This is a fork of MFT to support installation and usage with the STIR dataset. eg.
pip install MFT
Supports usage with the STIR dataset when installed, and used with STIRMetrics
All credit for the tracker, and licensing details are from:
Project Page Official implementation of the MFT tracker from the paper:
Michal Neoral, Jonáš Šerých, Jiří Matas: "MFT: Long-Term Tracking of Every Pixel", WACV 2024
Please cite our paper, if you use any of this.
@inproceedings{neoral2024mft,
title={{MFT}: Long-Term Tracking of Every Pixel},
author={Neoral, Michal and {\v{S}}er{\'{y}}ch, Jon{\'{a}}{\v{s}} and Matas, Ji{\v{r}}{\'{i}}},
journal={arXiv preprint arXiv:2305.12998},
year={2023},
}
Create and activate a new virtualenv:
# we have tested with python 3.7.4
python -m venv venv
source venv/bin/activate
Then install all the dependencies:
pip install torch numpy einops tqdm opencv-python scipy Pillow==9 matplotlib ipdb
pip uninstall torch numpy einops tqdm opencv-python scipy Pillow==9 matplotlib ipdb
pip install .
Simply running:
python demo.py
should produce a demo_out
directory with two visualizations.
See train.org
The demo video in demo_in
was extracted from youtube.
This work is licensed under the Attribution-NonCommercial-ShareAlike 4.0 International license.
The MFT/RAFT
directory contains a modified version of RAFT, which is licensed under BSD-3-Clause license.
Our modifications (OcclusionAndUncertaintyBlock
and its integration in raft.py
) are licensed again under the Attribution-NonCommercial-ShareAlike 4.0 International.
This work was supported by Toyota Motor Europe,
by the Grant Agency of the Czech Technical University in Prague, grant No. SGS23/173/OHK3/3T/13
, and
by the Research Center for Informatics project CZ.02.1.01/0.0/0.0/16_019/0000765
funded by OP VVV.