next up previous
Next: A wearable face-recognizer Up: The `visual memory Previous: Deja vu

Salient stack

We've all no doubt been lost at one time or another. Maybe you drive into a shopping complex, gambling complex, or the like, park your car, then can't find your way back at the end of the day. Wouldn't it be nice to be able to ``remember'' the path back to your car.

Imagine a stack of salient keyframes from your visual past. You see the roulette wheel on your right (that means turn left because you're walking in the opposite direction) then some slot machines to your right, then an escalator, looking up (which means you've got to go downstairs to get back to where you were before)... and yes, you see the parking garage, and you can even make out the letters `P5' so you now remember you were in level 5.

One way I overcome my visual memory disability and save myself from getting lost in a large shopping complex is by building up a stack of images, consciously deciding to capture an image at each branch point (this is the non-cyborgian mode of operation of the visual memory prosthetic). The current implementation uses the Wearable Wireless Webcam: each image is appended to the web page, and then the Web browser (Mosaic) is invoked. Alternate implementations have been built using a local image stack but the Web stack allows for shared applications (e.g. suppose that someone else was going to meet me --- she could start up Mosaic in her eyeglasses and quickly catch up to me).

Steve Mann
Wed Feb 14 01:19:59 EST 1996