The problem with surveillance cameras is that they can see but they can't think, which means there always has to be a human on the other end making cognitive sense of what's right in front of the camera. But if we meshed machine vision with visual intelligence, DARPA argues in a solicitation for its new "Mind's Eye" program, we could remove the human element from myriad tasks.
In essense, DARPA wants a smart camera that not only sees what's in front of it, but thinks about what's going on and even what might happen next.
For humans, taking in our surroundings and applying learned concepts to them is innate. We can use our imagination to apply learned concepts to potential scenarios that haven't even taken place. These things are so easy to do we don't even think about them, but they're very difficult to duplicate in machines.Machines, DARPA argues, can't piece the entire mosaic of space together, perceiving only the "nouns" in a given setting. "The focus of Mind's Eye is to add the perceptual and cognitive underpinnings for recognizing and reasoning about the verbs in those scenes, enabling a more complete narrative of action in the visual experience."
Applications for such technology abound, but specifically DARPA mentions the need for a smart camera that can "report on activity in an area of observation." The agency sees such visual devices deployed on fixed surveillance platforms, "camera_equipped perch-and-stare micro air vehicles" and unmanned ground vehicles. But if the technology is such that it can do all the things DARPA wants it to, we think they can do even better.
[DARPA via Danger Room]
138 years of Popular Science at your fingertips.
Stay up to date on the latest news of the future of science and technology from your iPhone with full articles, images and offline viewing
Featuring every article from the magazine and website, plus links from around the Web. Also see our PopSci DIY feed
Share links with friends, comment on stories and more
This month, a look at the future of secret warfare, the dangerous search for Afghanistan's mineral wealth, a backyard flamethrower, and the most amazing college labs.
Read the issue here.

Editor: John Mahoney | Email
Associate Editor: Paul Adams | Email
Contributing Writers:
Clay Dillow | Email
Rebecca Boyle | Email
You know... DARPA wants everything. I bet DARPA would want a base in the middle of the earth if they thought they could pull it off.
Yes, your right, they would (and do).
Big Brother is on his way. Maybe the book 1984 should be renamed 2012.
DARPA does want everything. A lot of technologies they want only help aid in conspiracy theories.
To me, this just doesn't seem very economical. You pull out the human observer, replace him/her with a computer - which costs about 100 times more than the human's salary, will no doubt be prone to errors and glitches, and will probably take up much more space.
And Heaven help us if these things are relied upon to provide military intelligence. The smartest computers in the world today can barely measure up to a small mammal brain; even beginning analysis trainees can recognize what they're seeing better than that.
Why do so many people assume that machines can outperform humans at everything?
Re: Q42
I agree that machines cannot replace humans, they are just not that intelligent yet. However, think of this: What if you had a "smart camera" that could identify when something may be happening within it's field of view. The "smart camera" then alerts the human observer who may or may not have noticed, especially if he/she has over 20 screens to watch. As I'm sure is sometimes the case.
I see this tech as augmenting our current surveillance tech rather than replacing it.
It costs 8$ an hour for a human job at the least +
6 hours a day times 300 (minus approx 60 days off=14424$
im pretty sure a computer camera and softwar etc. cost less.
Computers can be fooled. Humans are considerably less likely to be fooled. DARPA needs to understand this and SLOW DOWN!!