Abstract

Microsoft recently launched Xbox Kinect (http://www.xbox.com/kinect), a revolution in gaming where your whole body becomes the controller. Human pose estimation has long been a “grand challenge” of computer vision, and Kinect has been the first product that meets the speed, cost, accuracy, and robustness requirements to take pose estimation out of the lab and into the living room.

In this talk we will discuss some of the challenges of pose estimation and the technology behind Kinect, detailing a new algorithm, body part recognition, which drives Kinect’s skeletal tracking pipeline. Body part recognition uses a classifier to produce an interpretation of pixels coming from the Kinect depth-sensing camera into different parts of the body: head, left hand, right knee, etc. Estimating this pixel-wise classification is extremely efficient in parallel on the GPU . The classifications are then pooled across pixels to produce hypotheses of 3D body joint positions for use by a skeletal tracking algorithm. Our method has been designed to be robust, in two ways in particular. First, we train the system with a vast and highly varied training set of synthetic images to ensure the system works for all ages, body shapes & sizes, clothing and hair styles. Second, the recognition does not rely on any temporal information, and this ensures that the system can initialize from arbitrary poses and prevents catastrophic loss of track, enabling extended gameplay for the first time.