The software can be downloaded here. According to Microsoft, the SDK will allow access to raw data streams from the depth sensor, colour camera sensor, and four element microphone array.
This will let developers build upon the low-level streams that are generated by the Kinect sensor.
It can track the skeleton image of one or two people moving within the Kinect field of view and make it easy to create gesture-driven software.
There are also audio processing capabilities, including acoustic noise suppression and echo cancellation, beam formation to identify the current sound source, and integration with the Windows speech recognition API.
It is fairly involved. The SDK includes more than 100 pages of technical documentation for those who need to read the manual and there are built-in help files.
The Kinect has been one of Microsoft’s few success stories. On the Xbox it has flogged 0 million units since its release in November 2010.
People have been using hacks to access the Kinect on their computers and have come up with some interesting ways of using it.
Currently the SDK can only be used for non-commercial purposes, but Microsoft said that there will be a commercial version in the future.