LONDON – Microsoft Corp. has announced a free beta release of the Kinect for Windows software development kit (SDK).
Kinect is the gesture recognition system deployed by Microsoft in its Xbox 360 games console. It is based on recognition software developed by Microsoft and a 3-D image sensing technology developed by fabless chip company PrimeSense Ltd.
The SDK is a free beta release for noncommercial applications intended for developers, academic researchers and enthusiasts to create applications that include depth sensing, human motion tracking, and voice and object recognition using Kinect technology on the Windows 7 operating system.
The KfW SDK includes driver software, APIs for sensor streams, user interface routines, installer documents and other resources and supports the writing of applications with C++, C# or Visual Basic using Microsoft Visual Studio 2010. The Kinect sensor system can be bought stand-alone at retail stores and it produces data streams based on depth sensor, color camera sensor and a four-element microphone array. The SDK provides access to each of these.
The SDK has the capability to track the skeleton image of one or two people moving within the Kinect field of view, making it possible to create gesture-driven applications. Audio processing capabilities include sophisticated noise suppression and echo cancellation, beam formation to identify the current sound source, and integration with the Windows speech recognition API.
Microsoft said it intends to release a commercial version of the SDK at a later date.
As taken by surprise as MS probably was (that Kinect internals were as accessible as they were) they responded pretty quickly; stating almost immediately that this was their intention and [finally] coming through with an SDK.
Quite cool! now we'll be able to explode the control and we'll soon see the streets with new kiosks or interactive boots where you'll be requested to dance or make a strange body move just for fun or for winning a contest or something like that. I bet after refining this technology, this could be very well used for recognition since everybody moves different, I mean, I could distinguish MJ just by his jump shot, imagine a system recognizing you just by your walk.
You figure that they just about had to do it. Most of the interesting hacks have been using Linux, which had to be a little embarassing for MS. It probably won't replace a mouse and KB, but it would be a good platform to experiment with offbeat user and environmental interactions.
It seem that the fiction will be more realistic in the future due to these kind of developments but at the end of the day it will be fiction only.
Do you think that one should live in a non realistic world?
I am raising a non-realistic question at this point but it is worth giving a thought at this point of time.