Speedup robust features based unsupervised place recognition for assistive mobile robot
Vision Based qualitative localization or in the other word place recognition is an important perceptual problem at the center of several fundamental robot procedures. Place recognition approaches are utilized to solve the “global localization” problem. These methods are typically performed in a supe...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
IEEE
2011
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/68662/1/Speedup%20robust%20features%20based%20unsupervised%20place%20recognition%20for%20assistive%20mobile%20robot.pdf |
| _version_ | 1796978779770322944 |
|---|---|
| author | Karasfi, Babak Tang, Sai Hong Jalalian, Afsaneh Nakhaeinia, Danial |
| author_facet | Karasfi, Babak Tang, Sai Hong Jalalian, Afsaneh Nakhaeinia, Danial |
| author_sort | Karasfi, Babak |
| collection | UPM |
| description | Vision Based qualitative localization or in the other word place recognition is an important perceptual problem at the center of several fundamental robot procedures. Place recognition approaches are utilized to solve the “global localization” problem. These methods are typically performed in a supervised mode. In this paper an appearance-based unsupervised place clustering and recognition algorithm are introduced. This method fuses several image features using Speedup Robust Features (SURF) by agglomerating them into the 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. Experimental results show that this method is robust, accurate, efficient and able to create topological place clusters for solving the “global localization” problem with acceptable performance by the factor of clustering error and recognition precision. |
| first_indexed | 2024-03-06T09:59:19Z |
| format | Conference or Workshop Item |
| id | upm.eprints-68662 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T09:59:19Z |
| publishDate | 2011 |
| publisher | IEEE |
| record_format | dspace |
| spelling | upm.eprints-686622019-06-10T02:45:32Z http://psasir.upm.edu.my/id/eprint/68662/ Speedup robust features based unsupervised place recognition for assistive mobile robot Karasfi, Babak Tang, Sai Hong Jalalian, Afsaneh Nakhaeinia, Danial Vision Based qualitative localization or in the other word place recognition is an important perceptual problem at the center of several fundamental robot procedures. Place recognition approaches are utilized to solve the “global localization” problem. These methods are typically performed in a supervised mode. In this paper an appearance-based unsupervised place clustering and recognition algorithm are introduced. This method fuses several image features using Speedup Robust Features (SURF) by agglomerating them into the 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. Experimental results show that this method is robust, accurate, efficient and able to create topological place clusters for solving the “global localization” problem with acceptable performance by the factor of clustering error and recognition precision. IEEE 2011 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/68662/1/Speedup%20robust%20features%20based%20unsupervised%20place%20recognition%20for%20assistive%20mobile%20robot.pdf Karasfi, Babak and Tang, Sai Hong and Jalalian, Afsaneh and Nakhaeinia, Danial (2011) Speedup robust features based unsupervised place recognition for assistive mobile robot. In: 2011 International Conference on Pattern Analysis and Intelligent Robotics (ICPAIR 2011), 28-29 June 2011, Putrajaya, Malaysia. (pp. 97-102). 10.1109/ICPAIR.2011.5976919 |
| spellingShingle | Karasfi, Babak Tang, Sai Hong Jalalian, Afsaneh Nakhaeinia, Danial Speedup robust features based unsupervised place recognition for assistive mobile robot |
| title | Speedup robust features based unsupervised place recognition for assistive mobile robot |
| title_full | Speedup robust features based unsupervised place recognition for assistive mobile robot |
| title_fullStr | Speedup robust features based unsupervised place recognition for assistive mobile robot |
| title_full_unstemmed | Speedup robust features based unsupervised place recognition for assistive mobile robot |
| title_short | Speedup robust features based unsupervised place recognition for assistive mobile robot |
| title_sort | speedup robust features based unsupervised place recognition for assistive mobile robot |
| url | http://psasir.upm.edu.my/id/eprint/68662/1/Speedup%20robust%20features%20based%20unsupervised%20place%20recognition%20for%20assistive%20mobile%20robot.pdf |
| work_keys_str_mv | AT karasfibabak speeduprobustfeaturesbasedunsupervisedplacerecognitionforassistivemobilerobot AT tangsaihong speeduprobustfeaturesbasedunsupervisedplacerecognitionforassistivemobilerobot AT jalalianafsaneh speeduprobustfeaturesbasedunsupervisedplacerecognitionforassistivemobilerobot AT nakhaeiniadanial speeduprobustfeaturesbasedunsupervisedplacerecognitionforassistivemobilerobot |