At the recent MIX11 show in Las Vegas, Microsoft announced the release in May of a Windows software development kit (SDK) for Kinect for Xbox 360. Since Kinect launched in November 2010, enthusiasts have been exploring the potential of Kinect in a number of unexpected, nongaming scenarios, including industrial and service robots.
Microsoft detailed some of the features in the Kinect for Windows Beta SDK from Microsoft Research coming, including the following:
• Robust Skeletal Tracking for high-performance capabilities that track the skeleton image of one or two persons moving within the Kinect field of view
• Advanced Audio Capabilities, including four-element microphone array with sophisticated acoustic noise and echo cancellation for great audio; beam formation to identify the current sound source and integration with the Windows speech recognition API also included
• XYZ depth camera for standard color camera stream access and depth data that indicates the distance of the object from the Kinect camera
This SDK is intended for non-commercial use to enable experimentation in the world of natural user interface experiences, with new state-of-the-art features planned for future releases that will continue to provide new ways to experiment.
Microsoft Research recently released an 8-page research publication to be presented at the IEEE Conference on Computer Vision and Pattern Recognition in June titled Real-Time Human Pose Recognition in Parts from a Single Depth Image. The paper reveals a lot of interesting facts, science, and data behind the algorithms of Kinect.
Developers can sign up to be notified of the release at Microsoft's Kinect site.
--Posted by Vision Systems Design
