MIT’s 3D Gestural Computing For Everyone
The Handtracking project makes inexpensive human-interface computing a reality.
The folks at MIT continue to produce stunning work — the latest project in the form of extremely cheap gestural computing. The “Handtracking” project requires only a colorful lycra glove and a standard webcam, which is available on most new computers, to generate stunning 3-D capabilities (see below).
So what does all this cheap gestural computing mean? Well, it has direct applications for video games and learning as seen through the video.
In addition, Wang is expanding the idea to create a patterned t-shirt, for use capturing information about human motion. These types of systems are already used create digital animations for video games, but Wang and Popović’s work would make those systems dramatically cheaper and easier to use.
THE TECHNICAL DETAILS
The process, which is called “handtracking,” builds on two important designs.
The first is the layout of the multi-colored glove, which “is covered with 20 irregularly shaped patches that use 10 different colors. The number of colors had to be restricted so that the system could reliably distinguish the colors from each other, and from those of background objects, under a range of different lighting conditions.”
The second development stands on the shoulders of previous work done at MIT on a “new algorithm for rapidly looking up visual data in a database.” The algorithm is what allows the software to map the hand on the computer screen.