Virtual Experiments on ArUco and AprilTag Systems Comparison for Fiducial Marker Rotation Resistance under Noisy Sensory Data

Modern robotic researches propose various machine vision methods for accomplishing robotic tasks. The recognition quality in these tasks is very important for successful performance. A large number of them use fiducial marker systems as a main element of algorithms. However, only a few researches are comparing standard marker systems. This paper is dedicated to the comparison of AprilTag and ArUco markers resistance to rotations in the presence of synthetic noise. Experiments were conducted in ROS/Gazebo virtual environment in order to provide a fair comparison of marker detection and recognition algorithms while eliminating external environment conditions that influence the algorithms' performance. The presented virtual environments allow collecting a significant amount of data by experiment process automation. Different levels of additive white Gaussian noise were applied to input sensory data in order to simulate the imperfection of real digital cameras. The main contribution of the paper is the systematic comparison of AprilTag and ArUco markers for rotation resistance in the presence of optical sensor noise.