
  14. Confusion Matrix Analysis
  15. Discussion
  16. ...and 1 more sections

Figures (3)

  • Figure 1: Training and validation loss curves for box loss, class loss, DFL loss, and mAP metrics across 100 epochs.
  • Figure 2: Precision-Recall curve for the fatigue-related behavior classes: Yawn, Closed Eyes, No Yawn, Open Eyes.
  • Figure 3: Performance comparison of models in terms of mAP and F1-Score across the dataset.