Skip to content

achaar/visual_object_tracking

 
 

Repository files navigation

Authors

  • Sanjeev Kumar Singh
  • Ankur Kunder

Results on vot2013/bicycle:

Models FPS
ADNet 2.90
ADNet-Fast 15.00
Ours 9.65

Python version: This code is in Python3.6

Package Requirements: tensorflow==1.14.0, OpenCV==3.4.2, pyyaml, hdf5storage, h5py

Graphs

  • The plots shown are the obsrvations collected on single training video

Our Model

Implementation of 'Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning(CVPR 2017)'

GIF Description
vot2013_bicyce vot2013 Dataset bicycle
  • Green : Ground Truth, Blue : Ours implemented model

Data Preperation:

Step 1

Download the Visual Object Tracking Dataset from website. We have used the data for 2013, 2014 and 2015. More data always helps.

Step 2

Put the inside folder train_data as vot2013, vot2014 and vot2014. This folder should have folder video wise and inside each folder. extract frames in img folder.

Model Training

python runner.py -debug <bool denoting debug on 1 video> -mode <train|test> -rl <bool denoting if RL is on> -model_path <model-path> -vid_path <video-path>
  • Loss will be logged at model_path/loss.log
  • You can download our pre-trained model at this link.

Acknowledgements

Base Code is take from here

About

Course Project Reinforcement Learning(CSCE 689)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.3%
  • M 0.7%