A multilayered approach to location recognition

Outlined here is a framework for an autonomous mobile robot system for recognizing and mapping locations. The Scale Invariant Feature Transform is a powerful machine vision technique, but performs poorly on uniform colored or low contrast objects. We therefore set out to complement SIFT with other m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wimpey, B.J., Drucker, E., Martin, M., Potter, W.D.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Outlined here is a framework for an autonomous mobile robot system for recognizing and mapping locations. The Scale Invariant Feature Transform is a powerful machine vision technique, but performs poorly on uniform colored or low contrast objects. We therefore set out to complement SIFT with other machine vision techniques for a robust location recognition system in order to create better fingerprints of locations.
ISSN:1091-0050
1558-058X
DOI:10.1109/SECON.2009.5174077