MRS-VPR: A multi-resolution sampling based global visual place recognition method

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	MRS-VPR: A multi-resolution sampling based global visual place recognition method
	Li, Xueqian 3; Xu LY(许凌云)5 ; Zhang HD(张宏达)5; He YQ(何玉庆)5 ; Ji JM(吉建民)4; Jia, Zhenzhong 3; Li, Lu 3; Chen, Yin 2; Srivatsan, Rangaprasad Arun 3; Yin P(殷鹏)5
	2019
会议日期	May 20-24, 2019
会议地点	Montreal, QC, Canada
页码	7137-7142
英文摘要	Place recognition and loop closure detection are challenging for long-term visual navigation tasks. SeqSLAM is considered to be one of the most successful approaches to achieve long-term localization under varying environmental conditions and changing viewpoints. SeqSLAM uses a brute-force sequential matching method, which is computationally intensive. In this work, we introduce a multi-resolution sampling-based global visual place recognition method (MRS-VPR), which can significantly improve the matching efficiency and accuracy in sequential matching. The novelty of this method lies in the coarse-to-fine searching pipeline and a particle filter-based global sampling scheme, that can balance the matching efficiency and accuracy in the long-term navigation task. Moreover, our model works much better than SeqSLAM when the testing sequence is over a much smaller time scale than the reference sequence. Our experiments demonstrate that MRSVPR is efficient in locating short temporary trajectories within long-term reference ones without compromising on the accuracy compared to SeqSLAM.
源文献作者	Bosch ; DJI ; et al. ; Kinova ; Mercedes-Benz ; Samsung
产权排序	1
会议录	2019 International Conference on Robotics and Automation, ICRA 2019
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISSN号	1050-4729
ISBN号	978-1-5386-6026-3
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/25518]
专题	沈阳自动化研究所_机器人学研究室
通讯作者	Yin P(殷鹏)
作者单位	1.School of Computer Science, University of Beijing University of Posts and Telecommunications, Beijing, China 2.15213, United States 3.Biorobotics Lab, Robotics Institute, Carnegie Mellon University, Pittsburgh PA 4.School of Computer Science and Technology, University of Science and Technology of China, Hefei Anhui, China 5.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Shenyang, Beijing, China
推荐引用方式 GB/T 7714	Li, Xueqian,Xu LY,Zhang HD,et al. MRS-VPR: A multi-resolution sampling based global visual place recognition method[C]. 见:. Montreal, QC, Canada. May 20-24, 2019.