The article says:
Quote:
|
The wearer could walk around an office or factory identifying certain items by pointing at them. Objects indicated are then given a blank label on a screen inside the glasses that the user then fills in.
|
How are you supposed to fill in the label? Later, when reviewing the video? I don't see any cords going down to the waist of the person where a portable keyboard could be stashed in a fanny pack. (Oh, the image of coolness.) I see no microphones for voice stamping the entries.
The full text doesn't seem to say they follow eye movement, but maybe my reading comprehension isn't what it should be.
I think this is just a couple of webcams mounted to a helmet with a view screen in front of the eyes. I think the only real benefits here are the dual cameras can make a 3D image, and the camera is wearable. The article really pushes the ability to label images, so maybe there is some sort of software that makes the images easy to label and find later.