Funding agency: NSERC and MTO
Description: With the advance of deep learning networks, their applications in the assessment of pavement conditions are gaining more attention. A convolutional neural network (CNN) is the most commonly used network in image classification. In terms of pavement assessment, most existing CNNs are designed to only distinguish between cracks and non-cracks. Few networks classify cracks in different levels of severity. Information on the severity of pavement cracks is critical for pavement repair services. In this study, the state-of-the-art CNN used in the detection of pavement cracks was improved to localize the cracks and identify their distress levels based on three categories (low, medium, and high). In addition, a fully convolutional network (FCN) and U-net were, for the first time, utilized in the detection of pavement cracks. These designed architectures were validated using the data acquired on four highways in Ontario, Canada, and compared with the ground truth that was provided by the Ministry of Transportation of Ontario (MTO)
the gif version of the pavement crack detection results.
They are in Input, Label, CNN with Structured Prediction, and FCN order.
Each gif file consists of 10 images with approximately 5s delay.
Publication
(1)Jung, W., F. Naveed, B. Hu, J. Wang, and N. Li, 2019, “Exploitation of deep learning in the automatic detection of cracks on paved roads”, Geomatica, dx.doi.org/10.1139/geomat-2019-0008.
