Before BRIEF, we developed a fast method for keypoint recognition based on classification. We first used Randomized Trees as the classifier, and then developed the Ferns, a simplified version relying on a Naive Bayesian approach for better performances.
Videos
click on each image to download the video
Test Sequences
Original frames (259Mb !).
Relevant Publications
Compact Signatures for High-speed Interest Point Description and Matching
M. Calonder; V. Lepetit; P. Fua; K. Konolige; J. Bowman et al.
2009. IEEE International Conference on Computer Vision, Kyoto, JAPAN, Sep 29-Oct 02, 2009. p. 357-364. DOI : 10.1109/ICCV.2009.5459272. Keypoint Signatures for Fast Learning and Recognition
M. Calonder; V. Lepetit; P. Fua
2008. European Conference on Computer Vision, Marseille, FRANCE, Oct 12-18, 2008. p. 58-71. DOI : 10.1007/978-3-540-88682-2_6. Keypoint Signatures for Fast Learning and Recognition
M. Calonder; V. Lepetit; P. Fua
2008. European Conference on Computer Vision, Marseilles, October 2008. p. 58-71. DOI : 10.1007/978-3-540-88682-2_6. Fast Keypoint Recognition using Random Ferns
M. Özuysal; M. Calonder; V. Lepetit; P. Fua
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2010. Vol. 32, num. 3, p. 448-461. DOI : 10.1109/TPAMI.2009.23. Keypoint Recognition using Randomized Trees
V. Lepetit; P. Fua
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006. Vol. 28, num. 9, p. 1465-1479. DOI : 10.1109/TPAMI.2006.188.
