GPO:Global Plane Optimization for Fast and Accurate Monocular SLAM Initialization | |
Du SC(杜思聪)2,3; Guo HK(郭亨凯)1; Chen Y(陈尧)1; Lin YL(林懿伦)2,3; Meng XB(孟祥冰)2,3; Wen LF(文林福)1; Wang FY(王飞跃)2,3 | |
2020 | |
会议日期 | 2020.5.31-2020.8.31 |
会议地点 | 法国巴黎线上会议 |
英文摘要 | Initialization is essential to monocular Simultaneous Localization and Mapping (SLAM) problems. This paper focuses on a novel initialization method for monocular SLAM based on planar features. The algorithm starts by homography estimation in a sliding window. It then proceeds to a global plane optimization (GPO) to obtain camera poses and the plane normal. 3D points can be recovered using planar constraints without triangulation. The proposed method fully exploits the plane information from multiple frames and avoids the ambiguities in homography decomposition. We validate our algorithm on the collected chessboard dataset against baseline implementations and present extensive analysis. Experimental results show that our method outperforms the fine-tuned baselines in both accuracy and real-time. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44694] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
通讯作者 | Meng XB(孟祥冰) |
作者单位 | 1.字节跳动 2.复杂系统管理与控制国家重点实验室,中国科学院自动化研究所 3.中国科学院大学 |
推荐引用方式 GB/T 7714 | Du SC,Guo HK,Chen Y,et al. GPO:Global Plane Optimization for Fast and Accurate Monocular SLAM Initialization[C]. 见:. 法国巴黎线上会议. 2020.5.31-2020.8.31. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论