This is a derived software of original class-specific Hough forest code.
Authors : Juergen Gall, BIWI, ETH Zurich : Nima Razavi, BIWI, ETH Zurich Email: gall@vision.ee.ethz.ch : razavi@vision.ee.ethz.ch
References:
Gall J. and Lempitsky V., Class-Specific Hough Forests for Object Detection, IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09), 2009.
Note that this is not the original software that was used for the paper mentioned above. It is a re-implementation for Linux.
Part of the code is added and/or modified by..
Author: Ishrat Badami, AIS, Uni-Bonn Germany. Email : badami@vision.rwth-aachen.de
Additional features of this software compared to original Class-specific Hough forest:
- This code works with RGB-Depth data.
- Object position can be estimated in 3D camera coordinate system.
- Cannonical continous pose of an object can be computed.
References:
Ishrat Badami, Jörg Stückler, and Sven Behnke, Depth-Enhanced Hough Forests for Object-Class Detection and Continuous Pose Estimation. In 3rd Workshop on Semantic Perception, Mapping and Exploration (SPME), Karlsruhe, in conjunction with ICRA 2013.