Real-time SLAM relocalization with online learning of binary feature indexing

doi:10.1007/s00138-017-0873-z

	Real-time SLAM relocalization with online learning of binary feature indexing
	Feng, Youji 1,2; Wu, Yihong2 ; Fan, Lixin 3
发表期刊	MACHINE VISION AND APPLICATIONS
	2017-11-01
卷号	28 期号:8 页码:953-963
文章类型	Article
摘要	A visual simultaneous localization and mapping (SLAM) system usually contains a relocalization module to recover the camera pose after tracking failure. The core of this module is to establish correspondences between map points and key points in the image, which is typically achieved by local image feature matching. Since recently emerged binary features have orders of magnitudes higher extraction speed than traditional features such as scale invariant feature transform, they can be applied to develop a real-time relocalization module once an efficient method of binary feature matching is provided. In this paper, we propose such a method by indexing binary features with hashing. Being different from the popular locality sensitive hashing, the proposed method constructs the hash keys by an online learning process instead of pure randomness. Specifically, the hash keys are trained with the aim of attaining uniform hash buckets and high collision rates of matched feature pairs, which makes the method more efficient on approximate nearest neighbor search. By distributing the online learning into the simultaneous localization and mapping process, we successfully apply the method to SLAM relocalization. Experiments show that camera poses can be recovered in real time even when there are tens of thousands of landmarks in the map.
关键词	Slam Relocalization Binary Feature Indexing Approximate Nearest Neighbor Search
WOS标题词	Science & Technology ; Technology
DOI	10.1007/s00138-017-0873-z
收录类别	SCI
语种	英语
项目资助者	National High Technology Research and Development Program(2015AA0 20504) ; National Natural Science Foundation of China(61572499 ; Nokia Research(LF14011659182) ; 61421004)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics ; Engineering, Electrical & Electronic
WOS记录号	WOS:000413677000009
引用统计	被引频次：8[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/173211/20746
专题	多模态人工智能系统全国重点实验室_机器人视觉
作者单位	1.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 3.Nokia Technol, Tampere, Finland
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Feng, Youji,Wu, Yihong,Fan, Lixin. Real-time SLAM relocalization with online learning of binary feature indexing[J]. MACHINE VISION AND APPLICATIONS,2017,28(8):953-963.
APA	Feng, Youji,Wu, Yihong,&Fan, Lixin.(2017).Real-time SLAM relocalization with online learning of binary feature indexing.MACHINE VISION AND APPLICATIONS,28(8),953-963.
MLA	Feng, Youji,et al."Real-time SLAM relocalization with online learning of binary feature indexing".MACHINE VISION AND APPLICATIONS 28.8(2017):953-963.