Name
Abstract | ||
|---|---|---|
We have previously developed a mobile robot system which uses scale invariant visual landmarks to localize and simultaneously build a 3D map of the environment In this paper, we look at global localization, also known as the kidnapped robot problem, where the robot localizes itself globally, without any prior location estimate. This is achieved by matching distinctive landmarks in the current frame to a database map. A Hough transform approach and a random sample consensus (RANSAC) approach for global localization are compared, showing that RANSAC is much more efficient. Moreover, robust global localization can be achieved by matching a small sub-map of the local region built from multiple frames. |
Year | DOI | Venue |
|---|---|---|
2002 | 10.1109/IRDS.2002.1041393 | IROS |
Keywords | Field | DocType |
scale invariant visual landmarks,distinctive landmark matching,visual databases,mobile robot system,global localization,mobile robots,ransac approach,computerised navigation,distinctive visual features,feature extraction,database map,hough transform,kidnapped robot problem,random sample consensus,3d map building,hough transforms,robot vision,mobile robot,simultaneous localization and mapping,databases,semiconductor device modeling,random sampling,scale invariance,intelligent sensors,robustness,navigation | Computer vision,Computer science,RANSAC,Hough transform,Feature extraction,Robustness (computer science),Artificial intelligence,Robot,Simultaneous localization and mapping,Mobile robot,Kidnapped robot problem | Conference |
Volume | ISBN | Citations |
1 | 0-7803-7398-7 | 75 |
PageRank | References | Authors |
24.46 | 13 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Stephen Se | 1 | 786 | 92.81 |
| D. G. Lowe | 2 | 15718 | 1413.60 |
| James J. Little | 3 | 2430 | 269.59 |