A Cost Effective Solution for Road Crack Inspection using Cameras and Deep Neural Networks

TL;DR

This paper presents a cost-effective, camera-based deep learning approach for road crack detection that achieves state-of-the-art accuracy, using a novel neural network architecture and connectivity maps to improve detection reliability.

Contribution

It introduces ConnCrack, a novel neural network method combining Wasserstein GAN and connectivity maps for improved crack detection accuracy.

Findings

Achieves state-of-the-art precision, recall, and F1 scores.

Uses a low-cost GoPro camera for data collection.

Demonstrates effectiveness on public and collected datasets.

Abstract

Automatic crack detection on pavement surfaces is an important research field in the scope of developing an intelligent transportation infrastructure system. In this paper, a cost effective solution for road crack inspection by mounting commercial grade sport camera, GoPro, on the rear of the moving vehicle is introduced. Also, a novel method called ConnCrack combining conditional Wasserstein generative adversarial network and connectivity maps is proposed for road crack detection. In this method, a 121-layer densely connected neural network with deconvolution layers for multi-level feature fusion is used as generator, and a 5-layer fully convolutional network is used as discriminator. To overcome the scattered output issue related to deconvolution layers, connectivity maps are introduced to represent the crack information within the proposed ConnCrack. The proposed method is tested on a publicly available dataset as well our collected data. The results show that the proposed method achieves state-of-the-art performance compared with other existing methods in terms of precision, recall and F1 score.