Validation of the Leap Motion Controller using markered motion capture technology.

The Leap Motion Controller (LMC) is a low-cost, markerless motion capture device that tracks hand, wrist and forearm position. Integration of this technology into healthcare applications has begun to occur rapidly, making validation of the LMC׳s data output an important research goal. Here, we perform a detailed evaluation of the kinematic data output from the LMC, and validate this output against gold-standard, markered motion capture technology. We instructed subjects to perform three clinically-relevant wrist (flexion/extension, radial/ulnar deviation) and forearm (pronation/supination) movements. The movements were simultaneously tracked using both the LMC and a marker-based motion capture system from Motion Analysis Corporation (MAC). Adjusting for known inconsistencies in the LMC sampling frequency, we compared simultaneously acquired LMC and MAC data by performing Pearson׳s correlation (r) and root mean square error (RMSE). Wrist flexion/extension and radial/ulnar deviation showed good overall agreement (r=0.95; RMSE=11.6°, and r=0.92; RMSE=12.4°, respectively) with the MAC system. However, when tracking forearm pronation/supination, there were serious inconsistencies in reported joint angles (r=0.79; RMSE=38.4°). Hand posture significantly influenced the quality of wrist deviation (P<0.005) and forearm supination/pronation (P<0.001), but not wrist flexion/extension (P=0.29). We conclude that the LMC is capable of providing data that are clinically meaningful for wrist flexion/extension, and perhaps wrist deviation. It cannot yet return clinically meaningful data for measuring forearm pronation/supination. Future studies should continue to validate the LMC as updated versions of their software are developed.

[1]  Pietro Perona,et al.  Continuous dynamic time warping for translation-invariant curve alignment with applications to signature verification , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[2]  David Putrino,et al.  Telerehabilitation and emerging virtual reality approaches to stroke rehabilitation. , 2014, Current opinion in neurology.

[3]  Artur Krukowski,et al.  Rehabilitation after Stroke using Immersive User Interfaces in 3D Virtual and Augmented Gaming Environments , 2015, EAI Endorsed Trans. Pervasive Health Technol..

[4]  Luigi Cinque,et al.  Markerless Hand Gesture Interface Based on LEAP Motion Controller , 2014, DMS.

[5]  Christian Jutten,et al.  Multiclass Brain–Computer Interface Classification by Riemannian Geometry , 2012, IEEE Transactions on Biomedical Engineering.

[6]  A. Cappozzo,et al.  Human movement analysis using stereophotogrammetry. Part 1: theoretical background. , 2005, Gait & posture.

[7]  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.

[8]  Brian D Lowe,et al.  Accuracy and validity of observational estimates of wrist and forearm posture , 2004, Ergonomics.

[9]  Emanuel Todorov,et al.  Probabilistic Inference of Multijoint Movements, Skeletal Parameters and Marker Attachments From Diverse Motion Capture Data , 2007, IEEE Transactions on Biomedical Engineering.

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

[11]  Kevin Curran,et al.  Using Leap Motion and Gamification to Facilitate and Encourage Rehabilitation for Hand Injuries: Leap Motion for Rehabilitation , 2016 .

[12]  Victor M. R. Penichet,et al.  Movement-Based Interaction Applied to Physical Rehabilitation Therapies , 2014 .

[13]  C Disselhorst-Klug,et al.  A marker-based measurement procedure for unconstrained wrist and elbow motions. , 1999, Journal of biomechanics.

[14]  Nancy A Baker,et al.  Measurements of wrist and finger postures: a comparison of goniometric and motion capture techniques. , 2007, Journal of applied biomechanics.

[15]  Cristina V. Lopes,et al.  Free-hand interaction with leap motion controller for stroke rehabilitation , 2014, CHI Extended Abstracts.

[16]  Eamonn J. Keogh,et al.  Scaling and time warping in time series querying , 2005, The VLDB Journal.

[17]  Bryan Buchholz,et al.  ISB recommendation on definitions of joint coordinate systems of various joints for the reporting of human joint motion--Part II: shoulder, elbow, wrist and hand. , 2005, Journal of biomechanics.

[18]  Scott W Wolfe,et al.  Accuracy and reliability of three different techniques for manual goniometry for wrist motion: a cadaveric study. , 2009, The Journal of hand surgery.

[19]  Alexander Wong,et al.  Dense Depth Map Reconstruction from Sparse Measurements Using a Multilayer Conditional Random Field Model , 2015, 2015 12th Conference on Computer and Robot Vision.

[20]  Aaron E. Rosenberg,et al.  Performance tradeoffs in dynamic time warping algorithms for isolated word recognition , 1980 .

[21]  P. Jonsson,et al.  Comparison of measurement accuracy between two types of wrist goniometer systems. , 2001, Applied ergonomics.

[22]  Robert M. White,et al.  Comparative Anthropometry of the Hand , 1980 .

[23]  Anita Bagley,et al.  A method for determination of upper extremity kinematics. , 2002, Gait & posture.

[24]  Lawrence Wai-Choong Wong,et al.  Ubiquitous Human Upper-Limb Motion Estimation using Wearable Sensors , 2011, IEEE Transactions on Information Technology in Biomedicine.

[25]  Fatih Murat Porikli,et al.  Pedestrian Detection via Classification on Riemannian Manifolds , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  C. Cobelli,et al.  Comparison of Markerless and Marker-Based Motion Capture Technologies through Simultaneous Data Collection during Gait: Proof of Concept , 2014, PloS one.

[27]  Paul H. Chappell,et al.  Validation and Application of a Computational Model for Wrist and Hand Movements Using Surface Markers , 2008, IEEE Transactions on Biomedical Engineering.