Analysis and Improvements in AprilTag Based State Estimation

In this paper, we analyzed the accuracy and precision of AprilTag as a visual fiducial marker in detail. We have analyzed error propagation along two horizontal axes along with the effect of angular rotation about the vertical axis. We have identified that the angular rotation of the camera (yaw angle) about its vertical axis is the primary source of error that decreases the precision to the point where the marker system is not potentially viable for sub-decimeter precise tasks. Other factors are the distance and viewing angle of the camera from the AprilTag. Based on these observations, three improvement steps have been proposed. One is the trigonometric correction of the yaw angle to point the camera towards the center of the tag. Second, the use of a custom-built yaw-axis gimbal, which tracks the center of the tag in real-time. Third, we have presented for the first time a pose-indexed probabilistic sensor error model of the AprilTag using a Gaussian Processes based regression of experimental data, validated by particle filter tracking. Our proposed approach, which can be deployed with all three improvement steps, increases the system’s overall accuracy and precision by manifolds with a slight trade-off with execution time over commonly available AprilTag library. These proposed improvements make AprilTag suitable to be used as precision localization systems for outdoor and indoor applications.

[1]  Wenda Zhao,et al.  Improved Tag-based Indoor Localization of UAVs Using Extended Kalman Filter , 2019 .

[2]  Edwin Olson,et al.  AprilTag 2: Efficient and robust fiducial detection , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[3]  Vineet R. Kamat,et al.  AUGMENTED REALITY MARKERS AS SPATIAL INDICES FOR INDOOR MOBILE AECFM APPLICATIONS , 2012 .

[4]  Christopher Gaudig,et al.  Model identification of an unmanned underwater vehicle via an adaptive technique and artificial fiducial markers , 2015, OCEANS 2015 - MTS/IEEE Washington.

[5]  Stiven Schwanz Dias,et al.  A Visual-Inertial Navigation System Using AprilTag for Real-Time MAV Applications , 2018, 2018 25th International Conference on Mechatronics and Machine Vision in Practice (M2VIP).

[6]  Quan Quan,et al.  Pose Estimation for Multicopters Based on Monocular Vision and AprilTag , 2018, 2018 37th Chinese Control Conference (CCC).

[7]  Ben M. Chen,et al.  Vision-aided tracking of a moving ground vehicle with a hybrid UAV , 2017, 2017 13th IEEE International Conference on Control & Automation (ICCA).

[8]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[9]  Edwin Olson,et al.  AprilTag: A robust and flexible visual fiducial system , 2011, 2011 IEEE International Conference on Robotics and Automation.

[10]  Richard D. Green,et al.  High-accuracy fiducial markers for ground truth , 2016, 2016 International Conference on Image and Vision Computing New Zealand (IVCNZ).

[11]  Andrea Torsello,et al.  RUNE-Tag: A high accuracy fiducial marker with strong occlusion resilience , 2011, CVPR 2011.

[12]  Fan Xiao,et al.  What is the best fiducial? , 2002, The First IEEE International Workshop Agumented Reality Toolkit,.

[13]  Guo Yanning,et al.  Vision-based autonomous landing of unmanned aerial vehicles , 2017, 2017 Chinese Automation Congress (CAC).

[14]  Steven Lake Waslander,et al.  Autonomous Maritime Landings for Low-Cost VTOL Aerial Vehicles , 2014, 2014 Canadian Conference on Computer and Robot Vision.

[15]  Zoltan-Csaba Marton,et al.  Robot-to-Camera Calibration: A Generic Approach Using 6D Detections , 2017, 2017 First IEEE International Conference on Robotic Computing (IRC).

[16]  Eric Psota,et al.  Automated indoor RFID inventorying using a self-guided micro-aerial vehicle , 2014, IEEE International Conference on Electro/Information Technology.

[17]  Gregory Dudek,et al.  Fourier Tag: A Smoothly Degradable Fiducial Marker System with Configurable Payload Capacity , 2011, 2011 Canadian Conference on Computer and Robot Vision.

[18]  François Chaumette,et al.  Stability Analysis of Pose-Based Visual Servoing Control of Cable-Driven Parallel Robots , 2019, Mechanisms and Machine Science.

[19]  G. Reina,et al.  Adaptive Kalman Filtering for GPS-based Mobile Robot Localization , 2007, 2007 IEEE International Workshop on Safety, Security and Rescue Robotics.

[20]  Hugh F. Durrant-Whyte,et al.  Mobile robot localization by tracking geometric beacons , 1991, IEEE Trans. Robotics Autom..

[21]  Hamid K. Aghajan,et al.  A hybrid pose tracking approach for handheld augmented reality , 2015, ICDSC.

[22]  S. Srinivasa,et al.  Sensor fusion for fiducial tags: Highly robust pose estimation from single frame RGBD , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[23]  Bo Li,et al.  Infrastructure Based Calibration of a Multi-Camera and Multi-LiDAR System Using Apriltags , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[24]  Mark Fiala,et al.  ARTag, a fiducial marker system using digital techniques , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[25]  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).

[26]  Mark Fiala,et al.  Comparing ARTag and ARToolkit Plus fiducial marker systems , 2005, IEEE International Workshop on Haptic Audio Visual Environments and their Applications.

[27]  Xiangke Wang,et al.  Autonomous landing on ground target of UAV by using image-based visual servo control , 2017, 2017 36th Chinese Control Conference (CCC).

[29]  Dieter Schmalstieg,et al.  ARToolKitPlus for Pose Trackin on Mobile Devices , 2007 .

[30]  Wolfram Burgard,et al.  Robust Monte Carlo localization for mobile robots , 2001, Artif. Intell..

[31]  Ernesto Alejandro Ramirez.  An experimental study of mobile device localization , 2015 .

[32]  Adrian Hilton,et al.  A survey of advances in vision-based human motion capture and analysis , 2006, Comput. Vis. Image Underst..

[33]  Artur Sagitov,et al.  Comparing fiducial marker systems in the presence of occlusion , 2017, 2017 International Conference on Mechanical, System and Control Engineering (ICMSC).

[34]  Andrei George Florea,et al.  Sensor Fusion for Autonomous Drone Waypoint Navigation Using ROS and Numerical P Systems: A Critical Analysis of Its Advantages and Limitations , 2019, 2019 22nd International Conference on Control Systems and Computer Science (CSCS).

[35]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[36]  Ralf Dörner,et al.  Accuracy in optical tracking with fiducial markers: an accuracy function for ARToolKit , 2004, Third IEEE and ACM International Symposium on Mixed and Augmented Reality.

[37]  Fei-Yue Wang.  Driving into the Future with ITS , 2006, IEEE Intelligent Systems.

[38]  Ju Wang,et al.  Optimizing Ground Vehicle Tracking Using Unmanned Aerial Vehicle and Embedded Apriltag Design , 2016, 2016 International Conference on Computational Science and Computational Intelligence (CSCI).

[39]  Flavio Fontana,et al.  Aerial-guided navigation of a ground robot among movable obstacles , 2014, 2014 IEEE International Symposium on Safety, Security, and Rescue Robotics (2014).

[40]  Janille Maria Maragh.  Dynamic tracking with AprilTags for robotic education , 2013 .

[41]  Diego López-de-Ipiña,et al.  TRIP: A Low-Cost Vision-Based Location System for Ubiquitous Computing , 2002, Personal and Ubiquitous Computing.

[42]  D. Paulus,et al.  3D pose estimation for articulated vehicles using Kalman-filter based tracking , 2016, Pattern Recognition and Image Analysis.

[43]  Tianjiang Hu,et al.  AprilTag array-aided extrinsic calibration of camera–laser multi-sensor system , 2016, Robotics and biomimetics.

[44]  Ulrich Neumann,et al.  A Multi-ring Color Fiducial System and A Rule-Based Detection Method for Scalable Fiducial-tracking Augmented Reality , 1998 .