An Innovative UAV-Bridge Crack Detection System Using Deep Learning

  • Authors

    • Anthony Stone Computer Science Department, Southern Connecticut State University, CT, USA
    • Alaa Sheta Computer Science Department, Southern Connecticut State University, CT, USA
    https://doi.org/10.14419/k9sznk28

    Received date: January 4, 2026

    Accepted date: February 13, 2026

    Published date: February 23, 2026

  • Bridge Crack Inspection; Computer Vision; Convolutional Neural Network; Unmanned Aerial Vehicle; Structural Health Monitoring

  • Abstract

    Concrete bridge degradation and cracking are phenomena prevalent among a significant portion of bridges in the United States. The risks and high costs associated with bridge repair and restoration necessitate effective structural health monitoring paradigms that rely on accurate, timely, and efficient inspection methodologies. This study proposes an efficient inspection system based on unmanned aerial vehicles and computer vision. We use a specialized dataset of bridge crack visual data to train a convolutional neural network to classify images as containing a crack or not. We adopt a lightweight transfer-learning approach, leveraging the EfficientNetB0 model for rapid model development and deployment. We deploy this model for application in a case study on bridge health inspection, using a modeled concrete bridge in a simulated environment. The RYZE DJI Tello drone was used to navigate the space and capture optical data for real-time autonomous crack detection. The proposed methodology demonstrates the efficacy of such an approach in structural health monitoring.

  • References

    1. American Road & Transportation Builders Association, “2025 Bridge Report”, (2025), available online: https://artbabridgereport.org/reports/2025-
    2. ARTBA-Bridge-Report.pdf.
    3. B. Zhang, Y. Ren, S. He, Z. Gao, B. Li, and J. Song, “A review of methods and applications in structural health monitoring (SHM) for bridges”,
    4. Measurement, Vol. 245, (2025), pp. 116575.
    5. C. Kralovec and M. Schagerl, “Review of Structural Health Monitoring Methods Regarding a Multi-Sensor Approach for Damage Assessment of Metal
    6. and Composite Structures”, Sensors (Basel), Vol. 20, No. 3, (2020), pp. 826.
    7. B. J. Perry, Y. Guo, R. Atadero, and J. W. van de Lindt, “Streamlined bridge inspection system utilizing unmanned aerial vehicles (UAVs) and machine
    8. learning”, Measurement, Vol. 164, (2020), pp. 108048.
    9. D. Gillins, C. Parrish, M. Gillins, and C. Simpson, “EYES IN THE SKY: BRIDGE INSPECTIONS WITH UNMANNED AERIAL”, Oregon Department
    10. of Transportation, (2018).
    11. J. Wells and B. Lovelace, “Unmanned Aircraft System Bridge Inspection Demonstration Project Phase II Final Report”, Minnesota Department of
    12. Transportation, (2017).
    13. F. Gouveia, V. Silva, J. Lopes, et al., “Automated Identification of Building Features with Deep Learning for Risk Analysis”, Discover Applied Sciences,
    14. Vol. 6, (2024), pp. 466.
    15. D. Ai, G. Jiang, S.-K. Lam, P. He, and C. Li, “Computer vision framework for crack detection of civil infrastructure—A review”, Engineering
    16. Applications of Artificial Intelligence, Vol. 117, (2023), pp. 105478.
    17. R. Fu, M. Cao, D. Nov ´ak, X. Qian, and N. F. Alkayem, “Extended efficient convolutional neural network for concrete crack detection with illustrated
    18. merits”, Automation in Construction, Vol. 156, (2023), pp. 105098.
    19. D. Choi, W. Bell, D. Kim, and J. Kim, “UAV-Driven Structural Crack Detection and Location Determination Using Convolutional Neural Networks”,
    20. Sensors, Vol. 21, No. 8, (2021), pp. 2650.
    21. A. Karmokar, N. Jani, A. Kalla, H. Harlalka, and P. Sonar, “Inspection of Concrete Structures by a Computer Vision Technique and an Unmanned
    22. Aerial Vehicle”, 2020 International Conference on Computational Performance Evaluation (ComPE), (2020), pp. 338–343.
    23. J. Plested and T. Gedeon, “Deep Transfer Learning for Image Classification: A Survey”, arXiv preprint arXiv:2205.09904, (2022).
    24. C. F. Ozgenel and A. Gonenc Sorguc, “Performance Comparison of Pretrained Convolutional Neural Networks on Crack Detection in Buildings”,
    25. Proceedings of ISARC 2018.
    26. A. Mirzazade, C. Popescu, J. Gonzalez-Libreros, T. Blanksv ¨ard, B. T ¨aljsten, and G. Sas, “Semi-autonomous inspection for concrete structures using
    27. digital models and a hybrid approach based on deep learning and photogrammetry”, Journal of Civil Structural Health Monitoring, Vol. 13, No. 8,
    28. (2023), pp. 1633–1652.
    29. X. Wang, Y. R. Tan, W. Leong, S. Huang, R. Teo, and C. Xiang, “GPS Denied IBVS-Based Navigation and Collision Avoidance of UAV Using a
    30. Low-Cost RGB Camera”, arXiv preprint arXiv:2509.17435v1, (2025).
    31. Z. Ameli, Y. Aremanda, W. A. Friess, and E. N. Landis, “Impact of UAV Hardware Options on Bridge Inspection Mission Capabilities”, Drones, Vol. 6,
    32. No. 3, (2022), pp. 64.
    33. RYZE, “Tello”, (2025), available online: https://www.ryzerobotics.com/tello.
    34. DJI Tello, “Tello - DJITelloPy API Reference”, available online: https://djitellopy.readthedocs.io/en/latest/tello/.
    35. M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks”, arXiv preprint arXiv:1905.11946, (2020), available
    36. online: https://arxiv.org/abs/1905.11946.
    37. H. Zoubir, M. Rguig, and M. Elaroussi, “Crack recognition automation in concrete bridges using Deep Convolutional Neural Networks”, MATEC Web
    38. of Conferences, Vol. 349, (2021), pp. 03014.

  • Downloads

  • How to Cite

    Stone, A. ., & Sheta, A. (2026). An Innovative UAV-Bridge Crack Detection System Using Deep Learning. Journal of Advanced Computer Science & Technology, 13(1), 11-18. https://doi.org/10.14419/k9sznk28