Edge-AI Based Real-Time Crack Detection and Severity Classification for Concrete Bridge Inspection Using Deep Convolutional Networks
Abstract
Routine visual inspection of concrete bridges is labour-intensive, subjective and increasingly impractical given India's expanding network of over 175 000 road bridges. This paper presents an edge-AI inspection platform that performs real-time crack detection, segmentation and severity classification onboard an unmanned aerial vehicle. A lightweight encoder–decoder network combining a MobileNet-V3 backbone with a U-Net decoder was trained on a curated dataset of 11 240 bridge surface images and deployed on an NVIDIA Jetson Orin Nano edge device. The proposed model achieved a mean intersection-over-union of 0.86 and a sustained inference rate of 22 frames per second at 512×512 input resolution, outperforming three baseline architectures while remaining within a 7 W power envelope. Field validation across two bridge structures in Karnataka demonstrated reliable detection of hairline through severe crack categories with geo-tagged outputs streamed to a cloud dashboard for engineering review
Keywords: Structural health monitoring; Crack segmentation; Edge AI; Convolutional neural networks; UAV inspection; Concrete bridges.
References
- [1] Liu, Y., Yao, J., Lu, X., Xie, R., & Li, L. (2023). DeepCrack: A deep hierarchical feature learning architecture for crack segmentation. Neurocomputing, 519, 234–246.
- [2] Howard, A., et al. (2024). Searching for MobileNetV3. Proceedings of the IEEE/CVF International Conference on Computer Vision, 1314–1324.
- [3] Ronneberger, O., Fischer, P., & Brox, T. (2022). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Analysis, 81, 102553.
- [4] Indian Roads Congress (2023). IRC SP-35: Guidelines for Inspection and Maintenance of Bridges. New Delhi: IRC.
- [5] Sharma, P., Reddy, V., & Iyer, K. (2025). UAV-based structural inspection of Indian highway bridges: A field study. Journal of Bridge Engineering, ASCE, 30(4), 04025012.
- [6] Chen, F.-C., & Jahanshahi, M. R. (2024). Edge-deployable deep networks for civil infrastructure monitoring: A review. Automation in Construction, 158, 105203.
- [7] NVIDIA Corporation (2024). Jetson Orin Nano Developer Kit Technical Specifications. Santa Clara, CA.
Explore Our Related Journals
Looking for the right journal for your next manuscript? Explore our international peer-reviewed journals covering engineering, management, computer science, artificial intelligence and multidisciplinary research.