Deep convolutional generative adversarial network-based synthesis of datasets for road pavement distress segmentation

Abstract

We discuss a range of problems relating to road pavement defects detection and modern approaches to their solution. The presented comparison of publicly available datasets allows one to make a conclusion that the problem of segmentation of road pavement defects in driver wide-view road images is difficult and poorly investigated. To solve this problem, we have developed algorithms for generating a synthetic dataset for cracks and potholes distress based on computer graphics methods and deep convolutional generative adversarial networks. A comparison of the accuracy of road distress segmentation was performed by training a fully convolutional neural network U-Net on real and combined datasets.