Pavementscapes: a large-scale hierarchical image dataset for asphalt pavement damage segmentation

TL;DR

This paper introduces Pavementscapes, a large-scale, high-resolution dataset for asphalt pavement damage segmentation, enabling improved deep learning methods and benchmarking for pavement inspection tasks.

Contribution

The paper presents Pavementscapes, a new extensive dataset with detailed annotations, and evaluates deep learning models, establishing baselines and highlighting challenges in pavement damage segmentation.

Findings

Deep neural networks achieve promising segmentation performance.

Existing models face challenges with damage variability and occlusions.

The dataset facilitates future research and method development.

Abstract

Pavement damage segmentation has benefited enormously from deep learning. % and large-scale datasets. However, few current public datasets limit the potential exploration of deep learning in the application of pavement damage segmentation. To address this problem, this study has proposed Pavementscapes, a large-scale dataset to develop and evaluate methods for pavement damage segmentation. Pavementscapes is comprised of 4,000 images with a resolution of $1024 \times 2048$, which have been recorded in the real-world pavement inspection projects with 15 different pavements. A total of 8,680 damage instances are manually labeled with six damage classes at the pixel level. The statistical study gives a thorough investigation and analysis of the proposed dataset. The numeral experiments propose the top-performing deep neural networks capable of segmenting pavement damages, which provides the baselines of the open challenge for pavement inspection. The experiment results also indicate the existing problems for damage segmentation using deep learning, and this study provides potential solutions.