Random Dot Markers (UCHIYAMARKERS) UCHIYAMARKER
Preparation
- Download source (153KB)
(prepared
for
visual studio 2010. For
other versions, please prepare the solution file)
- Set up OpenCV (2.0 or later) and OpenGL GLUT
- Add OpenCV headers and library paths in mylib/opencvpath.h
- Set up OpenMP (optional)
- Compile the source
Setting
- Print markers in data directory (like 10cm x 10cm)
- Run the software
- Click 's' to watch binary images and check black dots are
extracted or not
- Click ESC to close the software and change the threshold for
binaization at Binarization() in mylib/myimage.cpp
Usage
- Run the software
- Show markers to a camera (rectangles are displayed if markers are
successfully retrieved)
- Click ESC to close the software (takes time for releasing memory)
Option
- Download one thousand markers (13MB) and
put
them into data directory (download markers
in PDF for printing if need)
- Make your own markers with our code
- Set the number of markers you use on int nummarker at
trackingInit() in main.cpp (need 500MB for
execution if use 1000 markers)
Technology
- Keypoint matching by locally likely arrangement hashing
(LLAH)
- Multiple planar object retrieval and tracking
Note
- Better to move the data directory into the directory of executable and directly run with the executable (running
on visual studio is a little slow)
- Better to change the number of
iterations for homography estimation with RANSAC in OpenCV for fast
retrieval (need to change const int maxIters like 300 in
cvFindHomography and recompile OpenCV)
- Use this software for only research (non-profit) purposes
- Feel free to email me for any questions
- Try deformable version
Back to top
Updated on Nov. 4, 2011.
contact: