Kinect Chapters 1 and 2.   Kinect Imaging

This chapter was previously labelled as "NUI Chapter 13".

The following chapters are about controlling Microsoft's Kinect Sensor using Java. This chapter introduces the Kinect, explains how to install the developer software on Windows (which can be a bit tricky), and looks at basic imaging (depth detection, camera, and infrared (IR)).

Future chapters will look at point clouds, skeletal user tracking in 2D and 3D, tilt motor control, hand tracking, basic gesture support, and gesture-controlled GUI components.

For readers already familiar with Kinect development, I'll be using OpenNI and NITE, not OpenKinect, CLNUI, or Microsoft's Kinect for Windows SDK. The 3D features (in the point cloud and skeletal tracking examples) are implemented using Java 3D.

I'll be using the Java API released with OpenNI and NITE in mid-July 2011; I won't be utilizing Processing libraries such as Simple-OpenNI.

Kinect imaging is explained using six versions of a viewer application:

• Version 1: draws a grayscale depth map specified using an XML configuration file.
• Version 2: also draws a grayscale depth map, but created at run time using a Context object.
• Version 3: shows a camera image map.
• Version 4: renders an IR map.
• Version 5: draws a colorized depth map.
• Version 6: shows a combined colorized depth and camera image, which is shown at the top of this page.

Downloads

• The PDF file for the draft chapter (732 KB). Last updated: 15th September 2011.
  
• Zipped code for Chapter 1 (3 KB). Last updated: 16th February 2012.
  
• Zipped code for Chapter 2 (36 KB). Last updated: 25th July 2012 (I modified version 6).
  IMPORTANT: the installation details for the OpenNI and NITE software have changed since the book was published; please read the details on the main KOPS page.

• Up to the Kinect Open Source Programming Secrets Index Page
• Back to OpenNI/NITE Installation on Windows
• On to Chapter 2.1. Charting the Depth Map