"Annotated Road Surface Anomalies Dataset for Real-Time Detection Using YOLOv8"
收藏DataCite Commons2025-07-28 更新2026-05-03 收录
下载链接：
https://ieee-dataport.org/documents/road-surface-anomaly-dataset
下载链接
链接失效反馈官方服务：
资源简介：
"This dataset contains 4,968 annotated images of road surface anomalies across five classes: Pothole, Drain Hole, Sewer Cover, Wet Surface, and Unpaved Road. Captured under varied lighting, weather, and surface conditions, the dataset is designed for real-time object detection tasks in road safety and infrastructure monitoring.Annotations were created using Roboflow in YOLOv8 format. The data is split into training (75%), validation (16%), and test (9%) sets. It supports the development of lightweight, high-accuracy models for smart city applications."
提供机构：
IEEE DataPort
创建时间：
2025-07-28
