Have posted all the code to the Kinect demos I have done so far. The readme also contains a full setup guide for getting started with libfreenect, ofxKinect, and OpenFrameworks on the mac.
One last kinect project before the weekend is over.
Controlling mario kart with Microsoft kinect.
I use the depth information to detect the position of both of my hands as well as the position of my leg. These inputs are then mapped to keyboard keys to be used as input in other applications. In this case an SNES emulator.
Apologize for how poorly I play, its quite late, so not much time to practice with this new input method
- Will post another video tomorrow once I have had more practice.
Another quick demo playing with open source drivers for the Kinect (http://openkinect.org)
A threshold is used on the depth-map to filter out everything but my hands, and then blob detection is used to locate their centers. This information is then used to scale and rotate an onscreen object.
Note that because the Kinect provides depth information, the object can be rotated on both its Z and Y axis. With a bit of work, a gesture could theoretically also be made to rotate along the X axis.
* sorry about the flickering, this is an artifact of screen recored I am using, and is not visible in actual use
Made in C++ with:
ofxKinect – http://github.com/???ofTheo/???ofxKinect
This is just a quick demo showing background removal, using both threshold as well as a captured depthmap (and image) of the empty scene.
Any foreground objects are then (arbitrarily) moved forward in the scene, and due to the motion, a paralax effect can be observed.
If the depth information were to actually used in offsetting the foreground object, a pretty convincing effect could be achieved for applications the dont require too much depth in the scene, like a head tracking effect.