A visual landmark framework for indoor mobile robot navigation
- 25 June 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 3942-3947 vol.4
- https://doi.org/10.1109/robot.2002.1014344
Abstract
Presents vision functions needed on a mobile robot to deal with landmark-based navigation in buildings. Landmarks are planar, quadrangular surfaces, which must be distinguished from the background, typically a poster on a wall or a door-plate. In a first step, these landmarks are detected and their positions with respect to a global reference frame are learned; this learning step is supervised so that only the best landmarks are memorized, with an invariant representation based on a set of interest points. Then, when the robot looks for visible landmarks, the recognition procedure takes advantage of the partial Hausdorff distance to compare the landmark model and the detected quadrangles. The paper presents the landmark detection and recognition procedures, and discusses their performances.Keywords
This publication has 5 references indexed in Scilit:
- Combining scene and auto-calibration constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Comparing and evaluating interest pointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- Local grayvalue invariants for image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Comparing images using the Hausdorff distancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- On the Foundations of Relaxation Labeling ProcessesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1983