A cost effective solution for pavement crack inspection using cameras and deep neural networks. (30th September 2020)

• Record Type: Journal Article
• Authors: Mei, Qipei; Gül, Mustafa
• Is Part Of: Construction & building materials. Volume 256(2020)
• Publication Date: 2020-09-30
• Subjects: Camera -- Pavement crack detection -- Deep learning -- Conditional Wasserstein generative adversarial network -- Connectivity map; Building materials -- Periodicals; 624.18
• DOI: 10.1016/j.conbuildmat.2020.119397
• Languages: English
• ISSNs: 0950-0618

Abstract

Highlights: A cost effective way to inspect cracks on road surfaces using a commercial-grade sport camera is presented. Generative adversarial networks and connectivity maps are used for crack detection. A dataset including 600 images collected from the roads is released together with this paper. 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 the 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.