A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization
2023-06-17
会议录名称2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
ISSN1063-6919
发表状态已发表
DOI10.1109/CVPR52729.2023.00078
摘要We propose a novel visual-inertial odometry (VIO) initialization method, which decouples rotation and translation estimation, and achieves higher efficiency and better robustness. Existing loosely-coupled VIO-initialization methods suffer from poor stability of visual structure-frommotion (SfM), whereas those tightly-coupled methods often ignore the gyroscope bias in the closed-form solution, resulting in limited accuracy. Moreover, the aforementioned two classes of methods are computationally expensive, because 3D point clouds need to be reconstructed simultaneously. In contrast, our new method fully combines inertial and visual measurements for both rotational and translational initialization. First, a rotation-only solution is designed for gyroscope bias estimation, which tightly couples the gyroscope and camera observations. Second, the initial velocity and gravity vector are solved with linear translation constraints in a globally optimal fashion and without reconstructing 3D point clouds. Extensive experiments have demonstrated that our method is 8 similar to 72 times faster (w.r.t. a 10-frame set) than the state-of-the-art methods, and also presents significantly higher robustness and accuracy.
关键词3D from multi-view and sensors
会议名称IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
出版地10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA
会议地点Vancouver, BC, Canada
会议日期17-24 June 2023
URL查看原文
收录类别CPCI-S
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号WOS:001058542601005
出版者IEEE COMPUTER SOC
来源库IEEE
引用统计
被引频次:10[WOS]   [WOS记录]     [WOS相关记录]
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/333414
专题信息科学与技术学院_硕士生
通讯作者He, Yijia
作者单位
1.Chinese Acad Sci, Beijing, Peoples R China
2.Wuhan Univ, Wuhan, Peoples R China
3.ShanghaiTech Univ, Shanghai, Peoples R China
4.Australian Natl Univ, Canberra, ACT, Australia
推荐引用方式
GB/T 7714
He, Yijia,Xu, Bo,Ouyang, Zhanpeng,et al. A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE COMPUTER SOC,2023.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[He, Yijia]的文章
[Xu, Bo]的文章
[Ouyang, Zhanpeng]的文章
百度学术
百度学术中相似的文章
[He, Yijia]的文章
[Xu, Bo]的文章
[Ouyang, Zhanpeng]的文章
必应学术
必应学术中相似的文章
[He, Yijia]的文章
[Xu, Bo]的文章
[Ouyang, Zhanpeng]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。