I was in Boston not too long ago on business. Boston is not a city that I have often frequented, but I found it to be beautiful with a mixture of the old with the new. Prior to my visit, I had recently read David McCullough’s fine book, 1776, which has much of its context in the old city of Boston. As I walked around the city looking at the buildings, I imagined what it was like in 1776.
I wished I could put the buildings and the text of the book in context, but I didn’t have time for a tour. I thought, “Wouldn’t it be cool if I could take a picture of a street scene and instantly be able to identify what I was looking at? Something like what the Bing search does on its home page.” The page displays an image that is tagged and hyperlinked to information about elements of the image. Now imagine that you could take a picture with your mobile camera, and those buildings in the picture would be automatically tagged using image recognition and actual GPS coordinates of the buildings. The picture would be placed in the context of my location and hyperlinked to information about the objects in the photo. You would have an automated tour guide.
This is not as farfetched as you might think. A new area of study called Attentive User Interfaces promises to make this a reality soon. Attentive user interfaces combine multimodal context awareness, vision-based object recognition and intelligent map technology to enhance perceptive presence. Leading research in this area is being conducted in Europe and has caught the attention of leading industrial heavyweights like Google, Microsoft and Nokia. Stay tuned for an app coming soon to your iPhone.