Amirkabir University of Technology Amirkabir Journal of Civil Engineering 2588-297X 52 9 2020 11 21 Pavement cracks detection and classification using deep convolutional networks Pavement cracks detection and classification using deep convolutional networks 2255 2278 3465 10.22060/ceej.2019.16103.6133 FA Sajad Ranjbar Department of Civil & Environmental Engineering, Amirkabir University of Technology Fereydoon Moghaddasnezhad Department of Civil & Environmental Engineering, Amirkabir University of Technology 0000-0003-3830-4555 HAMZEH ZAKERI RESEARCHER /AUT Journal Article 2019 04 13 Pavement inspection is one of the most important steps in the implementation of the pavement management system and extend efforts have been conducted to increase the efficiency of this system by using new technologies. In recent years, transportation agencies focus on creating automatic and more efficient systems for pavement inspection and a large number of researches have been done for this aim. According to the progress of computer science, data mining and machine learning as computer-based methods are used more in various areas (such as engineering, medical and economy), and significant results have been achieved. In the pavement management area, several researches have been performed to apply the machine learning, especially in pavement distresses evaluation. In this paper, the theoretical concepts have been explained, and several models have been created based on deep convolutional networks using transfer learning to detect and classify pavement cracks as the most prevalent pavement distress, and the performance of these models has been evaluated considering learning and test speed, and accuracy as the most important performance parameters. The results of this research indicate that the speed of models almost depends on the characteristics of pre-trained models that applied in the transfer learning process. Also, the accuracy of models based on various metrics (Sensitivity, F-score, etc.) is in range of 0.94 to 0.99 and indicates that deep learning method can be used to create expert systems for detection, classification, and quantification of pavement distresses such as cracking. Pavement inspection is one of the most important steps in the implementation of the pavement management system and extend efforts have been conducted to increase the efficiency of this system by using new technologies. In recent years, transportation agencies focus on creating automatic and more efficient systems for pavement inspection and a large number of researches have been done for this aim. According to the progress of computer science, data mining and machine learning as computer-based methods are used more in various areas (such as engineering, medical and economy), and significant results have been achieved. In the pavement management area, several researches have been performed to apply the machine learning, especially in pavement distresses evaluation. In this paper, the theoretical concepts have been explained, and several models have been created based on deep convolutional networks using transfer learning to detect and classify pavement cracks as the most prevalent pavement distress, and the performance of these models has been evaluated considering learning and test speed, and accuracy as the most important performance parameters. The results of this research indicate that the speed of models almost depends on the characteristics of pre-trained models that applied in the transfer learning process. Also, the accuracy of models based on various metrics (Sensitivity, F-score, etc.) is in range of 0.94 to 0.99 and indicates that deep learning method can be used to create expert systems for detection, classification, and quantification of pavement distresses such as cracking. https://ceej.aut.ac.ir/article_3465_797134c3e42371bb4979a462eb2f042a.pdf