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.

[1]  Yoshio Matsumoto,et al.  Avisual marker for precise pose estimation based on lenticular lenses , 2012, 2012 IEEE International Conference on Robotics and Automation.

[2]  Yoshio Matsumoto,et al.  A portable 6-DOF motion tracker using high-accuracy AR markers — First report on the feasibility , 2015, 2015 14th IAPR International Conference on Machine Vision Applications (MVA).

[3]  A. Kelly,et al.  TRAJECTORY GENERATION FOR CAR-LIKE ROBOTS USING CUBIC CURVATURE POLYNOMIALS , 2001 .

[4]  Satoshi Kagami,et al.  Continuous Curvature Trajectory Generation with Obstacle Avoidance for Car-Like Robots , 2005, International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06).

[5]  Andrew Howard,et al.  Design and use paradigms for Gazebo, an open-source multi-robot simulator , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[6]  Hirokazu Kato,et al.  Marker tracking and HMD calibration for a video-based augmented reality conferencing system , 1999, Proceedings 2nd IEEE and ACM International Workshop on Augmented Reality (IWAR'99).