Microsoft has published a scientific research paper ([PDF] Real-Time Human Pose Recognition in Parts from Single Depth Images (Microsoft Research)) detailing how Microsoft Kinect’s body tracking algorithm works. There is also a video (Kinect Research (youtube.com)) to go along with it. Also, I came across a separate article (Kinect’s AI breakthrough explained (I-Programmer.info)) which summaries how the algorithm works. Here is a small quote from that article:

“What the team did next was to train a type of classifier called a decision forest, i.e. a collection of decision trees. Each tree was trained on a set of features on depth images that were pre-labeled with the target body parts. That is, the decision trees were modified until they gave the correct classification for a particular body part across the test set of images. Training just three trees using 1 million test images took about a day using a 1000-core cluster.”

More Information:


Share