As announced at the CES 2012 in Las Vegas last month, the Kinect for Windows SDK version 1.0 and runtime are now available. The partners in the twelve launch countries are starting to ship Kinect for Windows hardware, enabling companies to start to deploy their solutions.
For those new, Kinect for Windows SDK enables developers to create applications that support gesture and voice recognition, using Kinect sensor technology on computers running Windows 7, Windows Embedded Standard 7, and Windows 8 Developer Preview (desktop applications only). It includes the following:
- Drivers, for using Kinect sensor devices on a computer running Windows 7, Windows Embedded Standard 7, and Windows 8 Developer Preview (desktop applications only)
- Application programming interfaces (APIs) and device interfaces, along with technical documentation
- Source code samples
Kinect for Windows SDK v1 and runtime comes with following improvements:
- Support for up to four Kinect sensors plugged into the same computer
- Significantly improved skeletal tracking, including the ability for developers to control which user is being tracked by the sensor
- Near Mode for the new Kinect for Windows hardware, which enables the depth camera to see objects as close as 40 centimeters in front of the device
- Many API updates and enhancements in the managed and unmanaged runtimes
- The latest Microsoft Speech components (V11) are now included as part of the SDK and runtime installer
- Improved "far-talk" acoustic model that increases speech recognition accuracy
- New and updated samples, such as Kinect Explorer, which enables developers to explore the full capabilities of the sensor and SDK, including audio beam and sound source angles, color modes, depth modes, skeletal tracking, and motor controls
- A commercial-ready installer which can be included in an application's set-up program, making it easy to install the Kinect for Windows runtime and driver components for end-user deployments.
- Robustness improvements including driver stability, runtime fixes, and audio fixes
The suggested retail price is $249, but Microsoft will also offer a special academic pricing of $149 for Qualified Educational Users later this year.
Download Kinect for Windows SDK v1 here.
Microsoft also published a series of video to help you get started with the Kinect for Windows SDK v1:
Installing and Using the Kinect Sensor video covers the basics of installing and using the Kinect sensor using v1 of the:
- An overview of the Kinect for Windows Quickstart Series
- An overview of what sensors and information you can use with the Kinect hardware
- Demos: We'll show what gets installed on your PC when you install the Kinect SDK and how you can use your Kinect as a microphone using Windows Sound Recorder.
Setting up your Development Environment discuss the following topics:
- The basics of using the Managed API
- The key developer resources to use in your application like the KinectWpfViewers that ship Kinect SDK Kinect Explorer sample and the Coding4Fun Toolkit for skeletal scaling that will be used in later Quickstart videos.
- Demos of how to manage and connect to a Kinect using the KinectSensors collection and using the KinectSensorChooser WPF control
Camera Fundamentals quickstart video convers:
- How to leverage the AllFramesReady event to synchronize data between the color, depth, and skeletal frames
- The supported resolutions for the color and depth cameras
- How to read the color byte array from the ColorImageFrame event and how to dynamically build a Bitmapsource to display the color image
- How to use the KinectColorViewer user control to display the Kinect's color image simply by databinding the Kinect property to the KinectSensorChooser user control
- How to tilt the Kinect camera and how it determines it's current angle
Working with depth data video includes:
- An overview of how depth data represents the distance and player for every pixel
- An overview of Default and Near Mode and what features are supported in both
- An explanation of what distance data the Kinect returns including knowing when you are too near, too far, or the distance is unknown
- The formulas for calculating depth and player information
- How to visualize depth and player data, including a monochrome histogram and player colorization
- How to use the WPF DepthViewer control to understand depth data returned from the Kinect
Skeletal Tracking Fundamentals video discusses:
- How skeleton data retrieves joint information for 20 joints (head, hands, hip center, etc)
- How skeletal tracking works and how you can choose what skeletons to track using tracking IDs.
- How you can tweak TransformSmoothParameters based on your applications needs (responsiveness versus smoothness)
- How you can use the built-in depth mapping methods to map a skeletal joint's position into depth and color space
- How you can use the Coding4Fun Toolkit to scale the skeletal joint value to make it easier for users of your application to not have to extend their reach when using your hand as a cursor
- How to use the SkeletonViewer to visualize all joints returned by Kinect including whether those joints are not tracked.
Audio Fundamentals discuss how you can leverage the audio features of Kinect in your application, including:
- How to use your Kinect to determine the angle and confidence for where a sound is coming from
- How to use the KinectAudioSource to record audio synchronously and asynchronously
- How to build a basic speech recognition application to dynamically turn application features on/off
- How the speech recognition engine can be used even when the application is not the current active application