A Point-Line VIO System With Novel Feature Hybrids and With Novel Line Predicting-Matching

doi:10.1109/LRA.2021.3113987

	A Point-Line VIO System With Novel Feature Hybrids and With Novel Line Predicting-Matching
	Wei, Hao1,2 ; Tang, Fulin 2; Xu, Zewen 1,2; Zhang, Chaofan 3; Wu, Yihong1,2
发表期刊	IEEE ROBOTICS AND AUTOMATION LETTERS
ISSN	2377-3766
	2021-10-01
卷号	6 期号:4 页码:8681-8688
通讯作者	Zhang, Chaofan(zcfan@aiofm.ac.cn) ; Wu, Yihong(yihong.wu@ia.ac.cn)
摘要	Weak texture and motion blur are always challenging problems for visual-inertial odometry (VIO) systems. To improve accuracy of VIO systems in the challenging scenes, we propose a point-line-based VIO system with novel feature hybrids and with novel predicting-matching for long line track. Point-line features with shorter tracks are categorized into "MSCKF" features and with longer tracks into "SLAM" features. Especially, "SLAM" lines are added into the state vector to improve accuracy of the proposed system. Besides, to ensure the reliability and stability of detection and tracking of line features, we also propose a new "Predicting-Matching" line segment tracking method to increase the track lengths of line segments. Experimental results show that the proposed method outperforms the state-of-the-art methods of VINS-Mono [1], PL-VINS [2] and OpenVINS [3]) on both a public dataset and a collected dataset in terms of accuracy. The collected dataset is full of extremely weak textures and motion blurs. On this dataset, the proposed method also obtains better accuracy than ORB-SLAM3 [4].
关键词	Simultaneous localization and mapping Feature extraction Three-dimensional displays Tracking Jacobian matrices Motion segmentation Cameras Visual-Inertial SLAM SLAM
DOI	10.1109/LRA.2021.3113987
关键词[WOS]	ROBUST
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61836015] ; National Natural Science Foundation of China[62002359] ; Beijing Advanced Discipline Fund[115200S001]
项目资助者	National Natural Science Foundation of China ; Beijing Advanced Discipline Fund
WOS研究方向	Robotics
WOS类目	Robotics
WOS记录号	WOS:000704109700008
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	三维视觉
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/45754
专题	多模态人工智能系统全国重点实验室_机器人视觉
通讯作者	Zhang, Chaofan; Wu, Yihong
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China 3.Chinese Acad Sci, Hefei Inst Phys Sci, Anhui Inst Opt & Fine Mech, Hefei 230031, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Wei, Hao,Tang, Fulin,Xu, Zewen,et al. A Point-Line VIO System With Novel Feature Hybrids and With Novel Line Predicting-Matching[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2021,6(4):8681-8688.
APA	Wei, Hao,Tang, Fulin,Xu, Zewen,Zhang, Chaofan,&Wu, Yihong.(2021).A Point-Line VIO System With Novel Feature Hybrids and With Novel Line Predicting-Matching.IEEE ROBOTICS AND AUTOMATION LETTERS,6(4),8681-8688.
MLA	Wei, Hao,et al."A Point-Line VIO System With Novel Feature Hybrids and With Novel Line Predicting-Matching".IEEE ROBOTICS AND AUTOMATION LETTERS 6.4(2021):8681-8688.