Skip to content

Latest commit

 

History

History

rt_gene_standalone

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 

RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments

License: CC BY-NC-SA 4.0 stars GitHub issues GitHub repo size

License + Attribution

This code is licensed under CC BY-NC-SA 4.0. Commercial usage is not permitted; please contact [email protected] or [email protected] regarding commercial licensing. If you use this dataset or the code in a scientific publication, please cite the following paper:

@inproceedings{FischerECCV2018,
author = {Tobias Fischer and Hyung Jin Chang and Yiannis Demiris},
title = {{RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments}},
booktitle = {European Conference on Computer Vision},
year = {2018},
month = {September},
pages = {339--357}
}

This work was supported in part by the Samsung Global Research Outreach program, and in part by the EU Horizon 2020 Project PAL (643783-RIA).

More information can be found on the Personal Robotic Lab's website: https://www.imperial.ac.uk/personal-robotics/software/.

Requirements

  1. Install required Python packages:
    • For conda users (recommended): conda install tensorflow-gpu numpy scipy tqdm pillow opencv matplotlib pytorch torchvision
    • For pip users: pip install tensorflow-gpu numpy scipy tqdm torch torchvision Pillow opencv-python matplotlib
  2. Download RT-GENE and add the source folder to your PYTHONPATH environment variable:
    1. cd $HOME/ && git clone https://github.com/Tobias-Fischer/rt_gene.git
    2. export PYTHONPATH=$HOME/rt_gene/rt_gene/src

Basic usage

  • Run $HOME/rt_gene/rt_gene_standalone/estimate_gaze_standalone.py. For supported arguments, run $HOME/rt_gene/rt_gene_standalone/estimate_gaze_standalone.py --help. Note that the first time the script is run, various model files are downloaded automatically. An alternative mirror for the model files is here; these files need to be moved into $HOME/rt_gene/rt_gene/model_nets.

Optional ensemble model files

  • To use an ensemble scheme using 4 models trained on the MPII, UTMV and RT-GENE datasets, simply use the --models argument, e.g cd $HOME/rt_gene/ && ./rt_gene_standalone/estimate_gaze_standalone.py --models './rt_gene/model_nets/all_subjects_mpii_prl_utmv_0_02.h5' './rt_gene/model_nets/all_subjects_mpii_prl_utmv_1_02.h5' './rt_gene/model_nets/all_subjects_mpii_prl_utmv_2_02.h5' './rt_gene/model_nets/all_subjects_mpii_prl_utmv_3_02.h5'

List of libraries

See main README.md