{"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/feature-pyramid-and-hierarchical-boosting","title":"Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection","arxiv_id":"1901.06340","date":"2019-01-18","proceeding":null,"authors":["Fan Yang","Lei Zhang","Sijia Yu","Danil Prokhorov","Xue Mei","Haibin Ling"],"abstract":"Pavement crack detection is a critical task for insuring road safety. Manual\ncrack detection is extremely time-consuming. Therefore, an automatic road crack\ndetection method is required to boost this progress. However, it remains a\nchallenging task due to the intensity inhomogeneity of cracks and complexity of\nthe background, e.g., the low contrast with surrounding pavements and possible\nshadows with similar intensity. Inspired by recent advances of deep learning in\ncomputer vision, we propose a novel network architecture, named Feature Pyramid\nand Hierarchical Boosting Network (FPHBN), for pavement crack detection. The\nproposed network integrates semantic information to low-level features for\ncrack detection in a feature pyramid way. And, it balances the contribution of\nboth easy and hard samples to loss by nested sample reweighting in a\nhierarchical way. To demonstrate the superiority and generality of the proposed\nmethod, we evaluate the proposed method on five crack datasets and compare it\nwith state-of-the-art crack detection, edge detection, semantic segmentation\nmethods. Extensive experiments show that the proposed method outperforms these\nstate-of-the-art methods in terms of accuracy and generality.","url_abs":"http://arxiv.org/abs/1901.06340v2","url_pdf":"http://arxiv.org/pdf/1901.06340v2.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":"feature-pyramid-and-hierarchical-boosting","repo_url":"https://github.com/fyangneil/pavement-crack-detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"crack500","name":"CRACK500","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.06340","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}