Skeleton Tracking
J. H. Webb, James Ashley · Apress eBooks · 2012
The raw depth data produced by Kinect has limited uses. To build truly interactive, fun, and memorable experiences with Kinect, we need more information beyond just the depth of each pixel. This is where skeleton tracking comes in. Skeleton tracking is the processing of depth image data to establish the positions of various skeleton joints on a human form. For example, skeleton tracking determines where a user’s head, hands, and center of mass are. Skeleton tracking provides X, Y, and Z values for each of these skeleton points. In the previous chapter, we explored elementary depth image processing techniques. Skeleton tracking systems go beyond our introductory image processing routines. They analyze depth images employing complicated algorithms that use matrix transforms, machine learning, and other means to calculate skeleton points.