This is more of a tech demo than art piece made in open frameworks. It demonstrates the possibilities of the technology, which is extremely vast and broad. However, the demo itself fails to show off anything spectacular. Specifically, what is being done on screen does not really require the specific hand motions, so it missed a great opportunity to dazzle us. It reminded me of FaceOSC, which reads in different inputs from the face.
The Echo Temple uses computer vision to let anyone interact with the music with a sign. The user moves a special sign around that modifies the volume, pitch and sound effect. I wonder what the piece would be like if all those are affected by the movement of the body rather than the movement of the signs though. How I wish I could experience it first hand though. It reminds me of rhythm games.