Ferns: Planar Object Detection Demo

Planar object detection software that uses Fern based classification to match feature points. Includes template based tracking to switch between detection/tracking. (Tracking is NOT enabled by default, see usage notes on how to turn it on.)


Source code is available under the GNU General Public License. In short, if you distribute a software that uses ferns-demo, you have to distribute it under GPL with the source code. Another option is to contact us to purchase a commercial license.

Updated code: Fixed minor issues with the svn version of OpenCV and the newer gcc distributions.


The distributed code assumes that you have already installed OpenCV and pkg-config is properly configured to locate it. (Ask for help from your local Unix expert if this does not mean much.)


Download the archive, untar the contents: tar -xzvf ferns_demo-1.1.tar.gz
Change directory: cd ferns_demo-1.1
Create the executable: make
Run the executable (webcam input): ./ferns-demo
Run the executable (test video): ./ferns-demo -v mousepad.mp4

For more information see README file inside the tarball.

V. Lepetit; P. Fua : Keypoint Recognition using Random Forests and Random Ferns; Decision Forests for Computer Vision and Medical Image Analysis; Springer, 2013. p. 111-124.
M. Özuysal; M. Calonder; V. Lepetit; P. Fua : Fast Keypoint Recognition using Random Ferns; IEEE Transactions on Pattern Analysis and Machine Intelligence. 2010. DOI : 10.1109/TPAMI.2009.23.

Download article.

M. Ozuysal; P. Fua; V. Lepetit : Fast Keypoint Recognition in Ten Lines of Code. 2007. IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, June 18-23, 2007.

Download article.

V. Lepetit; P. Fua : Keypoint Recognition using Randomized Trees; Transactions on Pattern Analysis and Machine Intelligence. 2006.

Download article.