ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Using Kinect for motion capture

Grega Gašperšič (2013) Using Kinect for motion capture. EngD thesis.

[img]
Preview
PDF
Download (5Mb)

    Abstract

    The goal of this thesis is to build a low budget system for motion capture. This includes replaying and interpolation of motion, and importing the captured data into the Maya and MotionBuilder environment. In order to do this, we must be able to capture motion data and convert it into a for that is comprehensible to humans and computers. Motion data is captured with the help of Microsofts motion detection sensor Kinect. The system is based on a RGB camera and a 3D depth sensor, consisting of a IR laser projector and a IR sensor. For the needs of the projected system, the data must be as accurate as possible. To this end, a visualization of a 3D complex model has been created, which serves as an aid in interpreting the accuracy of the captured data. The next step is to convert the movement data into human readable form and store the new data, for future use. As part of the visualization we also implement the replaying and interpolation of the new data. The final step is to implement a program to import data into Autodesk Maya and converting the data into a BVH file format that is suitable for importing into Autodesk MotionBuilder.

    Item Type: Thesis (EngD thesis)
    Keywords: motion capture, Microsoft Kinect sensor, data capture, 3D model visualization, data interpolation, data processing
    Number of Pages: 66
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    doc. dr. Matija Marolt271Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(ID=10156116)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 2202
    Date Deposited: 21 Sep 2013 17:06
    Last Modified: 02 Oct 2013 09:11
    URI: http://eprints.fri.uni-lj.si/id/eprint/2202

    Actions (login required)

    View Item