Lightweight Structured Line Map Based Visual Localization

doi:10.1109/LRA.2024.3387137

CASIA OpenIR > 中科院工业视觉智能装备工程实验室 > 精密感知与控制

	Lightweight Structured Line Map Based Visual Localization
	Liu, Hongmin 1,2; Cao, Chengyang 1,2; Ye, Hanqiao 3,4,5,6; Cui, Hainan3,4,5,6 ; Gao, Wei3,4,5,6 ; Wang, Xing 7; Shen, Shuhan3,4,5,6
发表期刊	IEEE ROBOTICS AND AUTOMATION LETTERS
ISSN	2377-3766
	2024-06-01
卷号	9 期号:6 页码:5182-5189
通讯作者	Shen, Shuhan(shshen@nlpr.ia.ac.cn)
摘要	Visual localization, also known as camera pose estimation, is a crucial component of many applications, such as robotics, autonomous driving, and augmented reality. Traditional visual localization algorithms typically run on point cloud maps generated by algorithms such as Structure-from-Motion (SfM) or Simultaneous Localization and Mapping (SLAM). However, point features are sensitive to weak textures and illumination changes. In addition, the generated 3D point cloud maps often contain millions of points, which puts higher demands on device storage and computing resources. To address these challenges, we propose a visual localization algorithm based on lightweight structured line maps. Instead of extracting and matching point features in the images, we select line segments that represent structured scene information as image features. These line segments are then used to construct a lightweight line map containing rich structured scene information. The camera pose is then estimated through a series of steps that include line extraction, matching, initial pose estimation, and pose refinement. Experimental results on benchmark datasets show that our method achieves competitive localization accuracy compared to current state-of-the-art visual localization methods, while significantly reducing the memory footprint of the 3D map.
关键词	Visual localization line segments lightweight structured line map pose estimation
DOI	10.1109/LRA.2024.3387137
关键词[WOS]	POSE ESTIMATION ; CORRESPONDENCES ; EFFICIENT
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China
项目资助者	National Natural Science Foundation of China
WOS研究方向	Robotics
WOS类目	Robotics
WOS记录号	WOS:001209593700010
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/57051
专题	中科院工业视觉智能装备工程实验室_精密感知与控制
通讯作者	Shen, Shuhan
作者单位	1.Univ Sci & Technol Beijing, Sch Intelligence Sci & Technol, Beijing 100083, Peoples R China 2.Univ Sci & Technol Beijing, Inst Artificial Intelligence, Beijing 100083, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 5.Luoyang Inst Robot & Intelligent Equipment, Luoyang 471003, Peoples R China 6.CASIA SenseTime Res Grp, Beijing 100190, Peoples R China 7.Beijing Electromech Engn Res Inst, Sci & Technol Complex Syst Control & Intelligent A, Beijing 100074, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Liu, Hongmin,Cao, Chengyang,Ye, Hanqiao,et al. Lightweight Structured Line Map Based Visual Localization[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2024,9(6):5182-5189.
APA	Liu, Hongmin.,Cao, Chengyang.,Ye, Hanqiao.,Cui, Hainan.,Gao, Wei.,...&Shen, Shuhan.(2024).Lightweight Structured Line Map Based Visual Localization.IEEE ROBOTICS AND AUTOMATION LETTERS,9(6),5182-5189.
MLA	Liu, Hongmin,et al."Lightweight Structured Line Map Based Visual Localization".IEEE ROBOTICS AND AUTOMATION LETTERS 9.6(2024):5182-5189.