Automated Quality Assessment of Asphalt Pavement Construction Through Computer Vision and Aggregate Texture Analysis
Keywords:
automated pavement quality assessment; computer vision; aggregate texture; asphalt construction; socio-technical systems; infrastructure governance; sustainability; edge computingAbstract
Asphalt pavement construction remains a critical but unevenly monitored component of transportation infrastructure. Conventional quality assurance relies on manual inspection, limited sampling, and retrospective testing, which can miss spatial variability in aggregate distribution, surface texture, compaction uniformity, and segregation. This paper examines automated quality assessment of asphalt pavement construction through computer vision and aggregate texture analysis from a system-level perspective. The discussion treats vision-based assessment not merely as a model deployment problem but as a socio-technical infrastructure involving sensing, edge and cloud computation, data governance, standards, procurement, maintenance, and public accountability. The paper analyzes architectural trade-offs among camera-based inspection, unmanned aerial sensing, smartphone imagery, and embedded edge devices, and it considers how aggregate texture and morphology influence mixture meso-structure, surface friction, durability, and moisture resistance. It further explores robustness under variable lighting, dust, vibration, and seasonal conditions, as well as fairness concerns when advanced assessment tools are deployed only on high-value corridors. Governance implications include performance-based specifications, auditable model decisions, interoperability with asset management systems, and alignment with environmental and safety policies. The paper argues that automated pavement quality assessment can improve consistency, reduce rework, and support sustainable construction, but only if technical accuracy is matched by institutional readiness, transparent validation, and equitable deployment. The conclusion identifies future research needs in multimodal sensing, uncertainty-aware inference, digital twins, and policy frameworks for accountable infrastructure automation.
References
1. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90. https://doi.org/10.1145/3065386
2. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778). IEEE.
3. Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137–1149.
4. Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3431–3440). IEEE.
5. Zhang, L., Yang, F., Zhang, Y. D., & Zhu, Y. J. (2016). Road crack detection using deep convolutional neural network. In 2016 IEEE International Conference on Image Processing (pp. 3708–3712). IEEE.
6. Koch, C., Georgieva, K., Kasireddy, V., Akinci, B., & Fieguth, P. (2015). A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure. Advanced Engineering Informatics, 29(2), 196–210.
7. Maeda, H., Sekimoto, Y., Seto, T., Kashiyama, T., & Omata, H. (2018). Road damage detection using deep neural networks with images captured through a smartphone. Computer-Aided Civil and Infrastructure Engineering, 33(12), 1123–1134.
8. Zhu, Z., German, S., & Brilakis, I. (2011). Visual retrieval of concrete crack properties for automated post-earthquake structural safety evaluation. Automation in Construction, 20(7), 874–883.
9. Hoskere, V., Narazaki, Y., Hoang, T. A., & Spencer, B. F. (2019). Vision-based modal survey of civil infrastructure using unmanned aerial vehicles. Journal of Structural Engineering, 145(7), 04019062.
10. Jahanshahi, M. R., & Masri, S. F. (2013). Adaptive vision-based crack detection using 3D scene reconstruction for condition assessment of structures. Automation in Construction, 22, 567–576.
11. National Academies of Sciences, Engineering, and Medicine. (2017). Automated pavement distress collection and analysis: A synthesis of highway practice (NCHRP Synthesis 512). Transportation Research Board.
12. Federal Highway Administration. (2017). Highway Performance Monitoring System field manual. U.S. Department of Transportation.
13. Winner, L. (1980). Do artifacts have politics? Daedalus, 109(1), 121–136.
14. Bijker, W. E., Hughes, T. P., & Pinch, T. (Eds.). (1987). The social construction of technological systems: New directions in the sociology and history of technology. MIT Press.
15. Kitchin, R., & Dodge, M. (2011). Code/space: Software and everyday life. MIT Press.
16. L.W.Shi, Z.Y.Hu, H.M.Huang, et al. Effect of coarse aggregate morphology on asphalt mixture meso‑structure using image recognition technology, Measurement, 2026, 290: 122757.
17. European Committee for Standardization. (2018). EN 13036-1: Road and airfield surface characteristics—Test methods—Part 1: Measurement of pavement surface macrotexture depth using a volumetric patch technique. CEN.
18. International Organization for Standardization. (2020). ISO 55000: Asset management—Overview, principles and terminology. ISO.
19. Transportation Research Board. (2020). Guide for pavement friction. National Academies Press.
20. American Association of State Highway and Transportation Officials. (2018). AASHTO T 283: Standard method of test for resistance of compacted asphalt mixtures to moisture-induced damage. AASHTO.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Computational Intelligence Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.