Bangladesh Road Damage Detection Dataset

This dataset contains annotated road images collected from different roads in Bangladesh for road damage and pothole detection research. The dataset was prepared for object detection tasks using YOLO-compatible annotation format.

The dataset includes both damaged road images and normal road images to improve model generalization and reduce false positive predictions. Road damages such as potholes, broken road surfaces, and visible cracks were annotated under a single class named "pothole".

The dataset is divided into train, validation, and test sets and exported in YOLOv8 format. It can be used for computer vision research, intelligent transportation systems, automated road monitoring, and deep learning-based road damage detection applications.