Using Tobit Kalman filtering in order to improve the Motion recorded by Microsoft Kinect

Abstract:


In this paper, we analyze data from Microsoft Kinect v2 camera using Kalman Tobit and Kalman filters so as to minimize noise. The data concern three-dimensional spatial coordinates recording movements of a persons'A joints, which are subject to measurement errors. The noise variances of the process and the measurements are estimated using the maximum likelihood function. In order to include into the model restrictive conditions based on anthropometric data (e.g. the distances between various joints) we apply the Tobit Kalman Filter. Additionally, restrictions for the joints displacements per fame based on real data can be used in order to get better results. Finally simulations of skeleton before and after using Kalman filtering are presented.


  • K. Loumponias, N. Vretos, P. Daras, G. Tsaklidis, "Using Tobit Kalman filtering in order to improve the Motion recorded by Microsoft Kinect", International workshop on applied probability IWAP 2016, 20-23 June, 2016, Toronto, Canada

  • Full document available here.
    Contact Information

    Dr. Petros Daras, Principal Researcher Grade Α
    1st km Thermi – Panorama, 57001, Thessaloniki, Greece
    P.O.Box: 60361
    Tel.: +30 2310 464160 (ext. 156)
    Fax: +30 2310 464164
    Email: daras@iti.gr