CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 先进机器人
Learning Representative Features for Robot Topological Localization Regular Paper
Zhao, Zeng-Shun1,2; Feng, Xiang2; Wei, Fang2; Lin, Yan-Yan2; Li, Yi-Bin1; Hou, Zeng-Guang3; Tan, Min3
Source PublicationINTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS
2013-04-26
Volume10
SubtypeArticle
AbstractThis paper proposes a new method for mobile robots to recognize places with the use of a single camera and natural landmarks. In the learning stage, the robot is manually guided along a path. Video sequences are captured with a front-facing camera. To reduce the perceptual alias of visual features, which are easily confused, we propose a modified visual feature descriptor which combines the dominant hue colour information with the local texture. A Location Features Vocabulary Model (LVFM) is established for each individual location using an unsupervised learning algorithm. During the course of travelling, the robot employs each detected interest point to vote for the most likely place. The spatial relationships between the locations, modelled by the Hidden Markov Model (HMM), are exploited to increase the robustness of location recognition in cases of dynamic change or visual similarity. The proposed descriptors are compared with several state-of-the-art descriptors including SIFT, colour SIFT, GLOH and SURF. Experiments show that both the LVFM based on the dominant Hue-SIFT feature and the spatial relationships between the locations contribute considerably to the high recognition rate.
KeywordVision-based Localization Hidden Markov Model Invariant Feature Competitive Learning
WOS HeadingsScience & Technology ; Technology
DOI10.5772/56324
WOS KeywordMOBILE ROBOTS ; DESCRIPTORS ; NAVIGATION
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(60805028 ; Natural Science Foundation of Shandong Province(ZR2010FM027) ; China Postdoctoral Science Foundation(2012M521336) ; Open Research Project from SKLMCCS(20120105) ; SDUST Research Fund(2010KYTD101) ; 61175076 ; 61225017)
WOS Research AreaRobotics
WOS SubjectRobotics
WOS IDWOS:000318219300002
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/3493
Collection复杂系统管理与控制国家重点实验室_先进机器人
Affiliation1.Shandong Univ, Sch Control Sci & Engn, Jinan 250100, Peoples R China
2.Shandong Univ Sci & Technol, Coll Informat & Elect Engn, Qingdao, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
Recommended Citation
GB/T 7714
Zhao, Zeng-Shun,Feng, Xiang,Wei, Fang,et al. Learning Representative Features for Robot Topological Localization Regular Paper[J]. INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS,2013,10.
APA Zhao, Zeng-Shun.,Feng, Xiang.,Wei, Fang.,Lin, Yan-Yan.,Li, Yi-Bin.,...&Tan, Min.(2013).Learning Representative Features for Robot Topological Localization Regular Paper.INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS,10.
MLA Zhao, Zeng-Shun,et al."Learning Representative Features for Robot Topological Localization Regular Paper".INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 10(2013).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao, Zeng-Shun]'s Articles
[Feng, Xiang]'s Articles
[Wei, Fang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao, Zeng-Shun]'s Articles
[Feng, Xiang]'s Articles
[Wei, Fang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao, Zeng-Shun]'s Articles
[Feng, Xiang]'s Articles
[Wei, Fang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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