Attentional Landmark Selection for Visual SLAM

Simone Frintrop and Patric Jensfelt and Henrik I. Christensen,

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.

BibTeX Entry:

@InProceedings{Frintrop06b,
  author =       {S. Frintrop and P. Jensfelt and H. I. Christensen},
  title =        {Attentional Landmark Selection for Visual SLAM},
  booktitle =    {Proc.~of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'06)},
  year =         2006,
  address =      {Beijing, China}
}

Download: pdf (444k)