Rapid pavement aggregate gradation estimation based on 3D data using a multi-feature fusion network

Weng, Zihang; Ablat, Gulnigar; Wu, Difei; Liu, Chenglong; Li, Feng; Du, Yuchuan; Cao, Jin

doi:10.1016/j.autcon.2021.104050

Cited by 25 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In case of insufficient observed data, Maeda et al applied a generative adversarial network (GAN) to generate distress images that could be used as new training data to improve detection accuracy (Maeda et al, 2021). Besides, a new pavement crack detection method was proposed to improve the detection accuracy by combining 2D grayscale images and 3D laser scanning data (Du et al, 2022;Huang et al, 2014;Weng et al, 2022). Some other advanced models were also proposed, such as functional brain network (Hua et al, 2019), parameter sharing-based deep network (Reyes & Ventura, 2019), deep support vector neural networks (Diaz-Vico et al, 2020), and so on.…”

Section: Pavement Distress Detection and Feature Extraction Methodsmentioning

confidence: 99%

Spatiotemporal matching method for tracking pavement distress using high‐frequency detection data

Pan

Liu

et al. 2022

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

Various algorithms based on deep learning have achieved promising results in pavement distress detection. However, the detected distresses are not tracked throughout the life cycle. In long‐term application scenarios, pavement distresses may take on different forms due to image acquisition mode, distress development, and environmental change, which make tracking distresses a tough question. We present in this study a spatiotemporal matching method based on high‐frequency real pavement distress datasets. Pavement distresses of fixed routes were collected 30 times over 5 months, and distresses with spatiotemporal information were obtained at time series. We apply image rectification, stitching and distress class, and bounding box generation algorithms for pre‐processing to align the collected images to the same‐detail level and angle. A four‐step spatiotemporal matching module is designed, including global positioning system (GPS) filtering, class filtering, relative position filtering, and distress feature filtering. The results reveal that the comprehensive rank‐3 hit rate of the matching method reaches 88.73%, and the method is robust to environmental factors, which helps show performance decay of distresses and the effect of maintenance operations. It is concluded that the spatiotemporal matching method is convenient to operate, and it lays the foundation for an agency to track distress evolution and make timely treatment of distresses in the life cycle.

show abstract

Section: Pavement Distress Detection and Feature Extraction Methodsmentioning

confidence: 99%

Spatiotemporal matching method for tracking pavement distress using high‐frequency detection data

Pan

Liu

et al. 2022

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…When SK > 0, it is positively skewed; when SK < 0, it is negatively skewed, which can reflect the symmetry information of the overall density curve of the coarse aggregate morphology and various test indicators. When KU > 0, the peak is high; when KU < 0, the peak is low, which can reflect the steepness of the various test indicators at the peak of the coarse aggregate morphology (Weng et al, 2022).…”

Section: Data Preparationmentioning

confidence: 99%

Quantitative analysis and comprehensive evaluation of coarse aggregate morphology for asphalt pavement

Zhang,

Cheng,

Kong

et al. 2024

Front. Mater.

View full text Add to dashboard Cite

The morphological characteristics of coarse aggregate play a crucial role in the mechanical properties, durability, and construction performance of asphalt mixtures and pavements in highway engineering. This study aims to quantitatively analyze the morphological characteristics of coarse aggregate and establish comprehensive evaluation indicators for its quality and performance. Two-dimensional cross-sectional images of coarse aggregates are obtained using the self-developed laser scanning equipment, and edge features are extracted using the Canny operator and edge tracing algorithm. Six morphological characteristic indicators are selected, and factor analysis is employed to propose comprehensive shape and edge feature for coarse aggregates. The results show that the proposed evaluation indicators effectively capture the shape and edge feature of coarse aggregates, with the exception of roughness, which is deemed unsuitable for evaluation. Factor analysis of six indicator values in 2,700 two-dimensional images led to the proposal of Shape Factor (SF) and Edge Feature Factor (EFF) as significant factors affecting aggregate shape and edge characteristics, respectively. Following optimization, SF ranged from 0.041 to 1.793, while EFF ranged from 0.368 to 1.745. The spearman’s rank correlation coefficient revealed strong correlations between the evaluation of coarse aggregate shape and edge features using the line laser-based comprehensive evaluation index. Specifically, correlation coefficients of 0.864 and 0.805 exceeded those of commonly used methods such as AIMS and X-ray CT, indicating the rationality and accuracy of the self-developed laser scanning device in evaluating aggregate morphology. This research provides strong support for the construction of highway engineering and optimization of coarse aggregate production and supply.

show abstract

“…However, they did not extract the gradation. On the other hand, Weng et al [21] proposed a multifeatured fusion network based on residual convolutional neural network to estimate the aggregate gradation using 3D data obtained from laser scanners. However, they directly reduced the dimension of point cloud data into image data for convolution, lacking comprehensive analysis of point cloud data features and corresponding applications.…”

Section: Introductionmentioning

confidence: 99%

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

Chen

et al. 2023

Automation in Construction

View full text Add to dashboard Cite

Rapid pavement aggregate gradation estimation based on 3D data using a multi-feature fusion network

Cited by 25 publications

References 45 publications

Spatiotemporal matching method for tracking pavement distress using high‐frequency detection data

Spatiotemporal matching method for tracking pavement distress using high‐frequency detection data

Quantitative analysis and comprehensive evaluation of coarse aggregate morphology for asphalt pavement

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

Contact Info

Product

Resources

About