Rapid extraction of pavement aggregate gradation based on point clouds using deep learning networks

Journal article (2023)

Authors

Siyu Chen Southeast University
Can Chen Southeast University
Tao Ma Southeast University
Chengjia Han Southeast University, Nanyang Technological University
Haoyuan Luo Southeast University
Siqi Wang Southeast University
Y. Gao Pavement Engineering - CEG
Yaowen Yang Nanyang Technological University
Research Group
Pavement Engineering (CEG) (TU Delft)
Copyright: © 2023 Siyu Chen, Can Chen, Tao Ma, Chengjia Han, Haoyuan Luo, Siqi Wang, Y. Gao, Yaowen Yang
DOI
help_outline
https://doi.org/10.1016/j.autcon.2023.105023
Point clouds Artificial neural networks Asphalt pavement Aggregate gradation Multi-feature fusion
More Info
expand_more

Published Date

2023

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Civil Engineering & Geosciences

Department

Engineering Structures

Research Group

Pavement Engineering

Abstract

Usage of asphalt mixture with poor gradation will most likely lead to pavement deficiency. There is a growing need for rapid and non-destructive methods to extract pavement aggregate gradation. In this study, a deep learning-based method that utilizes point clouds data for gradation extraction was proposed. Firstly, a data enhancement algorithm along with three data format conversion methods (aligned point cloud, voxel, and depth image) were proposed to preprocess the original collected point clouds. Subsequently, different neural network models were designed for each data format to extract gradation. Finally, a multi-feature fusion network was developed, which using extraction network as the backbone and additional auxiliary information. In the case study, the MAE loss of multi-feature fusion networks with PointNet, Vox-ResNet34 and GoogLeNet-v4 as the backbone respectively achieved 0.202, 0.142 and 0.046 on the test set, which means an estimation accuracy of more than 95% for the pavement aggregate gradation.