Knowledge Commons of Institute of Automation,CAS
A Partial Sparsification Scheme for Visual-Inertial Odometry | |
Zhu ZK(朱志凯)1,2 | |
2020-07-06 | |
会议名称 | 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM) |
会议日期 | 2020-07-06 |
会议地点 | Virtual Conference |
摘要 | In this paper, we present a partial sparsification scheme for the marginalization of visual inertial odometry (VIO) systems. Sliding window optimization is widely used in VIO systems to guarantee constant complexity by optimizing over a set of recent states and marginalizing out past ones. The marginalization step introduces fill-in between variables incident to the marginalized ones, and most VIO systems discard measurements targeted at active landmark points to maintain sparsity of the marginalized information matrix, at the expense of potential information loss. The scheme is to first retain the dense prior from the marginalization excluding visual measurements, followed by a dense marginalization step that connects landmarks. The dense marginalization prior is then partially sparsified to extract pseudo factors that maintain the overall sparsity while minimizing the information loss. The proposed scheme is tested on public datasets and achieves appreciable results compared with several state-of-the-art approaches. The test also demonstrates that our scheme is applicable to real-time operations. |
收录类别 | EI |
七大方向——子方向分类 | 机器人感知与决策 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44853 |
专题 | 复杂系统认知与决策实验室_决策指挥与体系智能 |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhu ZK. A Partial Sparsification Scheme for Visual-Inertial Odometry[C],2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
root.pdf(1115KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Zhu ZK(朱志凯)]的文章 |
百度学术 |
百度学术中相似的文章 |
[Zhu ZK(朱志凯)]的文章 |
必应学术 |
必应学术中相似的文章 |
[Zhu ZK(朱志凯)]的文章 |
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