Abstract
Localization can be defined as the process of estimating the pose of an agent, given a representation of the environment and sensor input. In this work, we use
Topo-metric Appearance Maps to represent the environment, and introduce a new method for localization using only a camera. The method relies on local image
features detection, description and matching; by parallelizing these computationally intensive tasks on the graphical processing unit (GPU), it is possible to do online localization using a Topometric Appearance Map. The method is developed as an integral part of a mobile service robot system [1] , and empirically evaluated using
a real robot in a typical indoor environment.
Topo-metric Appearance Maps to represent the environment, and introduce a new method for localization using only a camera. The method relies on local image
features detection, description and matching; by parallelizing these computationally intensive tasks on the graphical processing unit (GPU), it is possible to do online localization using a Topometric Appearance Map. The method is developed as an integral part of a mobile service robot system [1] , and empirically evaluated using
a real robot in a typical indoor environment.
| Original language | English |
|---|---|
| Publication date | 2010 |
| Number of pages | 1 |
| Publication status | Published - 2010 |
| Event | Visionday 2010: Industrial - DTU, Kgs. Lyngby, Denmark Duration: 25 May 2010 → 28 May 2010 |
Conference
| Conference | Visionday 2010: Industrial |
|---|---|
| Location | DTU |
| Country/Territory | Denmark |
| City | Kgs. Lyngby |
| Period | 25/05/2010 → 28/05/2010 |