{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/automatic-pavement-crack-detection-based-on","title":"Automatic Pavement Crack Detection Based on Structured Prediction with the Convolutional Neural Network","arxiv_id":"1802.02208","date":"2018-02-01","proceeding":null,"authors":["Zhun Fan","Yuming Wu","Jiewei Lu","Wenji Li"],"abstract":"Automated pavement crack detection is a challenging task that has been\nresearched for decades due to the complicated pavement conditions in real\nworld. In this paper, a supervised method based on deep learning is proposed,\nwhich has the capability of dealing with different pavement conditions.\nSpecifically, a convolutional neural network (CNN) is used to learn the\nstructure of the cracks from raw images, without any preprocessing. Small\npatches are extracted from crack images as inputs to generate a large training\ndatabase, a CNN is trained and crack detection is modeled as a multi-label\nclassification problem. Typically, crack pixels are much fewer than non-crack\npixels. To deal with the problem with severely imbalanced data, a strategy with\nmodifying the ratio of positive to negative samples is proposed. The method is\ntested on two public databases and compared with five existing methods.\nExperimental results show that it outperforms the other methods.","url_abs":"http://arxiv.org/abs/1802.02208v1","url_pdf":"http://arxiv.org/pdf/1802.02208v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"automatic-pavement-crack-detection-based-on","repo_url":"https://github.com/brijml/xcaliber-task","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}