Randomized trees for real-time keypoint recognition

In earlier work, we proposed treating wide baseline matching of feature points as a classification problem, in which each class corresponds to the set of all possible views of such a point. We used a K-mean plus Nearest Neighbor classifier to validate our approach, mostly because it was simple to im...

Full description

Saved in:
Bibliographic Details
Published in2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 2; pp. 775 - 781 vol. 2
Main Authors Lepetit, V., Lagger, P., Fua, P.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Cameras
Classification tree analysis
Computer vision
Laboratories
Lighting
Nearest neighbor searches
Object detection
Real time systems
Robustness
Online AccessGet full text

Cover

More Information
Summary:In earlier work, we proposed treating wide baseline matching of feature points as a classification problem, in which each class corresponds to the set of all possible views of such a point. We used a K-mean plus Nearest Neighbor classifier to validate our approach, mostly because it was simple to implement. It has proved effective but still too slow for real-time use. In this paper, we advocate instead the use of randomized trees as the classification technique. It is both fast enough for real-time performance and more robust. It also gives us a principled way not only to match keypoints but to select during a training phase those that are the most recognizable ones. This results in a real-time system able to detect and position in 3D planar, non-planar, and even deformable objects. It is robust to illuminations changes, scale changes and occlusions.
ISBN:0769523722
9780769523729
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2005.288