消息
×
loading..
Efficient Globally-Optimal Correspondence-Less Visual Odometry for Planar Ground Vehicles
2020-05-01
会议录名称PROCEEDINGS - IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION
ISSN1050-4729
页码2696-2702
发表状态已发表
DOI10.1109/ICRA40945.2020.9196595
摘要The motion of planar ground vehicles is often non-holonomic, and as a result may be modelled by the 2 DoF Ackermann steering model. We analyse the feasibility of estimating such motion with a downward facing camera that exerts fronto-parallel motion with respect to the ground plane. This turns the motion estimation into a simple image registration problem in which we only have to identify a 2-parameter planar homography. However, one difficulty that arises from this setup is that ground-plane features are indistinctive and thus hard to match between successive views. We encountered this difficulty by introducing the first globally-optimal, correspondence-less solution to plane-based Ackermann motion estimation. The solution relies on the branch-and-bound optimisation technique. Through the low-dimensional parametrisation, a derivation of tight bounds, and an efficient implementation, we demonstrate how this technique is eventually amenable to accurate real-time motion estimation. We prove its property of global optimality and analyse the impact of assuming a locally constant centre of rotation. Our results on real data finally demonstrate a significant advantage over the more traditional, correspondence-based hypothesise-and-test schemes. © 2020 IEEE.
会议录编者/会议主办者IEEE
关键词Intelligent robots Branch and bound method Computer vision Ground vehicles Ackermann steering Efficient implementation Global optimality Optimisation techniques Planar homography Real time motion estimation Registration problems Visual odometry
会议名称2020 IEEE International Conference on Robotics and Automation, ICRA 2020
出版地NEW YORK
会议地点Paris, France
会议日期May 31, 2020 - August 31, 2020
URL查看原文
收录类别EI ; CPCI-S
语种英语
WOS研究方向Automation & Control Systems ; Engineering ; Robotics
WOS类目Automation & Control Systems ; Engineering, Electrical & Electronic ; Robotics
WOS记录号WOS:000712319502002
出版者Institute of Electrical and Electronics Engineers Inc., United States
EI入藏号20204309375278
EI主题词Motion estimation
EISSN2577-087X
EI分类号723.5 Computer Applications ; 731.6 Robot Applications ; 741.2 Vision ; 921.5 Optimization Techniques
原始文献类型Conference article (CA)
来源库IEEE
引用统计
正在获取...
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/251839
专题信息科学与技术学院
信息科学与技术学院_PI研究组_Laurent Kneip组
信息科学与技术学院_本科生
信息科学与技术学院_博士生
作者单位
School of School of Information Science and Technology, ShanghaiTech University
第一作者单位信息科学与技术学院
第一作者的第一单位信息科学与技术学院
推荐引用方式
GB/T 7714
Ling Gao,Junyan Su,Jiadi Cui,et al. Efficient Globally-Optimal Correspondence-Less Visual Odometry for Planar Ground Vehicles[C]//IEEE. NEW YORK:Institute of Electrical and Electronics Engineers Inc., United States,2020:2696-2702.
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
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Ling Gao]的文章
[Junyan Su]的文章
[Jiadi Cui]的文章
百度学术
百度学术中相似的文章
[Ling Gao]的文章
[Junyan Su]的文章
[Jiadi Cui]的文章
必应学术
必应学术中相似的文章
[Ling Gao]的文章
[Junyan Su]的文章
[Jiadi Cui]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 10.1109@ICRA40945.2020.9196595.pdf
格式: Adobe PDF
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。