Leap motion controller three dimensional verification and polynomial correction

Abstract We propose a leap motion controller (LMC) dimensional verification based on ISO 10360-2:2009 with a coordinated measuring machine (CMM) as the reference framework. A pointer device comprising a thin aluminum cylinder was used to simulate a human finger. This was mounted on the spindle of the CMM to mark known positions over the LMC workspace. Polynomial tendency line corrections were applied to reduce the error in the LMC and CMM framework alignment. One dimension verification results were less than 0.1 mm in the X and Z axes, whereas the Y axis produced unsuitable results. The mean error was 9.6 mm in three-dimensional (3D) verification. Our findings demonstrate the difference between manufacturer quoted accuracy (0.01 mm) to that practically obtainable when the pointer was placed in a known position. LMC needs to add tracking models and position error compensation in applications requiring high accuracy, such as industrial processes or surgical procedure simulations.

[1]  Joze Guna,et al.  An Analysis of the Precision and Reliability of the Leap Motion Sensor and Its Suitability for Static and Dynamic Tracking , 2014, Sensors.

[2]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[3]  Hans Martin Kjer,et al.  Evaluation of surface registration algorithms for PET motion correction , 2010 .

[4]  Ling Shao,et al.  Enhanced Computer Vision With Microsoft Kinect Sensor: A Review , 2013, IEEE Transactions on Cybernetics.

[5]  Heng-Tze Cheng,et al.  Contactless gesture recognition system using proximity sensors , 2011, 2011 IEEE International Conference on Consumer Electronics (ICCE).

[6]  Frederick C. Harris,et al.  Real-time natural hand gestures , 2005, Comput. Sci. Eng..

[7]  Junsong Yuan,et al.  Robust Part-Based Hand Gesture Recognition Using Kinect Sensor , 2013, IEEE Transactions on Multimedia.

[8]  Doug A. Bowman,et al.  Slice-n-Swipe: A free-hand gesture user interface for 3D point cloud annotation , 2014, 3DUI.

[9]  Ok-Hue Cho,et al.  A Study about Honey Bee Dance Serious Game for Kids Using Hand Gesture , 2014, MUE 2014.

[10]  Young-Sik Jeong,et al.  Surface Touch Interaction Method Using Inverted Leap Motion Device , 2014 .

[11]  Yuan Yao,et al.  Contour Model-Based Hand-Gesture Recognition Using the Kinect Sensor , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[12]  H. Schwenke,et al.  Error mapping of CMMs and machine tools by a single tracking interferometer , 2005 .

[13]  Pedro Arias,et al.  Metrological evaluation of Microsoft Kinect and Asus Xtion sensors , 2013 .

[14]  Frank Weichert,et al.  Analysis of the Accuracy and Robustness of the Leap Motion Controller , 2013, Sensors.

[15]  Ankit Chaudhary,et al.  Tracking of Fingertips and Centers of Palm Using KINECT , 2011, 2011 Third International Conference on Computational Intelligence, Modelling & Simulation.

[16]  Kourosh Khoshelham,et al.  Accuracy analysis of kinect depth data , 2012 .