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