Yes you read the title correctly - it is Kinect not Kinetic art - but there is plenty of movement in it. As well as being an inspiration to practical engineering, the Kinect and its 3D depth maps are inspiring art of all sorts.
It is all too easy to get excited about the serious application of the Kinect, but there is an extra excitement that occurs when you just play with the device and see what sort of image the depth camera produces. Put this together with some color video and the effect become even more "artistic". If you add some algorithms that take the 3D depth map and use the 2D color images as texture maps then you are into something really special.
It looks as if the 2D camera has captured a full 3D scene and you can move the view point to see new compositions. It isn't perfect as the textures are more like advertising billboards stuck onto hidden objects, but the imperfections add to the artistic effect.
James George and Alexander Porter have taken CCTV images and used custom software to combine the depth map with hi-res images from a Canon 5D. To quote from James George's blog:
It is in this technological atmosphere that we chose to collaborate. We soldered together an inverter and motorcycle batteries to run the laptop and Kinect sensor on the go. We attached a Canon 5D DSLR to the sensor and plugged it in to a laptop. The entire kit went into a backpack.
We spent an evening in the New York Union Square subway capturing high resolution stills and and archiving depth data of pedestrians. We wrote an openFrameworks application to combine the data, allowing us to place fragments of the two dimensional images into three dimensional space, navigate through the resulting environment and render the output.
In this case the results are displayed as still images with the 3D creating strange and fragmented forms.
Another interesting experiment takes video and similar custom software to create a moving 2.5D display.
Clearly there are lots of ways of using the depth data available from a Kinect to create artistic experiences. You could say that AR doesn't just stand for Augmented Reality but Artistic Reality.
Neural networks are great at reacting to complex data, but not so good at the sort of slower thinking it takes to solve a problem like getting from A to B using a subway or unscrambling a sliding bloc [ ... ]