herohuyongtao / deeptag-pytorch

Official implementation of paper [DeepTag: A General Framework for Fiducial Marker Design and Detection]
https://herohuyongtao.github.io/research/publications/deep-tag/
101 stars 19 forks source link
fiducial-marker

Implementation of paper DeepTag: A General Framework for Fiducial Marker Design and Detection.

Project page: https://herohuyongtao.github.io/research/publications/deep-tag/.

Overview

DeepTag is a general framework for fiducial marker design and detection, which supports existing and newly-designed marker families. DeepTag is a two-stage marker detection pipeline:

pipeline

How to run

The configuration file is in JSON format. Please modify the configurations to fit your needs. Example configurations files for image and video input are provided (i.e., config_image.json and config_video.json).

Detail explaination of configuration file:

Besides supporting existing markers like AprilTag, ArUco, ARToolkitPlus, TopoTag & RuneTag, DeepTag also supports newly-designed markers like AprilTag-XO, AprilTag-XA and RuneTag+ (provided in folders images_tag). Set family to apriltagxo in config for AprilTag-XO and AprilTag-XA, and runetag for RuneTag+ respectively.

Terms of use

The source code is provided for research purposes only. Any commercial use is prohibited. When using the code in your research work, please cite the following paper:

"DeepTag: A General Framework for Fiducial Marker Design and Detection."
Zhuming Zhang, Yongtao Hu, Guoxing Yu, and Jingwen Dai
IEEE TPAMI 2023.

@article{zhang2023deeptag,
title={{DeepTag: A General Framework for Fiducial Marker Design and Detection}},
author={Zhang, Zhuming and Hu, Yongtao and Yu, Guoxing and Dai, Jingwen},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume={45},
number={3},
pages={2931-2944},
year={2023},
publisher={IEEE}
}

Contact

If you find any bug or have any question about the code, please report to the Issues page.