Tracking Fiducial Markers with Discriminative Correlation Filters
We present a new work for the camera pose estimation. This method employs Discriminative Correlation Filters for tracking the marker and its corners, achieving continuous detection even under extreme blurring and scaling conditions, using low computation times.
The system operates under two approaches, firstly the tracking of individual markers. In a second scenario, the use of marker mapping for a robust camera location.
The tools are fully integrated under the ArUco system.
The library can be downloaded at SourceForge
Very detailed documentation can be obtained HERE
If you use this library in your research, you must cite:
- “Speeded up detection of squared fiducial markers”, Francisco J.Romero-Ramirez, Rafael Muñoz-Salinas, Rafael Medina-Carnicer, Image and Vision Computing, vol 76, pages 38-47, year 2018