Efficient Solution to PnP Problem Based on Vision Geometry

doi:10.1109/LRA.2023.3333740

	Efficient Solution to PnP Problem Based on Vision Geometry
	Qixuan Sun 1; Tianyu Zhang 1; Guanghui Zhang 1; Kaifang Wang 1; Dongchen Zhu 1; Jiamao Li 1; Xiaolin Zhang1,2
	2024
发表期刊	IEEE ROBOTICS AND AUTOMATION LETTERS (IF:4.6[JCR-2023],5.5[5-Year])
ISSN	2377-3774
EISSN	2377-3766
卷号	9 期号:4 页码:3100-3107
发表状态	已发表
DOI	10.1109/LRA.2023.3333740
摘要	Perspective-n-Point (PnP) problem aims to estimate pose from known 3D map points and their projections. Efficient PnP (EPnP), one of the classical PnP solvers, represents camera pose with control points, which are easier to estimate utilizing the least square (LS) formulation. However, the geometry refinement procedure performed by most EPnP-based methods is separated from the solution of LS formulation, which creates difficulty in balancing between minimizing the loss function and preserving the essential geometry properties of control points. To handle the problem, we propose a novel method to integrate geometry constraints into control points formulation and reformulate the LS to quadratic constraints quadratic programming (QCQP). We deduce an innovative analytical solution, dubbed ACEPnP, to the constrained EPnP problem, which is faster than the customarily applied numerical methods. An uncertainty-aware least square registration procedure is designed in ACEPnP to compute camera pose from control points. Our method is plug-and-play and can be embedded in various variants of EPnP. Experiments in synthetic and real data show that our methods outperform other state-of-the-arts. Compared to the best PnP solver, EPnPU*, our approaches reduce rotation errors by 12.2% and translation errors by 34.8% with similar time consumption on the KITTI odometry dataset.
关键词	Localization SLAM vision-based navigation
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20234815120719
EI主题词	Cameras
EI分类号	722.2 Computer Peripheral Equipment ; 731.5 Robotics ; 742.2 Photographic Equipment ; 921 Mathematics ; 921.6 Numerical Methods
原始文献类型	Journal article (JA)
来源库	IEEE
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/354965
专题	信息科学与技术学院_特聘教授组_张晓林组
作者单位	1.Bionic Vision System Laboratory, State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China 2.ShanghaiTech University, Shanghai, China
推荐引用方式 GB/T 7714	Qixuan Sun,Tianyu Zhang,Guanghui Zhang,et al. Efficient Solution to PnP Problem Based on Vision Geometry[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2024,9(4):3100-3107.
APA	Qixuan Sun.,Tianyu Zhang.,Guanghui Zhang.,Kaifang Wang.,Dongchen Zhu.,...&Xiaolin Zhang.(2024).Efficient Solution to PnP Problem Based on Vision Geometry.IEEE ROBOTICS AND AUTOMATION LETTERS,9(4),3100-3107.
MLA	Qixuan Sun,et al."Efficient Solution to PnP Problem Based on Vision Geometry".IEEE ROBOTICS AND AUTOMATION LETTERS 9.4(2024):3100-3107.