Simulation and Evaluation of LentiMark Markers for Accurate Pose Estimation

This paper reports the development and evaluation of a simulated environment to perform autonomous tasks using LentiMark augmented reality marker-based pose estimation. Performance of marker-based pose estimation is evaluated in simulation over conditions such as position with respect to camera, yaw and roll of marker, varying illumination and shadow, motion blur and marker occlusion. While results will not directly translate to real world performance, limitations in the marker system's pose estimation accuracy due to pixelisation effects, detection failure due to background confusion under roll, and performance degradation with any marker occlusion are identified.