Fiducial markers such as QR codes, ArUco, and AprilTag have become very popular tools for labeling and camera positioning. They are robust and easy to detect, even in devices with low computing power. However, their industrial appearance deters their use in scenarios where an attractive and visually appealing look is required. In these cases, it would be preferable to use customized markers showing, for instance, a company logo. This work proposes a novel method to design, detect, and track customizable fiducial markers. Our work allows creating markers templates imposing few restrictions on its design, e.g., a company logo or a picture can be used. The designer must indicate positions into the template where bits will encode a unique identifier for each marker. Then, our method will automatically create a dictionary of markers, all following the same design, but each with a unique identifier. Finally, we propose a method for detecting and tracking the markers even under occlusion, which is not allowed in traditional fiducial markers. The experiments conducted show that the performance of the customizable markers is similar to the best traditional markers systems without significantly sacrificing speed.
INDEX TERMSCustomized Markers, Fiducial Markers, ArUco, AprilTag. I. INTRODUCTION 1 Fiducial markers have become a popular and efficient 2 method to solve labeling and monocular localization prob-3 lems at low cost in indoor environments. Their use has 4 spread in a wide variety of fields, such as surgery [18, 6], 5 robot navigation [34, 43], autonomous aerial vehicle land-6 ing [4], augmented reality applications [19], distributed au-7 tonomous 3D printing [46], human cognitive processes [2], 8 the study of animal behaviour [1] and patient positioning 9 in radiotherapy treatments [36] among others. 10 There are several desirable properties a fiducial marker 11 system should have. It must be easy and fast automatically 12 detecting its markers in images. Each marker should have a unique identifier, and it should be possible to estimate its 14 position w.r.t the camera. They should be robustly detected 15 under occlusion, varying lighting conditions, rotation, and 16 scale.