A multiclass U-Net segmentation pipeline to identify multiple microstructural features in asphalt material volume: application to high-RAP mixtures
Preprint
- 21 April 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Developing reliable segmentation procedures to observe fatigue crack propagation in asphalt mixtures is challenging due to material heterogeneity containing, particularly when they contain high reclaimed asphalt pavement contents. Specifically, when images are X-ray computed tomograms (XCT), overlapping X-ray attenuation responses by the distinct material phases make conventional image analysis methods fail to consistently distinguish cracks from surrounding phases. In this study, a multiclass deep learning segmentation pipeline based on a U-Net architecture is presented for the simultaneous identification, within XCT, of the background and five material phases (crack and voids, mastic, PM-RAP fine asphalt mixtures (FAM), PM-RAP coarse aggregates, and virgin aggregates). The pipeline integrates pre-processing, semi-automatic and manual labelling, patch-based training, and volumetric rendering, enabling a robust phase discrimination across large XCT. The trained model achieved high segmentation performance, with a mean Intersection over Union (mIoU) of 0.89, accurately differentiating aggregates, mastic regions, and cracks. Three-dimensional renders of the segmented phases revealed preferential crack initiation along virgin aggregate–binder interfaces and allowed detailed assessment of the interaction between PM-RAP components. This pipeline provides a scalable and reproducible methodology for phase-contextualised crack analysis, offering new insights into fatigue damage mechanisms in heterogeneous asphalt systems and supporting the development of more durable recycled pavement materials.Keywords
This publication has 36 references indexed in Scilit:
- Application of U-Net+ + deep learning network for segmentation and processing of asphalt mixture X-ray CT imagesApplied Soft Computing, 2025
- Bridging 2D and 3D segmentation networks for computation-efficient volumetric medical image segmentation: An empirical study of 2.5D solutionsComputerized Medical Imaging and Graphics, 2022
- Re-using Ladle Furnace Steel slags as filler in asphalt mixturesConstruction and Building Materials, 2022
- Evaluation of fatigue performance of high RAP-WMA mixturesInternational Journal of Pavement Research and Technology, 2019
- Study of remobilization phenomena at reclaimed asphalt binder/virgin binder interphases for recycled asphalt mixtures using novel microscopic methodologiesConstruction and Building Materials, 2018
- A review of semantic segmentation using deep neural networksInternational Journal of Multimedia Information Retrieval, 2017
- The potential of Attenuated Total Reflection imaging in the mid-infrared for the study of recycled asphalt mixturesConstruction and Building Materials, 2016
- Cracking mechanisms in asphalt mixtures2015
- Investigating the blending of reclaimed asphalt with virgin materials using rheology, electron microscopy and computer tomographyComposites Part B: Engineering, 2014
- Comparative study of Hough Transform methods for circle findingImage and Vision Computing, 1990