Using Charuco Patterns with ReCFusion SDK- for Multi-Sensor Calibration

Hello,

I’ve been exploring the capabilities of the ReCFusion SDK for a project I’m currently working on, and I have a specific question regarding marker patterns. I am interested in using Charuco patterns rather than the standard 6 Aruco patterns provided by the SDK for my application, and I’d like to ask about the possibility of implementing Charuco patterns with the ReCFusion SDK.

For those who may not be familiar, Charuco (ChArUco) patterns are a combination of chessboard and Aruco markers, offering more flexibility and accuracy in marker-based tracking. They are commonly used in computer vision applications for their adaptability to various scenarios.

My main goal is to achieve a higher level of precision and robustness in my marker-based tracking using Charuco patterns. So, I’m wondering if anyone in this community has experience with implementing Charuco patterns with the ReCFusion SDK or if there’s official support for it in the SDK.

I’d appreciate it if anyone could share their insights or experiences with using Charuco patterns in combination with ReCFusion. If this is currently unsupported, perhaps there are workarounds or plans for future updates to accommodate Charuco patterns.

Currently, it seems that RecFusion SDK supports only 6 ArUco markers (available in the markers/ directory of the installed SDK) without any possibility of an extension. Furthermore, it is highly possible (by looking at the DLL-dependencies) that the SDK uses OpenCV to perform the calibration. If that is so, you could skip the calibration made by RecFusion SDK and implement a similar calibration on your own using OpenCV which has the ArUco/ChArUco markers support:

https://docs.opencv.org/4.8.0/d5/dae/tutorial_aruco_detection.html
https://docs.opencv.org/4.8.0/da/d13/tutorial_aruco_calibration.html