Related Experiment Video
Updated: Aug 6, 2026
08:03
Advanced Self-Healing Asphalt Reinforced by Graphene Structures: An Atomistic Insight
Published on: May 31, 2022
Binary image acquisition and texture parameter calculation of asphalt pavement based on a U-Net model
Fengwei An1,2, Haoran Jiang3, Yulong Zhao4
1China Communications Construction Jiangsu Highway Engineering Co., Ltd., Nanjing, China.
Plos One
|July 22, 2026
Summary
This study introduces a U-Net model for asphalt pavement image segmentation, accurately calculating texture parameters. The method shows strong correlation with traditional skid resistance measurements, offering improved pavement evaluation.
Area of Science:
- Civil Engineering
- Materials Science
- Computer Vision
Background:
- Current methods for assessing pavement skid resistance have limitations.
- Accurate evaluation of asphalt pavement texture is crucial for safety.
Purpose of the Study:
- To develop a novel method for asphalt pavement skid resistance evaluation using U-Net semantic segmentation.
- To precisely calculate pavement texture distribution parameters from segmented images.
Main Methods:
- Constructed a dataset of asphalt pavement images and performed preprocessing.
- Utilized U-Net semantic segmentation to differentiate aggregate and void components.
- Calculated texture parameters from binary images and correlated them with sand patch measurements.
Main Results:
- The U-Net model achieved an F1-score of 0.7214, indicating satisfactory segmentation performance.
- High correlation coefficients (R²=0.85 for MTD, R²=0.86 for fractal dimension) were found between the proposed method and traditional measurements.
- Correlations were statistically significant at the 95% confidence level.
Conclusions:
- The proposed U-Net based method provides effective technical support for texture-based skid resistance evaluation.
- This approach offers a precise and reliable alternative for assessing asphalt pavement surfaces.
