Gesture recognition – the next big opportunity for machine vision?

Is it safe to say that you are all familiar with the Kinect from Microsoft? If not, allow me to summarize: the Kinect allows people to control their Xbox game system by making gestures. The system projects a pattern of infrared dots out into the room, and these are seen by a camera set some inches to the side of the projector. With a little bit of math, the Kinect can work out the 3D coordinates of each one of those dots. Thus when a user moves his hand in a certain way, the system sees that motion and can translate it into a command.

However, there is an alternative method, and that is to use 2 cameras in a stereo set up. This is the approach taken by TYZX in their 3D products. In fact if you take a look at their website you’ll see they’re doing some really cool things, like tracking people in retail environments.

Now TYZX is an interesting company, not least because a Paul Allen is listed as one of their investors (the Paul Allen? I’m guessing so.) In fact they are going in the direction that, a few years back, I expected Cognex to take: broadening the application of machine vision to sophisticated 3D tasks, like intelligent control of entrance doors. Well TYZX aren’t doing that yet, but I feel sure their portfolio of patents would let them go in that direction.

And related to all this is the recent news that Qualcomm has acquired the gesture recognition technology of GestureTek. Now Qualcomm is a big, smart organization, so I’m sure the only reason they would make such an investment is because they see a big opportunity in the years ahead. As does Paul Allen. As, indeed does Microsoft, who are starting to look very smart in quickly leaping in to bed with Primesense.

It all points to an area that’s rapidly becoming ‘hot’, so I suggest we watch these companies closely.