Evaluation of Orientation Ambiguity and Detection Rate in April Tag and WhyCode

TL;DR

This paper evaluates April Tag and WhyCode fiducial systems on embedded hardware, focusing on orientation ambiguity and detection rate, highlighting their suitability for drone landing but potential pose estimation errors.

Contribution

It provides a comparative analysis of April Tag and WhyCode fiducials regarding orientation ambiguity and detection performance on embedded systems.

Findings

Both systems have high detection rates suitable for drone landing.

Orientation ambiguity can lead to erroneous control signals.

Custom variants can improve detection but not eliminate orientation issues.

Abstract

Fiducial systems provide a computationally cheap way for mobile robots to estimate the pose of objects, or their own pose, using just a monocular camera. However, the orientation component of the pose of fiducial markers is unreliable, which can have destructive effects in autonomous drone landing on landing pads marked with fiducial markers. This paper evaluates the April Tag and WhyCode fiducial systems in terms of orientation ambiguity and detection rate on embedded hardware. We test 2 April Tag variants - 1 default and 1 custom - and 3 Whycode variants - 1 default and 2 custom. We determine that they are suitable for autonomous drone landing applications in terms of detection rate, but may generate erroneous control signals as a result of orientation ambiguity in the pose estimates.