Fig. 3: Summary of dataset composition and augmentation.
From: Lightweight deep learning for real-time road distress detection on mobile devices
a Collection and generation of images of road distress. Categorized into four types: longitudinal cracks, transverse cracks, alligator cracks, and broken pavement markings. Each category includes images captured under four conditions: (i) parallel view, (ii) oblique view, (iii) rainy weather, and (iv) nighttime. b Dataset used in experiments. c Comparison of experimental results for the MobileNet family models.
