{"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/agricolmap-aerial-ground-collaborative-3d","title":"AgriColMap: Aerial-Ground Collaborative 3D Mapping for Precision Farming","arxiv_id":"1810.00457","date":"2018-09-30","proceeding":null,"authors":["Ciro Potena","Raghav Khanna","Juan Nieto","Roland Siegwart","Daniele Nardi","Alberto Pretto"],"abstract":"The combination of aerial survey capabilities of Unmanned Aerial Vehicles\nwith targeted intervention abilities of agricultural Unmanned Ground Vehicles\ncan significantly improve the effectiveness of robotic systems applied to\nprecision agriculture. In this context, building and updating a common map of\nthe field is an essential but challenging task. The maps built using robots of\ndifferent types show differences in size, resolution and scale, the associated\ngeolocation data may be inaccurate and biased, while the repetitiveness of both\nvisual appearance and geometric structures found within agricultural contexts\nrender classical map merging techniques ineffective. In this paper we propose\nAgriColMap, a novel map registration pipeline that leverages a grid-based\nmultimodal environment representation which includes a vegetation index map and\na Digital Surface Model. We cast the data association problem between maps\nbuilt from UAVs and UGVs as a multimodal, large displacement dense optical flow\nestimation. The dominant, coherent flows, selected using a voting scheme, are\nused as point-to-point correspondences to infer a preliminary non-rigid\nalignment between the maps. A final refinement is then performed, by exploiting\nonly meaningful parts of the registered maps. We evaluate our system using real\nworld data for 3 fields with different crop species. The results show that our\nmethod outperforms several state of the art map registration and matching\ntechniques by a large margin, and has a higher tolerance to large initial\nmisalignments. We release an implementation of the proposed approach along with\nthe acquired datasets with this paper.","url_abs":"http://arxiv.org/abs/1810.00457v2","url_pdf":"http://arxiv.org/pdf/1810.00457v2.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":"agricolmap-aerial-ground-collaborative-3d","repo_url":"https://github.com/cirpote/AgriColMap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}