Robotics: Science and Systems IX

Realtime Registration-Based Tracking via Approximate Nearest Neighbour Search

Travis Dick, Camilo Perez, Martin Jagersand, Azad Shademan

Abstract:

We introduce a new 2D visual tracking algorithm that utilizes an approximate nearest neighbour search to estimate per-frame state updates. We experimentally demonstrate that the new algorithm is more efficient than the standard registration-based tracking algorithms and that it is capable of accurately estimating larger per-frame motions. Finally, the algorithm is demonstrated to be more robust in a vision-controlled robotic alignment task.

Download:

Bibtex:

  
@INPROCEEDINGS{Dick-RSS-13, 
    AUTHOR    = {Travis Dick AND Camilo Perez AND Martin Jagersand AND Azad Shademan}, 
    TITLE     = {Realtime Registration-Based Tracking via Approximate Nearest Neighbour Search}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2013}, 
    ADDRESS   = {Berlin, Germany}, 
    MONTH     = {June},
    DOI       = {10.15607/RSS.2013.IX.044} 
}