{"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/relocalization-global-optimization-and-map","title":"Relocalization, Global Optimization and Map Merging for Monocular Visual-Inertial SLAM","arxiv_id":"1803.01549","date":"2018-03-05","proceeding":null,"authors":["Tong Qin","Perliang Li","Shaojie Shen"],"abstract":"The monocular visual-inertial system (VINS), which consists one camera and\none low-cost inertial measurement unit (IMU), is a popular approach to achieve\naccurate 6-DOF state estimation. However, such locally accurate visual-inertial\nodometry is prone to drift and cannot provide absolute pose estimation.\nLeveraging history information to relocalize and correct drift has become a hot\ntopic. In this paper, we propose a monocular visual-inertial SLAM system, which\ncan relocalize camera and get the absolute pose in a previous-built map. Then\n4-DOF pose graph optimization is performed to correct drifts and achieve global\nconsistent. The 4-DOF contains x, y, z, and yaw angle, which is the actual\ndrifted direction in the visual-inertial system. Furthermore, the proposed\nsystem can reuse a map by saving and loading it in an efficient way. Current\nmap and previous map can be merged together by the global pose graph\noptimization. We validate the accuracy of our system on public datasets and\ncompare against other state-of-the-art algorithms. We also evaluate the map\nmerging ability of our system in the large-scale outdoor environment. The\nsource code of map reuse is integrated into our public code, VINS-Mono.","url_abs":"http://arxiv.org/abs/1803.01549v1","url_pdf":"http://arxiv.org/pdf/1803.01549v1.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":"relocalization-global-optimization-and-map","repo_url":"https://github.com/HKUST-Aerial-Robotics/VINS-Mono","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"state-estimation","task_name":"State Estimation"},{"task_slug":"global-optimization","task_name":"global-optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}