Determination of the air void content of asphalt concrete mixtures using artificial intelligence techniques to segment micro-CT images. Issue 11 (19th September 2022)

• Record Type: Journal Article
• Authors: Enríquez-León, Alexis Jair; de Souza, Thiago Delgado; Aragão, Francisco Thiago Sacramento; Braz, Delson; Pereira, André Maués Brabo; Nogueira, Liebert Parreiras
• Is Part Of: International journal of pavement engineering. Volume 23:Issue 11(2022)
• Page Start: 3973
• Page End: 3982
• Publication Date: 2022-09-19
• Subjects: X-ray micro-computed tomography -- air void -- digital image processing -- threshold -- machine learning -- deep learning; Pavements -- Design and construction -- Periodicals; Highway engineering -- Periodicals; 625.805
• DOI: 10.1080/10298436.2021.1931197
• Languages: English
• ISSNs: 1029-8436

Abstract

ABSTRACT: X-ray micro-computed tomography (micro-CT) is an advanced technique able to provide a comprehensive examination of the volumetric characteristics of asphalt mixtures. A key step for the air void (AV) quantification using micro-CT images is the segmentation, which is a stage of the digital image processing. The most common segmentation technique, the manual threshold (TH) selection, depends significantly on the operator skills, image homogeneity, and material complexity. These factors that can limit the reproducibility of the TH procedure. Machine learning and deep learning recently appeared as promising alternatives to solve this challenge. In this paper, images of an asphalt concrete (AC) specimen were acquired in a modern high-resolution micro-CT scanner to determine its AV content using four different segmentation tools, i.e. TH, watershed, machine learning, and deep learning. All methods presented similar results for the total AV content. The advantages and limitations of using each technique were discussed in terms of computational effort, user-friendliness, and accuracy of the results. Machine learning and deep learning were identified as powerful tools for AC segmentation, being accurate and easy to adjust, however taking longer data processing times.