What question did this study set out to answer?

This study aims to develop and evaluate a real-time road damage detection system utilizing an improved YOLOv8 model.

Deep Learning-Based Road Damage Detection Using Improved YOLOv8: Model Performance and Implementation

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates road damage detection in Indonesia, suggesting a practical tool for infrastructure monitoring.

This study aims to develop and evaluate a real-time road damage detection system utilizing an improved YOLOv8 model.
Model trained to identify six types of road damage using a hybrid dataset of 2,946 images.
Implemented mosaic augmentation and optimized preprocessing techniques to enhance generalization.
Deployed the model as a smartphone application for automated road condition surveys.
Achieved a mean Average Precision (mAP@50) of 96.3%.
F1-score reached 91% with overall accuracy of 91%.
Demonstrated superior performance in detecting and classifying various road damage types.

Rahman et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark