EN
TR
Superpixel-Based Image Analysis for Stripping Detection in Asphalt Mixtures with ANN and U-Net Models
Abstract
The reliable detection of stripping in asphalt mixtures is a critical challenge for pavement performance evaluation, as conventional physical tests rely heavily on subjective observation and lack reproducibility. This study proposes an image-based quantitative method that integrates geometric standardization, superpixel segmentation, and feature extraction to enhance the objectivity of stripping assessment. Petri dish images were first standardized through square cropping and bicubic resampling to ensure comparability across samples. Superpixels were then generated, and multiple spatial, geometric, photometric, and texture-based features were extracted, including distance-to-center, compactness, local color similarity, and global color deviation. Automatic background labeling was achieved through a color-based masking approach validated by visual inspection. The extracted feature set was subsequently employed for supervised classification using artificial neural networks (ANNs), with model performance evaluated against reference segmentations. The results demonstrate that the proposed method achieves high classification accuracy, with robust generalization across multiple sample sets. In particular, ANN-based predictions exhibited superior discriminative capability in distinguishing stripped from coated aggregate regions, outperforming U-Net segmentation under identical input conditions. The findings highlight that incorporating contextual descriptors, such as black pixel ratio and blue-background masking, significantly improves classification robustness in low-contrast and noisy regions. Overall, the proposed framework provides a reproducible and efficient alternative to conventional stripping tests, enabling reliable quantitative evaluation of asphalt mixture performance. This study contributes to the advancement of automated image analysis methods in pavement engineering and establishes a foundation for broader integration of computer vision into asphalt durability assessment.
Keywords
Kaynakça
- Cao R. J., Zhao Y. L., Gao Y., Huang X. M., Zhang L. L., Effects of flow rates and layer thicknesses for aggregate conveying process on the prediction accuracy of aggregate gradation by image segmentation based on machine vision. Construction and Building Materials 222, 566-578, 2019.
- Cui P. D., Wu S. P., Xiao Y., Wang F., Wang F. S., Quantitative evaluation of active based adhesion in Aggregate-Asphalt by digital image analysis. Journal of Adhesion Science and Technology 33(14), 1544-1557, 2019.
- Gürer C., Karaşahin M., Sathi Kaplama Agregalarının Adezyon Özelliklerinin Araştırılması. Yapı Teknolojileri Elektronik Dergisi 10(2), 1-11, 2016.
- Huang H. H., Luo J. Y., Tutumluer E., Hart J. M., Stolba A. J., Automated Segmentation and Morphological Analyses of Stockpile Aggregate Images using Deep Convolutional Neural Networks. Transportation Research Record 2674(10), 285-298, 2020.
- Huang T., Liu G. Q., Evaluation for coarse aggregate distribution of asphalt mixtures based on the two-dimensional digital image analysis. Construction and Building Materials 450, 138716, 2024.
- Kamani M., Ajalloeian R., Investigation of the changes in aggregate morphology during different aggregate abrasion/degradation tests using image analysis. Construction and Building Materials 314, 125614, 2022.
- Li H. J., Asbjörnsson G., Lindqvist M., Image Process of Rock Size Distribution Using DexiNed-Based Neural Network. Minerals 11(7), 736, 2021.
- Li M., Wang J., Guo Z. B., Chen J. C., Zhao Z. D., Ren J. L., Evaluation of the Adhesion between Aggregate and Asphalt Binder Based on Image Processing Techniques Considering Aggregate Characteristics. Materials 16(14), 5097, 2023.
Ayrıntılar
Birincil Dil
İngilizce
Konular
Derin Öğrenme
Bölüm
Araştırma Makalesi
Yayımlanma Tarihi
26 Aralık 2025
Gönderilme Tarihi
20 Ağustos 2025
Kabul Tarihi
18 Aralık 2025
Yayımlandığı Sayı
Yıl 1970 Cilt: 6 Sayı: 2
APA
Akgöl, K., & Tuna, M. C. (2025). Superpixel-Based Image Analysis for Stripping Detection in Asphalt Mixtures with ANN and U-Net Models. Journal of Materials and Mechatronics: A, 6(2), 442-462. https://doi.org/10.55546/jmm.1769352
AMA
1.Akgöl K, Tuna MC. Superpixel-Based Image Analysis for Stripping Detection in Asphalt Mixtures with ANN and U-Net Models. J. Mater. Mechat. A. 2025;6(2):442-462. doi:10.55546/jmm.1769352
Chicago
Akgöl, Kadir, ve Mehmet Can Tuna. 2025. “Superpixel-Based Image Analysis for Stripping Detection in Asphalt Mixtures with ANN and U-Net Models”. Journal of Materials and Mechatronics: A 6 (2): 442-62. https://doi.org/10.55546/jmm.1769352.
EndNote
Akgöl K, Tuna MC (01 Aralık 2025) Superpixel-Based Image Analysis for Stripping Detection in Asphalt Mixtures with ANN and U-Net Models. Journal of Materials and Mechatronics: A 6 2 442–462.
IEEE
[1]K. Akgöl ve M. C. Tuna, “Superpixel-Based Image Analysis for Stripping Detection in Asphalt Mixtures with ANN and U-Net Models”, J. Mater. Mechat. A, c. 6, sy 2, ss. 442–462, Ara. 2025, doi: 10.55546/jmm.1769352.
ISNAD
Akgöl, Kadir - Tuna, Mehmet Can. “Superpixel-Based Image Analysis for Stripping Detection in Asphalt Mixtures with ANN and U-Net Models”. Journal of Materials and Mechatronics: A 6/2 (01 Aralık 2025): 442-462. https://doi.org/10.55546/jmm.1769352.
JAMA
1.Akgöl K, Tuna MC. Superpixel-Based Image Analysis for Stripping Detection in Asphalt Mixtures with ANN and U-Net Models. J. Mater. Mechat. A. 2025;6:442–462.
MLA
Akgöl, Kadir, ve Mehmet Can Tuna. “Superpixel-Based Image Analysis for Stripping Detection in Asphalt Mixtures with ANN and U-Net Models”. Journal of Materials and Mechatronics: A, c. 6, sy 2, Aralık 2025, ss. 442-6, doi:10.55546/jmm.1769352.
Vancouver
1.Kadir Akgöl, Mehmet Can Tuna. Superpixel-Based Image Analysis for Stripping Detection in Asphalt Mixtures with ANN and U-Net Models. J. Mater. Mechat. A. 01 Aralık 2025;6(2):442-6. doi:10.55546/jmm.1769352