Raw Data for A Lightweight Deep Learning for Real-Time Road Distress Detection on Mobile Devices

This dataset supports the research presented in the paper “A Lightweight Deep Learning for Real-Time Road Distress Detection on Mobile Devices.” The dataset contains annotated road distress images collected from diverse locations across Europe and Asia, ensuring robustness and generalizability. It includes raw images, preprocessed data, and corresponding labels used for model training, validation, and testing. The dataset is designed to facilitate the development and benchmarking of lightweight deep learning models for real-time road distress detection on resource-constrained devices, such as smartphones and mixed reality (MR) systems.