13 December 2010

Exploring Microsoft Kinect

Microsoft Kinect is the latest offering by software giant Microsoft in the world of console gaming. Kinect is the newest device to enter the quickly emerging motion gaming market. Launched in November 2010, it is Microsoft’s answer to the Nintendo Wii and Playstation Move motion gaming controllers. Although Kinect can, in principle, be clubbed with these devices, its working principle is radically different. Microsoft Kinect aims at revolutionizing the motion gaming industry by using the player’s body itself as the controller. Unlike other motion gaming devices, Kinect does not have a controller that must be held by the player. Instead it has a motion capturing camera that tracks every single movement of the user. It then uses these motions to allow the user to play games, control menus and start applications. This motion capturing technology is a combination of an “RGB camera, depth sensor and multi array microphone running proprietary software”. Apart from tracking 3D motions, the Kinect sensor is also capable of recognizing voice and facial patterns. This means that a user just has to step in front of the sensor and he can be automatically logged into his profile and that one can control menus or pause/unpause games by simply saying so. Requiring a working space of six to eight feet, Kinect ships with a starter kit of games including titles such as Kinect Adventures and Dance Central . Since its release Kinect has sold more 2.5 million units and is set to revolutionize the gaming industry.      

I was exploring as to how one can really play/tweak with kinect when i came across this interesting article by Sebastian,you can find more here .This is how it goes,... there's a cool video which he feature its also attached here.
With the release of OpenKinect, an open-source library that lets PC users interact with Microsoft's depth-sensing and environment-recognizing Kinect, crazy-cool applications of the technology are beginning to emerge. In this video (embedded after the break), one creative hacker mashes together a bunch of open-source libraries to create... well, a modern-day equivalent of HAL 9000. 

Using OpenKinect as an interface, OpenCV to process the captured images, CMU Sphinx to recognize speech and Festvox to synthesize speech, one hacker was able to create a program that recognizes random real-world objects and communicates with a user in real time. He notes in the video's description that it's just a 'proof of concept', but one wonders how long it actually took him to cobble it together because the video was uploaded only a few days after OpenKinect's release.

The most exciting prospect though, in my opinion, is that Microsoft must surely be working on their own in-house tools (and games!) to better utilize Kinect's potential. The cocky work of lone cowboy coders is one thing, but next-generation interfaces from powerhouses like Microsoft are something else. 

You can view the original article here  .

No comments: