SIA OpenIR  > 水下机器人研究室
Underwater Loop-Closure Detection for Mechanical Scanning Imaging Sonar by Filtering the Similarity Matrix With Probability Hypothesis Density Filter
Jiang M(蒋敏)1,2,3; Song SM(宋三明)1,2; Herrmann, J. Michael4; Li, Jihong5; Li YP(李一平)1,2; Hu ZQ(胡志强)1,2; Li ZG(李智刚)1,2; Liu J(刘健)1,2; Li S(李硕)1,2; Feng XS(封锡盛)1,2
Department水下机器人研究室
Source PublicationIEEE Access
ISSN2169-3536
2019
Volume7Pages:166614-166628
Indexed BySCI ; EI
EI Accession number20200208022084
WOS IDWOS:000509585900035
Contribution Rank1
Funding OrganizationNatural Science Foundation of China under Grant 61973297 ; Strategic Priority Program of the Chinese Academy of Sciences under Grant XDC03060105 and Grant XDA13030203 ; State Key Laboratory of Robotics of China under Grant 2017-Z010 ; National Key Research and Development Program of China under Grant 2016YFC0300801, Grant 2016YFC0300604, and Grant 2016YFC0301601 ; Key Research Program of Frontier Sciences, Chinese Academy of Sciences (CAS), under Grant QYZDY-SSW-JSC005 ; Project of ``R&D Center for Underwater Construction Robotics'' through the Ministry of Ocean and Fisheries (MOF) ; Korea Institute of Marine Science and Technology Promotion (KIMST), South Korea, under Grant PJT200539 ; Public Science and Technology Research Funds Projects of Ocean under Grant 201505017 ; Project ``Field Demonstration and Industrialization of Heavy Duty ROV Technology'' through the Ministry of Ocean and Fisheries (MOF), South Korea, under Grant 20190396
KeywordForward-looking sonar intensity projection histogram PHD lter polar gradient matrix underwater loop-closure detection
Abstract

Robust and accurate estimation of position and attitude of a UUV (Unmanned Underwater Vehicle) from sonar scans is essential for simultaneous localization and mapping (SLAM). Both dead-reckoning based on the inertial navigation system and the motion parameter estimation based on the registration of the ultrasound scan sequence can contribute to the performance of the system. However, the rapidly-growing accumulated error tends to counteract the precise localization of the vehicle. In this paper, a method for loop-closure detection is proposed that adjusts the accumulated error for the underwater acoustic SLAM when the vehicle scans the underwater environment using an Mechanical Scanning Imaging Sonar (MSIS). Firstly, a similarity matrix for pairs of scans is constructed to represent the loop-closing tracks. In the registration step, two novel features, namely the intensity projection histograms and a polar gradient matrix, are extracted to calculate the translational and rotational parameters respectively. Secondly, the probability hypothesis density (PHD) filter is used to extract the possible loop-closure constraints from the similarity matrix, removing the random noise brought by accidental correlation and refining the concurrent loop-closing tracks resulted from long-range scanning. Lastly, the loop-closure constraints from the refined loop-closing tracks are fed into the GraphSLAM system to adjust the pose of each scan by constraint optimization. Experiments on the MSIS sonar images collected in structured and unstructured underwater environments validate the effectiveness of the proposed loop-closure detection method.

Language英语
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS KeywordDATA ASSOCIATION ; NAVIGATION ; SLAM ; LOCALIZATION ; EXPLORATION ; TIME
WOS Research AreaComputer Science ; Engineering ; Telecommunications
Funding ProjectNatural Science Foundation of China[61973297] ; Strategic Priority Program of the Chinese Academy of Sciences[XDC03060105] ; Strategic Priority Program of the Chinese Academy of Sciences[XDA13030203] ; State Key Laboratory of Robotics of China[2017-Z010] ; National Key Research and Development Program of China[2016YFC0300801] ; National Key Research and Development Program of China[2016YFC0300604] ; National Key Research and Development Program of China[2016YFC0301601] ; Key Research Program of Frontier Sciences, Chinese Academy of Sciences (CAS)[QYZDY-SSW-JSC005] ; Project of R&D Center for Underwater Construction Robotics'' through the Ministry of Ocean and Fisheries (MOF)[PJT200539] ; Korea Institute of Marine Science and Technology Promotion (KIMST), South Korea[PJT200539] ; Public Science and Technology Research Funds Projects of Ocean[201505017] ; Project Field Demonstration and Industrialization of Heavy Duty ROV Technology'' through the Ministry of Ocean and Fisheries (MOF), South Korea[20190396]
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/26038
Collection水下机器人研究室
Corresponding AuthorSong SM(宋三明)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
4.Institute of Perception, Action and Behaviour, The University of Edinburgh, Edinburgh EH8 9AB, U.K.
5.Marine Robotics R&D Division, Korea Institute of Robot and Convergence, Pohang 37666, South Korea
Recommended Citation
GB/T 7714
Jiang M,Song SM,Herrmann, J. Michael,et al. Underwater Loop-Closure Detection for Mechanical Scanning Imaging Sonar by Filtering the Similarity Matrix With Probability Hypothesis Density Filter[J]. IEEE Access,2019,7:166614-166628.
APA Jiang M.,Song SM.,Herrmann, J. Michael.,Li, Jihong.,Li YP.,...&Feng XS.(2019).Underwater Loop-Closure Detection for Mechanical Scanning Imaging Sonar by Filtering the Similarity Matrix With Probability Hypothesis Density Filter.IEEE Access,7,166614-166628.
MLA Jiang M,et al."Underwater Loop-Closure Detection for Mechanical Scanning Imaging Sonar by Filtering the Similarity Matrix With Probability Hypothesis Density Filter".IEEE Access 7(2019):166614-166628.
Files in This Item:
File Name/Size DocType Version Access License
Underwater Loop-Clos(2141KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Jiang M(蒋敏)]'s Articles
[Song SM(宋三明)]'s Articles
[Herrmann, J. Michael]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jiang M(蒋敏)]'s Articles
[Song SM(宋三明)]'s Articles
[Herrmann, J. Michael]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jiang M(蒋敏)]'s Articles
[Song SM(宋三明)]'s Articles
[Herrmann, J. Michael]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Underwater Loop-Closure Detection for Mechanical Scanning Imaging Sonar by Filtering the Similarity Matrix With Probability Hypothesis Density Filter.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.