Comparative Study of VGG16, ResNet50, and YOLOv8 Models in Detecting Driver Distraction in Varying Lighting Conditions
Observing driver distractions while driving gives valuable information to prevent accidents, so it is necessary to use effective monitoring methods. Deep learning is showing new capabilities in solving this issue. This study evaluates the results of CNN, YOLOv8, ResNet50 and VGG16 deep learning mode...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Zagreb, Faculty of organization and informatics
2025-01-01
|
| Series: | Journal of Information and Organizational Sciences |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/480303 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850130108048736256 |
|---|---|
| author | Ali Nafaa Jaafar Mustafa Nafea Alzubaidi |
| author_facet | Ali Nafaa Jaafar Mustafa Nafea Alzubaidi |
| author_sort | Ali Nafaa Jaafar |
| collection | DOAJ |
| description | Observing driver distractions while driving gives valuable information to prevent accidents, so it is necessary to use effective monitoring methods. Deep learning is showing new capabilities in solving this issue. This study evaluates the results of CNN, YOLOv8, ResNet50 and VGG16 deep learning models as they detect drivers who are practising distracted driving behaviours under real-time and various lighting conditions (day and night). The models were trained on two datasets: the labelled State Farm dataset and the Driver Monitor Dataset (DMD). They successfully identified ten distinct categories of distraction for the State Farm dataset and five categories for the monitoring drivers dataset. Pre-trained models were optimized using transfer learning through fine-tuning to enhance detection accuracy. This paper studies related work on distracted driving and shares ideas for designing advanced systems that use various methods to improve accuracy. YOLOv8 reached an outstanding test accuracy of 98.46% on the State Farm dataset, proving itself superior to other methods and confirming its effectiveness for monitoring. In addition, YOLOv8 reached 96.46% accuracy in the DMD dataset, outperforming VGG16 at 90.58% and ResNet50 at 70.80%. YOLOv8 was able to recognise important driver behaviours in real time with a dataset of 15 subjects and 20 different driving postures. The research proves that the YOLOv8 model is fit for use in intelligent monitoring systems designed to detect distracted driving and promote safer driving through focused actions. |
| format | Article |
| id | doaj-art-dda93219c6c74953a9843647859cd33b |
| institution | OA Journals |
| issn | 1846-3312 1846-9418 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | University of Zagreb, Faculty of organization and informatics |
| record_format | Article |
| series | Journal of Information and Organizational Sciences |
| spelling | doaj-art-dda93219c6c74953a9843647859cd33b2025-08-20T02:32:46ZengUniversity of Zagreb, Faculty of organization and informaticsJournal of Information and Organizational Sciences1846-33121846-94182025-01-0149113915910.31341/jios.49.1.9Comparative Study of VGG16, ResNet50, and YOLOv8 Models in Detecting Driver Distraction in Varying Lighting ConditionsAli Nafaa Jaafar0Mustafa Nafea Alzubaidi1Electrical Engineering Technical College, Middle Technical University, Baghdad, IraqComputer Techniques Engineering Department, Al-Esraa University College, Baghdad, IraqObserving driver distractions while driving gives valuable information to prevent accidents, so it is necessary to use effective monitoring methods. Deep learning is showing new capabilities in solving this issue. This study evaluates the results of CNN, YOLOv8, ResNet50 and VGG16 deep learning models as they detect drivers who are practising distracted driving behaviours under real-time and various lighting conditions (day and night). The models were trained on two datasets: the labelled State Farm dataset and the Driver Monitor Dataset (DMD). They successfully identified ten distinct categories of distraction for the State Farm dataset and five categories for the monitoring drivers dataset. Pre-trained models were optimized using transfer learning through fine-tuning to enhance detection accuracy. This paper studies related work on distracted driving and shares ideas for designing advanced systems that use various methods to improve accuracy. YOLOv8 reached an outstanding test accuracy of 98.46% on the State Farm dataset, proving itself superior to other methods and confirming its effectiveness for monitoring. In addition, YOLOv8 reached 96.46% accuracy in the DMD dataset, outperforming VGG16 at 90.58% and ResNet50 at 70.80%. YOLOv8 was able to recognise important driver behaviours in real time with a dataset of 15 subjects and 20 different driving postures. The research proves that the YOLOv8 model is fit for use in intelligent monitoring systems designed to detect distracted driving and promote safer driving through focused actions.https://hrcak.srce.hr/file/480303VGG16ResNet50YOLOv8distracted driver detectionTransfer learning |
| spellingShingle | Ali Nafaa Jaafar Mustafa Nafea Alzubaidi Comparative Study of VGG16, ResNet50, and YOLOv8 Models in Detecting Driver Distraction in Varying Lighting Conditions Journal of Information and Organizational Sciences VGG16 ResNet50 YOLOv8 distracted driver detection Transfer learning |
| title | Comparative Study of VGG16, ResNet50, and YOLOv8 Models in Detecting Driver Distraction in Varying Lighting Conditions |
| title_full | Comparative Study of VGG16, ResNet50, and YOLOv8 Models in Detecting Driver Distraction in Varying Lighting Conditions |
| title_fullStr | Comparative Study of VGG16, ResNet50, and YOLOv8 Models in Detecting Driver Distraction in Varying Lighting Conditions |
| title_full_unstemmed | Comparative Study of VGG16, ResNet50, and YOLOv8 Models in Detecting Driver Distraction in Varying Lighting Conditions |
| title_short | Comparative Study of VGG16, ResNet50, and YOLOv8 Models in Detecting Driver Distraction in Varying Lighting Conditions |
| title_sort | comparative study of vgg16 resnet50 and yolov8 models in detecting driver distraction in varying lighting conditions |
| topic | VGG16 ResNet50 YOLOv8 distracted driver detection Transfer learning |
| url | https://hrcak.srce.hr/file/480303 |
| work_keys_str_mv | AT alinafaajaafar comparativestudyofvgg16resnet50andyolov8modelsindetectingdriverdistractioninvaryinglightingconditions AT mustafanafeaalzubaidi comparativestudyofvgg16resnet50andyolov8modelsindetectingdriverdistractioninvaryinglightingconditions |