Slashdot Mirror
Video Surveillance System That Reasons Like a Human
An anonymous reader writes "BRS Labs has created a technology it calls Behavioral Analytics which uses cognitive reasoning, much like the human brain, to process visual data and to identify criminal and terroristic activities. Built on a framework of cognitive learning engines and computer vision, AISight, provides an automated and scalable surveillance solution that analyzes behavioral patterns, activities and scene content without the need for human training, setup, or programming."
that was a press release for the company's product. It has no reliable or interesting information whatsoever.
So it's a subsidiary of Spinvox then?
With good heuristics, some bayesian analysis (is there an object or not?) or neural nets...I can actually imagine a lot of possibilities here. Suppose I've got a gate at an airport--traffic should all be going in one direction. Anything going the other way--anomaly. I could imagine ML systems picking that up fairly easily.
Similarly if I've got a physically secured compound with double fences (the first fence is for screening--the second is your secure perimeter), foot traffic in the secure area should be predictable, on a schedule, and follow certain rates and patterns. Anything outside the pattern would be worth throwing a red box around and drawing human attention to. Even if it didn't get a "time" input, the presence of motion in unusual planes, or of non-human shapes might be a viable alert.
Detecting terrorism...okay...that seems funky. But I can definitely imagine that with a little bit of context you could very easily rig a good camera system up to alert on unusual events if the light levels were done correctly.
To do what AISight does one needs:
Moving objects must be dynamically tracked and their behavior somehow segmented into steps. This is arbitrary in that there can be a theoretically infinite variety of such segments for any given macro behavior. E.g., I can say "Mary handed the book to Tom." or I can say "Mary grasped the book, Mary extended her arm in the direction of Tom, Tom extended his hand in the direction of Mary and grasped the book, Mary un-grasped the book, Tom retracted his arm (with the book)." Both describe the same action, but the second has a finer segmentation of behavior.
All the pieces are available in freeware. It's essentially a classic AI expert system. Since they're getting millions for known technology (and software), I expect to see a freeware version of this available soon!8-))
"interesting" is context-sensitive. So filtering will not work: it either triggers false positives (normal behaviour that is unknown or misinterpreted) until the threshold is raised enough. Then it will create false negatives, e.g. flag an actual criminal act as 'normal' and hide it from the supervisors eye for workload reasons.
Human behaviour is more complex and situation depended than actual AI could handle. This whole article reads like bullshit bingo or a pr-campaign for some insider stock trading scams.
And even *IF* (and this is a big if) it might work like proposed - do we really want to implement fully automatic total survaillance? And do not think this will be restricted to the fence of a top secret naval base. It will be produced by corporations, meaning there will be some strong interest into widespread use. And there will always be the need for politicians to ring the alarm bell and demanding more 'security'. Have a look at UK - highest density of surveillance and yet problems with terrorism and crimes.
I agree in business its ok, but really every intersection in Texas has 4 cameras now. Even ones in small towns, paid for by grants from DHS.
In the Dallas Metroplex, they have also installed networking which is supposed to be used by emergency workers (this makes me laugh as when there is a real disaster they will not have power) but I am sure they are also being used by the cities to read the power and water meters in the future.
Taking even a small failure rate, the cost of maintenance will be beyond what the cities can stand to keep the systems up. The big brother ideal will fail and only leave us with a bill to pay.