tracker_benchmark

by jwlim

206 Stars 120 Forks Last release: Not found 45 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

Trakcer Benchmark (Tested on python 2.7.10)

Usage - Default (for all trackers, all sequences, all evaltypes(OPE, SRE, TRE)) - command: python run_trackers.py

  • For specific trackers, sequences, evaltypes

    • command: python run_trackers.py -t "tracker" -s "sequence" -e "evaltype"
    • sequence can be name of Sequence, 'tb50', 'tb100' and 'cvpr13' (using data/tb50.txt, tb100.txt, cvpr13.txt)
    • e.g.
      • python run_trackers.py -t IVT,TLD -s Couple,Crossing -e OPE,SRE
        )
      • python run_trackers.py -s tb50
  • Plotting

    • Success rate plotting command:
      python draw_graph.py
    • Precision plotting commaind:
      python draw_graph.py precision
    • Draw bbox results:
      python draw_bbox.py

Libraries - Matlab Engine for python (only needed for executing matlab script files of trackers)

http://kr.mathworks.com/help/matlab/matlab-engine-for-python.html
  • matplotlib
  • numpy
  • Python Imaging Library (PIL)

    http://www.pythonware.com/products/pil/

Troubleshooting - Segmentaion Fault when running 'python runtracker.py ...' on MacOSX - Set DYLDLIBRARYPATH environment variable. - e.g.: export DYLDLIBRARYPATH=/usr/local/Cellar/python/2.7.11/Frameworks/Python.framework/Versions/Current/lib/:$DYLDLIBRARY_PATH

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.