Name
Abstract | ||
|---|---|---|
The problem of place recognition is central to robot map learning. A robot needs to be able to recognize when it has returned to a previously visited place, or at least to be able to estimate the likelihood that it has been at a place before. Our approach is to compare images taken at two places, using a stochastic model of changes due to shift, zoom, and occlusion to predict the probability that one of them could be a perturbation of the other. We have performed experiments to gather the valve of a χ2 statistic applied to image matching from a variety of indoor locations. Image pairs gathered from nearby locations generate low χ2 values, and images gathered from different locations generate high values. The rate of false positive and false negative matches is low |
Year | DOI | Venue |
|---|---|---|
1998 | 10.1109/ROBOT.1998.680722 | Robotics and Automation, 1998. Proceedings. 1998 IEEE International Conference |
Keywords | Field | DocType |
estimation theory,image matching,mobile robots,navigation,object recognition,path planning,probability,robot vision,statistical analysis,autonomous mobile robots,estimation theory,image matching,probability,robot vision,statistical analysis,stochastic model,visual place recognition | Motion planning,Computer vision,Statistic,Computer science,Zoom,Pixel,Artificial intelligence,Estimation theory,Robot,Mobile robot,Cognitive neuroscience of visual object recognition | Conference |
Volume | ISSN | ISBN |
3 | 1050-4729 | 0-7803-4300-X |
Citations | PageRank | References |
4 | 0.47 | 10 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hemant D. Tagare | 1 | 113 | 20.58 |
| Drew V. Mcdermott | 2 | 1554 | 386.24 |
| Hong Xiao | 3 | 4 | 0.47 |