Skip to content

Update aruco.bib with core ArUco and AprilTag references#4061

Open
Shashikumar-ezhilarasu wants to merge 1 commit intoopencv:4.xfrom
Shashikumar-ezhilarasu:update-aruco-bib
Open

Update aruco.bib with core ArUco and AprilTag references#4061
Shashikumar-ezhilarasu wants to merge 1 commit intoopencv:4.xfrom
Shashikumar-ezhilarasu:update-aruco-bib

Conversation

@Shashikumar-ezhilarasu
Copy link

Description

This PR updates the aruco.bib file located at modules/aruco/doc/aruco.bib to include essential references for ArUco and AprilTag fiducial markers.

Changes included:

  • Added foundational ArUco marker papers (Garrido-Jurado et al., 2014)
  • Added AprilTag papers (Olson 2011, Wang 2016, Mueller 2017)
  • Added ARTag and ARToolKit references
  • Included key algorithms such as RANSAC, EPnP, and camera calibration papers used in fiducial detection
  • Removed duplicate or irrelevant entries for conciseness

Motivation:
The previous .bib file lacked several key references, which are important for developers, students, and researchers using the ArUco module. This update ensures proper citation and improves documentation completeness.

Impact:

  • Documentation update only (.bib)
  • No code or functionality changes

Pull Request Readiness Checklist

  • I agree to contribute to the project under Apache 2 License
  • To the best of my knowledge, the proposed patch is not based on code under GPL or another license that is incompatible with OpenCV
  • The PR is proposed to the proper branch (master or 4.x depending on repo guidelines)
  • There is a reference to the original work and related research:
    • Original aruco.bib lacked key ArUco/AprilTag references
    • References added based on papers:
      • Garrido-Jurado et al., 2014 (ArUco)
      • Olson, 2011 (AprilTag)
      • Wang & Olson, 2016 (AprilTag 2)
      • Mueller et al., 2017 (AprilTag 3)
      • Others: Fiala 2005, Kato & Billinghurst 1999, Fischler & Bolles 1981, Bradski 2000
  • Accuracy test, performance test, and test data are not applicable, as this is purely a documentation update
  • The feature is well documented, and sample code can still be built without any issues

Note for Maintainers

This is a purely documentation PR, intended to improve scholarly references in the aruco module. No functional changes have been made.
Thank you !!

Comment on lines +65 to +71
@inproceedings{Mueller2017AprilTag3,
author = {Fadri Furrer Mueller and Matthias Faessler and David Cieslewski and Roland Siegwart and Juan Nieto},
title = {{AprilTag} 3: {A} robust multi-family fiducial system},
booktitle = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
year = {2017},
month = {September}
} No newline at end of file
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not the AprilTag 3 paper, but an hallucination from an LLM. This paper does not exist at all...
Sorry but an LLM can already better summarize the relevant works for fiducial markers detection for a student than just adding these entries.


The previous .bib file lacked several key references, which are important for developers, students, and researchers using the ArUco module. This update ensures proper citation and improves documentation completeness.

I don't see these references appearing in the generated doc. Without actual citing in the doc, they don't seem to appear in the html bibliography. So this is completely useless.

Added ARTag and ARToolKit references
Included key algorithms such as RANSAC, EPnP, and camera calibration papers used in fiducial detection

I also disagree to add references (ARTag, ARToolKit) to these papers while OpenCV does not support these tag families. For related papers/works, students can read the ArUco / AprilTag paper. Or they will directly use an LLM to summarize the related works.

Included key algorithms such as RANSAC, EPnP, and camera calibration papers used in fiducial detection

EPnP, RANSAC and the camera calibration papers are already present in the bibliography. BTW, these papers are not the one to be used for EPnP and camera calibration works.

Removed duplicate or irrelevant entries for conciseness

???


For an actual doc improvement, it would need some efforts to:

  • add the proper references for the corresponding functions
  • check that the implementation corresponds to the paper, if the implementation deviates from the original work (e.g. for performance reason) it should be mentioned (ideally)
  • and many other things such as refresh of the tutorials, fuse the Python tutorials with the rest, add more theory, ...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants