The Magic of Gestural Interface

I'm a fan of technology based on gesture recognition - that's hardly a secret for anyone. I believe that while in its simple sense promises a way for computers to begin to understand human body language, at a deeper level it will allow us to build a richer bridge between machines and humans, beyond the primitive text and graphic user interfaces and the limited input we now have via keyboards and mouses.

Well, the guys at MIT Media Lab are certainly ahead of the game when it comes to create devices leveraging this technology and, over the last few years, they have worked on several projects trying to improve the human-computer interface based on the magic of gestural recognition. G-Speak is one of their latest - and best - examples.



Developed together with Oblong Industries (started back in 1996), G-speak fully immerses the user into the computer environment by making use of real-world space and geometry and combining gestures and spatial location to interact with on screen objects.

The SOE's combination of gestural i/o, recombinant networking, and real-world pixels brings the first major step in computer interface since 1984; starting today, g-speak will fundamentally change the way people use machines at work, in the living room, in conference rooms, in vehicles. The g-speak platform is a complete application development and execution environment that redresses the dire constriction of human intent imposed by traditional GUIs. Its idiom of spatial immediacy and information responsive to real-world geometry enables a necessary new kind of work: data-intensive, embodied, real-time, predicated on universal human expertise.

Yes. I'm sure it seems familiar. Remember the movie Minority Report, where characters performed forensic analysis using massive, gesturally driven displays? Well, the chief scientist for Oblong Industries, John Underkoffler, was one of the movie's science and technology advisors to the film and based the design of those scenes directly on his earlier work at MIT.

Can you imagine how much the interaction between people and computer can change based on this? How activities such as gaming and social media can be impacted? I'm certainly looking forward to see it.

Interestingly, the G-Speak platform is already in use in a variety of Fortune 50 companies, government agencies and universities - they offer a software development kit that runs on both Linux and Mac OS X. Yet it seems like the mainstream will have to wait longer to be able to use it. Now, considering that just few years ago things such as continuous speech recognition or face and fingerprint analysis were considered part of sci-fiction, making gestures to control computers really doesn't feel so far away.