Pedestrians detection using Hough forests
This a linux port of the original code provided by Olga Barinova from the Vision Group at Moscow State University, 2010.
Please visit the project website for more details.
This derivative work follows the Microsoft Research Shared Source license, which allows only non-comercial usage.
See original README.txt and MSR-SSLA.txt for more details.
Citing in publications
When using this software, please acknowledge the effort that went into development by referencing the paper:
Barinova O., Lempitsky V., Kohli P.,
On detection of multiple object instances using Hough transform,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10), 2010.
Note that this is not the original software that was used for the paper mentioned above. It is a re-implementation.
This linux version requires:
All of these are provided as packages in the mainstream linux distributions.
- Move inside the
cmake ./ && maketo build the program
- Download the tud-campus and tud-crossing test sequences.
example/campus-config.txtto fit your local path
- Make sure the configuration text file is stored in Unix (LF) style line ending
You should see progress messages being printed and after some minutes detection images being created in the results folder.