Training for Task Specific Keypoint Detection

In this paper, we show that a better performance can be achieved by training a keypoint detector to only find those points that are suitable to the needs of the given task. We demonstrate our approach in an urban environment, where the keypoint detector should focus on stable man-made structures and ignore objects that undergo natural changes such as vegetation and clouds. We use Wald-Boost learning with task specific training samples in order to train a keypoint detector with this capability. We show that our aproach generalizes to a broad class of problems where the task is known beforehand.


Published in:
Pattern Recognition, Proceedings, 5748, 151-160
Presented at:
DAGM Symposium on Pattern Recognition, Jena, GERMANY, Sep 09-11, 2009
Year:
2009
Publisher:
Springer-Verlag New York, Ms Ingrid Cunningham, 175 Fifth Ave, New York, Ny 10010 Usa
ISBN:
978-3-642-03797-9
Keywords:
Laboratories:




 Record created 2011-12-16, last modified 2018-03-17

Preprint:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)