Constrained Kalman filter for improving Kinect based measurements

Microsoft Kinect has the huge potential to be used in home-based rehabilitation and clinical assessments for patients suffering from stroke or other neurological disorder, due to its affordability and unobtrusiveness in analysing joint kinematics. However, skeleton data obtained from Kinect Xbox 360 (Kinect 1) or Kinect Xbox One (Kinect 2) are usually noisy which affects accuracy of estimation of three dimensional joint locations. The noise profile varies for both stationary and dynamic postures and it affects anthropometric measurements of the body segments connecting any two joints. We propose a novel approach to constrain a standard Kalman filter, based on the dynamics of individual joints, in order to keep the distance between any two physically connected joints (namely bone length) constant over time. Our constrained Kalman filter method not only tracks the joints accurately but also reduces the variation in bone lengths by 92% and 94% for Kinect 2 and 1 respectively.

[1]  Ramsey Michael Faragher,et al.  Understanding the Basis of the Kalman Filter Via a Simple and Intuitive Derivation [Lecture Notes] , 2012, IEEE Signal Processing Magazine.

[2]  M. Ferraro,et al.  A novel bio-kinematic encoder for human exercise representation and decomposition - Part 2: Robustness and optimisation , 2013, 2013 International Conference on Control, Automation and Information Sciences (ICCAIS).

[3]  S. McDaniel,et al.  Global ageing in the twenty-first century: An introduction , 2013 .

[4]  Livio Pinto,et al.  Calibration of Kinect for Xbox One and Comparison between the Two Generations of Microsoft Sensors , 2015, Sensors.

[5]  Sean Kean,et al.  Meet the Kinect: An Introduction to Programming Natural User Interfaces , 2011 .

[6]  P. Olivier,et al.  Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson's disease. , 2014, Gait & posture.

[7]  Philippe Fraisse,et al.  Estimation of the center of mass with Kinect and Wii balance board , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Jeffrey A Reinbolt,et al.  OpenSim: a musculoskeletal modeling and simulation framework for in silico investigations and exchange. , 2011, Procedia IUTAM.

[9]  F. Duan,et al.  A study of the human-robot synchronous control system based on skeletal tracking technology , 2013, 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[10]  Mordecai Avriel,et al.  Nonlinear programming , 1976 .

[11]  B Bonnechère,et al.  Validity and reliability of the Kinect within functional assessment activities: comparison with standard stereophotogrammetry. , 2014, Gait & posture.

[12]  J. H. Wilkinson.  The algebraic eigenvalue problem , 1966 .

[13]  Jeffrey L Saver,et al.  Stroke Declines From Third to Fourth Leading Cause of Death in the United States: Historical Perspective and Challenges Ahead , 2011, Stroke.

[14]  Richard Green,et al.  Low-Latency Filtering of Kinect Skeleton Data for Video Game Control , 2014, IVCNZ '14.

[15]  Bruce Carse,et al.  Affordable clinical gait analysis: an assessment of the marker tracking accuracy of a new low-cost optical 3D motion analysis system. , 2013, Physiotherapy.

[16]  Chun Yang,et al.  Kalman Filtering with Nonlinear State Constraints , 2009 .