Home

Awesome

SiamFC - MXNet

:high_brightness: MXNet/gluon :high_brightness: port of the tracking method described in the paper Fully-Convolutional Siamese nets for object tracking

Running the tracker

  1. Set root_dataset in hyperparams/params.json to your dataset path
  2. Set all from hyperparams/params.json to true or to set one or more specific sequences (e.g. Basketball and/or Soccer) in video with setting all to false
  3. See if you are happy with the default parameters in hyperparams/params.json
  4. Call the main script python run_tracker.py
  5. The results.mat can be found in results which you can run on OTB

Results on test sequence:

tracking_girl

AUC (%) on OTB

TrackerOTB2013OTB2015
paper (SiamFC_3s)60.858.2
ours (SiamFC_MXnet)60.958.8

Precision (%) on OTB

TrackerOTB2013OTB2015
paper (SiamFC_3s)80.977.3
ours (SiamFC_MXnet)81.476.7

Note

Some errors in fixed_crop and resize need to be fixed, which caused me a lot of headaches

References

@inproceedings{bertinetto2016fully,
  title={Fully-Convolutional Siamese Networks for Object Tracking},
  author={Bertinetto, Luca and Valmadre, Jack and Henriques, Joao F and Vedaldi, Andrea and Torr, Philip H S},
  booktitle={ECCV 2016 Workshops},
  pages={850--865},
  year={2016}
}