{"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/the-earth-aint-flat-monocular-reconstruction","title":"The Earth ain't Flat: Monocular Reconstruction of Vehicles on Steep and Graded Roads from a Moving Camera","arxiv_id":"1803.02057","date":"2018-03-06","proceeding":null,"authors":["Junaid Ahmed Ansari","Sarthak Sharma","Anshuman Majumdar","J. Krishna Murthy","K. Madhava Krishna"],"abstract":"Accurate localization of other traffic participants is a vital task in\nautonomous driving systems. State-of-the-art systems employ a combination of\nsensing modalities such as RGB cameras and LiDARs for localizing traffic\nparticipants, but most such demonstrations have been confined to plain roads.\nWe demonstrate, to the best of our knowledge, the first results for monocular\nobject localization and shape estimation on surfaces that do not share the same\nplane with the moving monocular camera. We approximate road surfaces by local\nplanar patches and use semantic cues from vehicles in the scene to initialize a\nlocal bundle-adjustment like procedure that simultaneously estimates the pose\nand shape of the vehicles, and the orientation of the local ground plane on\nwhich the vehicle stands as well. We evaluate the proposed approach on the\nKITTI and SYNTHIA-SF benchmarks, for a variety of road plane configurations.\nThe proposed approach significantly improves the state-of-the-art for monocular\nobject localization on arbitrarily-shaped roads.","url_abs":"http://arxiv.org/abs/1803.02057v1","url_pdf":"http://arxiv.org/pdf/1803.02057v1.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":"the-earth-aint-flat-monocular-reconstruction","repo_url":"https://github.com/sarthaksharma13/Earth-ain-t-Flat_IROS18","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"the-earth-aint-flat-monocular-reconstruction","repo_url":"https://github.com/sarthaksharma13/IROS18","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"the-earth-aint-flat-monocular-reconstruction","repo_url":"https://github.com/sarthaksharma13/RenderForCNN_KeypointGeneration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"the-earth-aint-flat-monocular-reconstruction","repo_url":"https://github.com/sarthaksharma13/RenderForCNN_annotation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"monocular-reconstruction","task_name":"Monocular Reconstruction"},{"task_slug":"object-localization","task_name":"Object Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.02057","atlas_url":"https://app.syntology.ai/?focus=1803.02057","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}