A Real-Time Road Damage Detection System for IoT Edge Devices Using Lightweight Deep Learning Models

Road damage detection is essential for timely pavement maintenance and transportation safety. Traditional approaches, which rely on manual inspection, are both timeconsuming and labor-intensive. Although deep learning-based computer vision techniques have shown remarkable potential to surpass conventional methods, their real-world deployment remains challenging, primarily due to limitations in dataset diversity and the computational demands of complex models on resource-constrained hardware. To address these challenges in Internet of Things (IoT) environments, we propose an end-to-end road damage detection system optimized for edge deployment. Our approach begins with systematic video data collection using an industrial camera mounted on a moving vehicle. Experts then extract and manually annotate 13,528 frames, encompassing nine distinct categories of road damage and assets. Utilizing this dataset, we train a lightweight YOLOv5s network tailored for real-time detection. The model is subsequently quantized and deployed on an NVIDIA Jetson Xavier NX edge device. The detection results are transmitted to the cloud in real time, leveraging IoT infrastructure to enable scalable storage and analysis. The proposed system demonstrates a practical, efficient, and scalable solution for real-time road condition monitoring in industrial applications.