Error aware multiple vertical planes based visual localization for mobile robots in urban environments

IMR OpenIR

	Error aware multiple vertical planes based visual localization for mobile robots in urban environments
其他题名	Error aware multiple vertical planes based visual localization for mobile robots in urban environments
	Li HaiFeng 1; Wang HongPeng 2; Liu JingTai 2
	2015
发表期刊	SCIENCE CHINA-INFORMATION SCIENCES
ISSN	1674-733X
卷号	58 期号:3
摘要	A novel error-aware visual localization method is proposed that utilizes vertical planes, such as vertical building facades in urban areas as landmarks. Vertical planes, reconstructed from coplanar vertical lines, are robust high-level features if compared with point features or line features. Firstly, the error models of vertical lines and vertical planes are built, where maximum likelihood estimation (MLE) is employed to estimate all vertical planes from coplanar vertical lines. Then, the closed-form representation of camera location error variance is derived. Finally, the minimum variance camera pose estimation is formulated into a convex optimization problem, and the weight for each vertical plane is obtained by solving this well-studied problem. Experiments are carried out and the results show that the proposed localization method has an accuracy of about 2 meters, at par with commercial GPS operating in open environments.
其他摘要	A novel error-aware visual localization method is proposed that utilizes vertical planes, such as vertical building facades in urban areas as landmarks. Vertical planes, reconstructed from coplanar vertical lines, are robust high-level features if compared with point features or line features. Firstly, the error models of vertical lines and vertical planes are built, where maximum likelihood estimation (MLE) is employed to estimate all vertical planes from coplanar vertical lines. Then, the closed-form representation of camera location error variance is derived. Finally, the minimum variance camera pose estimation is formulated into a convex optimization problem, and the weight for each vertical plane is obtained by solving this well-studied problem. Experiments are carried out and the results show that the proposed localization method has an accuracy of about 2 meters, at par with commercial GPS operating in open environments.
关键词	SLAM IMAGE visual localization multiple vertical planes error aware convex optimization satellite images urban environment mobile robot
收录类别	CSCD
语种	英语
资助项目	[National Natural Science Foundation of China] ; [Fundamental Research Funds for the Central Universities] ; [Pre-research Major Project of Civil Aviation University of China] ; [Scientific Research Funds for Civil Aviation University of China] ; [State Key Laboratory of Robotics]
CSCD记录号	CSCD:5386556
引用统计
文献类型	期刊论文
条目标识符	http://ir.imr.ac.cn/handle/321006/156754
专题	中国科学院金属研究所
作者单位	1.Civil Aviat University China, Coll Comp Sci & Technol, Tianjin 300300, Peoples R China 2.Nankai Univ, Institute Robot & Automat Informat Syst, Tianjin 300071, Peoples R China 3.中国科学院金属研究所
推荐引用方式 GB/T 7714	Li HaiFeng,Wang HongPeng,Liu JingTai. Error aware multiple vertical planes based visual localization for mobile robots in urban environments[J]. SCIENCE CHINA-INFORMATION SCIENCES,2015,58(3).
APA	Li HaiFeng,Wang HongPeng,&Liu JingTai.(2015).Error aware multiple vertical planes based visual localization for mobile robots in urban environments.SCIENCE CHINA-INFORMATION SCIENCES,58(3).
MLA	Li HaiFeng,et al."Error aware multiple vertical planes based visual localization for mobile robots in urban environments".SCIENCE CHINA-INFORMATION SCIENCES 58.3(2015).