{"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/roadtracer-automatic-extraction-of-road","title":"RoadTracer: Automatic Extraction of Road Networks from Aerial Images","arxiv_id":"1802.03680","date":"2018-02-11","proceeding":"CVPR 2018 6","authors":["Favyen Bastani","Songtao He","Sofiane Abbar","Mohammad Alizadeh","Hari Balakrishnan","Sanjay Chawla","Sam Madden","David DeWitt"],"abstract":"Mapping road networks is currently both expensive and labor-intensive.\nHigh-resolution aerial imagery provides a promising avenue to automatically\ninfer a road network. Prior work uses convolutional neural networks (CNNs) to\ndetect which pixels belong to a road (segmentation), and then uses complex\npost-processing heuristics to infer graph connectivity. We show that these\nsegmentation methods have high error rates because noisy CNN outputs are\ndifficult to correct. We propose RoadTracer, a new method to automatically\nconstruct accurate road network maps from aerial images. RoadTracer uses an\niterative search process guided by a CNN-based decision function to derive the\nroad network graph directly from the output of the CNN. We compare our approach\nwith a segmentation method on fifteen cities, and find that at a 5% error rate,\nRoadTracer correctly captures 45% more junctions across these cities.","url_abs":"http://arxiv.org/abs/1802.03680v2","url_pdf":"http://arxiv.org/pdf/1802.03680v2.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":"roadtracer-automatic-extraction-of-road","repo_url":"https://github.com/mitroadmaps/roadtracer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"road-segementation","task_name":"Road Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"roadtracer","name":"RoadTracer","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.03680","atlas_url":"https://app.syntology.ai/?focus=1802.03680","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}