Title:
Attentional Landmark Selection for Visual SLAM
Attentional Landmark Selection for Visual SLAM
Files
Author(s)
Frintrop, Simone
Jensfelt, Patric
Christensen, Henrik I.
Jensfelt, Patric
Christensen, Henrik I.
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
In this paper, we introduce a new method to
automatically detect useful landmarks for visual SLAM. A
biologically motivated attention system detects regions of interest
which “pop-out” automatically due to strong contrasts and the
uniqueness of features. This property makes the regions easily
redetectable and thus they are useful candidates for visual landmarks.
Matching based on scene prediction and feature similarity
allows not only short-term tracking of the regions, but also
redetection in loop closing situations. The paper demonstrates
how regions are determined and how they are matched reliably.
Various experimental results on real-world data show that the
landmarks are useful with respect to be tracked in consecutive
frames and to enable closing loops.
Sponsor
Date Issued
2006-10
Extent
Resource Type
Text
Resource Subtype
Article