An Efficient Two Stage Detection Segmentation Framework for Automated Road Crack Assessment
DOI:
https://doi.org/10.29408/edumatic.v10i1.33699Keywords:
infrastructure monitoring, road crack, semantic segmentation, ssd-mobilenetv3, u-netAbstract
Road cracks significantly degrade infrastructure quality and pose a threat to traffic safety. To minimize manual inspection inefficiencies, this study investigates a segmentation model integrating MobileNetV3-Small as a backbone for the U-Net architecture to reduce processing time. The performance of the proposed MobileNetV3-Small-U-Net is benchmarked against a standard U-Net using three public datasets: DeepCrack (537 images), CFD (118 images), and Crack500 (3368 images) sourced from GitHub and Kaggle. This research explores the influence of optimization algorithms on evaluation results across these diverse datasets. Specifically, the study evaluates Adam, RMSprop, and SGD optimizers at an image resolution of 224 x 224 pixels, with a 0.001 learning rate and 0.9 momentum. On-the-fly augmentation techniques, including horizontal flips and brightness adjustments (0.8 to 1.2), were implemented during training. Experimental results demonstrate that MobileNetV3-Small-U-Net enhances computational efficiency by achieving a 9 ms inference time, which is 2 ms faster than the standard U-Net. These findings confirm that a MobileNetV3-Small backbone accelerates inference, despite a slight trade-off in evaluation metrics. Additionally, results reveal that the SGD optimizer is unsuitable for these segmentation tasks due to high error rates and the lack of an adaptive learning rate.
References
Abdusalomov, A., Umirzakova, S., Kutlimuratov, A., Mirzaev, D., Dauletov, A., Botirov, T., Zakirova, M., Mukhiddinov, M., & Cho, Y. I. (2025). Lightweight UAV-Based System for Early Fire-Risk Identification in Wild Forests. Fire, 8(8). https://doi.org/10.3390/fire8080288
Cao, H., Gao, Y., Cai, W., Xu, Z., & Li, L. (2023). Segmentation Detection Method for Complex Road Cracks Collected by UAV Based on HC-Unet++. Drones, 7(3). https://doi.org/10.3390/drones7030189
Deng, L., Zhang, A., Guo, J., & Liu, Y. (2023). An Integrated Method for Road Crack Segmentation and Surface Feature Quantification under Complex Backgrounds. Remote Sensing, 15(6). https://doi.org/10.3390/rs15061530
Dharma, A. S., Pardosi, C. N. S., & Silaen, Z. P. (2025). Comparative Performance of Yolov8 and Ssd-mobilenet Algorithms for Road Damage Detection in Mobile Applications. Sinkron, 9(3), 1159–1169. https://doi.org/10.33395/sinkron.v9i3.15008
Dogo, E. M., Afolabi, O. J., & Twala, B. (2022). On the Relative Impact of Optimizers on Convolutional Neural Networks with Varying Depth and Width for Image Classification. Applied Sciences (Switzerland), 12(23). https://doi.org/10.3390/app122311976
He, M., & Lau, T. L. (2024). CrackHAM: A Novel Automatic Crack Detection Network Based on U-Net for Asphalt Pavement. IEEE Access, 12, 12655–12666. https://doi.org/10.1109/ACCESS.2024.3353729
Jia, J., Zhang, M., Zhang, J., & Jing, C. (2026). Cracking Characteristics of Asphalt Pavement Under Thermal Stresses. Materials, 19(4), 771. https://doi.org/10.3390/ma19040771
Joy, J., Ram, B. G., & Sun, X. (2026). Real-time deep learning segmentation for agricultural applications: Insights for precision weed management. Smart Agricultural Technology, 13, 101894. https://doi.org/10.1016/j.atech.2026.101894
Kompanets, A., Duits, R., Pai, G., Leonetti, D., & Snijder, H. H. (Bert). (2025). Loss function inversion for improved crack segmentation in steel bridges using a CNN framework. Automation in Construction, 170, 105896. https://doi.org/10.1016/j.autcon.2024.105896
Liu, Y., Du, X., & Li, W. (2026). DCP-TransUNet: An Approach for Crack Segmentation on Roads. Sensors, 26(3). https://doi.org/10.3390/s26031071
López, P., Zubasti, P., García, J., & Molina, J. M. (2026). A UAV-Based Framework for Visual Detection and Geospatial Mapping of Real Road Surface Defects. Drones, 10(2), 119. https://doi.org/10.3390/drones10020119
Lourenco, M., Caetano, D., Mora, A., Oliveira, L. B., & Oliveira, H. (2025). Accurate Rural Road Network With Improved Dataset for Strengthen Wildfire Emergency Response. IEEE Access, 13, 146983–147001. https://doi.org/10.1109/ACCESS.2025.3600192
Luo, J., Lin, H., Wei, X., & Wang, Y. (2023). Adaptive Canny and Semantic Segmentation Networks Based on Feature Fusion for Road Crack Detection. IEEE Access, 11, 51740–51753. https://doi.org/10.1109/ACCESS.2023.3279888
Mayya, A. M., & Alkayem, N. F. (2024). Enhance the Concrete Crack Classification Based on a Novel Multi-Stage YOLOV10-ViT Framework. Sensors, 24(24). https://doi.org/10.3390/s24248095
Mehmood, F., Ahmad, S., & Whangbo, T. K. (2023). An Efficient Optimization Technique for Training Deep Neural Networks. Mathematics, 11(6). https://doi.org/10.3390/math11061360
Morellos, A., Dolaptsis, K., Tziotzios, G., Pantazi, X. E., Kateris, D., Berruto, R., & Bochtis, D. (2024). An IoT Transfer Learning-Based Service for the Health Status Monitoring of Grapevines. Applied Sciences (Switzerland), 14(3). https://doi.org/10.3390/app14031049
Patel, R., Rajput, P. A., Prabhu, G., Sharma, P., & Karthik, G. M. (2026). Deep learning-driven automated microstructural quantification in tungsten heavy alloys using U-net segmentation and image processing. International Journal of Refractory Metals and Hard Materials, 138, 107719. https://doi.org/https://doi.org/10.1016/j.ijrmhm.2026.107719
Trigka, M., & Dritsas, E. (2025). A Comprehensive Survey of Machine Learning Techniques and Models for Object Detection. Sensors, 25(1). https://doi.org/10.3390/s25010214
Valero-Carreras, D., Alcaraz, J., & Landete, M. (2023). Comparing two SVM models through different metrics based on the confusion matrix. Computers and Operations Research, 152, 106131. https://doi.org/10.1016/j.cor.2022.106131
Xu, Y., Xia, Y., Zhao, Q., Yang, K., & Li, Q. (2024). A Road Crack Segmentation Method Based on Transformer and Multi-Scale Feature Fusion. Electronics (Switzerland), 13(12), 1–21. https://doi.org/10.3390/electronics13122257
Yu, J., Qian, S., & Chen, C. (2024). Lightweight Crack Automatic Detection Algorithm Based on TF-MobileNet. Applied Sciences (Switzerland), 14(19). https://doi.org/10.3390/app14199004
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Alvin Hujaya, Muhammad Rizky Pribadi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All articles in this journal are the sole responsibility of the authors. Edumatic: Jurnal Pendidikan Informatika can be accessed free of charge, in accordance with the Creative Commons license used.
This work is licensed under a Lisensi a Creative Commons Attribution-ShareAlike 4.0 International License.
