MTPDSD
MTPDSD is a comprehensive dataset containing 2,600 high‑quality pavement distress images, annotated with instance segmentation. It includes seven pavement distress categories: cracks, potholes, sealed cracks, patches, alligator cracks, facility covers, and expansion joints. In total, there are 3,596 annotated distress instances, each with a mask precisely aligned to the damage boundary.
Dataset description and usage context
MTPDSD: Multi‑Type Pavement Distress Segmentation Dataset Overview
Dataset Introduction
MTPDSD is a comprehensive dataset comprising 2,600 high‑quality pavement distress images, annotated using instance segmentation.
The dataset covers 7 pavement distress categories, namely cracks, potholes, sealed cracks, patches, alligator cracks, facility covers, and expansion joints. A total of 3,596 pavement distress instances are provided, each annotated with a mask that tightly follows the damage boundary.
The following image shows examples of all seven categories of pavement distress.
Data Collection
The dataset was acquired using a vehicle‑mounted pavement distress data collection system. The system captures wide‑angle images with a dashboard camera and high‑resolution images with a rear‑view camera, enabling multi‑angle high‑quality image acquisition for a comprehensive dataset.
Pair the dataset with AI analysis and content workflows.
Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.