Unsupervised place recognition for assistive mobile robots based on local feature descriptions.

Place recognition is an important perceptual robotic problem, especially in the navigation process. Previous place-recognition approaches have been used for solving ‘global localization’ and ‘kidnapped robot’ problems. Such approaches are usually performed in a supervised mode. In this paper, a robu...

Full description

Bibliographic Details
Main Authors: Tang, Sai Hong, Ramli, Abdul Rahman, Samsudin, Khairulmizam
Format: Article
Language:English
English
Published: SAGE Publications 2011
Online Access:http://psasir.upm.edu.my/id/eprint/23443/
http://psasir.upm.edu.my/id/eprint/23443/1/Unsupervised%20place%20recognition%20for%20assistive%20mobile%20robots%20based%20on%20local%20feature%20descriptions.pdf
_version_ 1848844759081156608
author Tang, Sai Hong
Ramli, Abdul Rahman
Samsudin, Khairulmizam
author_facet Tang, Sai Hong
Ramli, Abdul Rahman
Samsudin, Khairulmizam
author_sort Tang, Sai Hong
building UPM Institutional Repository
collection Online Access
description Place recognition is an important perceptual robotic problem, especially in the navigation process. Previous place-recognition approaches have been used for solving ‘global localization’ and ‘kidnapped robot’ problems. Such approaches are usually performed in a supervised mode. In this paper, a robust appearance-based unsupervised place clustering and recognition algorithm is introduced. This method fuses several image features using speed up robust features (SURF) by agglomerating them into a union form of features inside each place cluster. The number of place clusters can be extracted by investigating the SURF-based scene similarity diagram between adjacent images. During a human-guided learning step, the robot captures visual information acquired by an embedded camera and converts them into topological place clusters. Experimental results show the robustness, accuracy, and efficiency of the method, as well as its ability to create topological place clusters for solving global localization and kidnapped robot problems. The performance of the developed system is remarkable in terms of time, clustering error, and recognition precision.
first_indexed 2025-11-15T08:36:01Z
format Article
id upm-23443
institution Universiti Putra Malaysia
institution_category Local University
language English
English
last_indexed 2025-11-15T08:36:01Z
publishDate 2011
publisher SAGE Publications
recordtype eprints
repository_type Digital Repository
spelling upm-234432016-01-12T07:06:48Z http://psasir.upm.edu.my/id/eprint/23443/ Unsupervised place recognition for assistive mobile robots based on local feature descriptions. Tang, Sai Hong Ramli, Abdul Rahman Samsudin, Khairulmizam Place recognition is an important perceptual robotic problem, especially in the navigation process. Previous place-recognition approaches have been used for solving ‘global localization’ and ‘kidnapped robot’ problems. Such approaches are usually performed in a supervised mode. In this paper, a robust appearance-based unsupervised place clustering and recognition algorithm is introduced. This method fuses several image features using speed up robust features (SURF) by agglomerating them into a union form of features inside each place cluster. The number of place clusters can be extracted by investigating the SURF-based scene similarity diagram between adjacent images. During a human-guided learning step, the robot captures visual information acquired by an embedded camera and converts them into topological place clusters. Experimental results show the robustness, accuracy, and efficiency of the method, as well as its ability to create topological place clusters for solving global localization and kidnapped robot problems. The performance of the developed system is remarkable in terms of time, clustering error, and recognition precision. SAGE Publications 2011 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/23443/1/Unsupervised%20place%20recognition%20for%20assistive%20mobile%20robots%20based%20on%20local%20feature%20descriptions.pdf Tang, Sai Hong and Ramli, Abdul Rahman and Samsudin, Khairulmizam (2011) Unsupervised place recognition for assistive mobile robots based on local feature descriptions. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 225 (8). pp. 1068-1085. ISSN 0959-6518 10.1177/0959651811406641 English
spellingShingle Tang, Sai Hong
Ramli, Abdul Rahman
Samsudin, Khairulmizam
Unsupervised place recognition for assistive mobile robots based on local feature descriptions.
title Unsupervised place recognition for assistive mobile robots based on local feature descriptions.
title_full Unsupervised place recognition for assistive mobile robots based on local feature descriptions.
title_fullStr Unsupervised place recognition for assistive mobile robots based on local feature descriptions.
title_full_unstemmed Unsupervised place recognition for assistive mobile robots based on local feature descriptions.
title_short Unsupervised place recognition for assistive mobile robots based on local feature descriptions.
title_sort unsupervised place recognition for assistive mobile robots based on local feature descriptions.
url http://psasir.upm.edu.my/id/eprint/23443/
http://psasir.upm.edu.my/id/eprint/23443/
http://psasir.upm.edu.my/id/eprint/23443/1/Unsupervised%20place%20recognition%20for%20assistive%20mobile%20robots%20based%20on%20local%20feature%20descriptions.pdf