Skeleton space transformation

The Kinect sensor represents the skeleton data in a 3D coordinate system. With respect to the Kinect sensor and human body points, the x axis and y axis define the position of the joint and z axis represents the distance from the sensor. The overall representation of the skeleton data within global space is knows as skeleton space. The origin of the skeleton space is the depth images, which return the skeleton data with the set of joint positions. In the end, each joint position is represented with (x, y, z) coordinates.

With only the skeleton data, it is difficult to directly interact with the user. This is because the user's coordinate space is different than the skeleton joint information. So we need some approach to transform the skeleton joint's coordinate system into a global space where both the users and the application understand each other's coordinate system.

The Kinect for Windows SDK provides us with a set of APIs that allows us to easily translate...