Just before the start of the weekend, Mary Jo Foley broke the story that the Mountain View lab of Microsoft Research was being closed. Ideally, most of the researchers will be redistributed to other locations and not be casualties of the most recent round of layoffs.
The Kinect sensor is one of the great examples of Microsoft Research successfully working well with a product team to bring something to market. Researchers from around the world worked on Project Natal (the code-name for Kinect). An extremely important contribution to the machine learning required to make skeleton tracking work on the Kinect was made in Mountain View.
Machine learning works best when you are dealing with lots of data. In the case of skeleton tracking, millions of images had been gathered. But how do you find the hardware to process that many images?
Fortunately, the Mountain View group specialized in distributed computing. One researcher in particular, Mihai Budiu, worked on a project that he believed would help the Project Natal team to solve one of its biggest hurdles. The project was called DryadLinq and could be used to coordinate parallel processing over a large server cluster. The problem it solved was recognizing body parts for people of various sizes and shapes – a preliminary step to generating the skeleton view.
The research lab at Mountain View was an essential part of the Kinect story. It will be missed.