Slashdot Mirror
Airport Video Surveillance Goes Hi-Tech
conq writes "BusinessWeek has a piece on new tech used in the airport of Helsinki to monitor behavior and alert people when predefined situations arise. From the article: "The system can alert staff to events which may need further investigation without the need for every camera to be observed by staff. For example, suspect packages or vehicles left unattended will be flagged up and staff alerted. Similarly if the system detects queues growing beyond a pre-defined length in the security zone staff will be alerted of the need to open another lane""
Similarly if the system detects queues growing beyond a pre-defined length in the security zone staff will be alerted of the need to open another lane.
Can't the actual human employees at the head of the line make this determination and alert whomever has the authority to open another lane? Seems like a solution looking for a problem if you ask me.
...if the system detects queues growing beyond a pre-defined length in the security zone staff will be alerted of the need to open another lane
Forget the airport, I want this at my local supermarket!
"Kittens give Morbo gas!"
... when I see a line of 500 densely-packed people waiting to go through an X-ray machine intended to prevent somebody from blowing up a plane loaded with 200 densely-packed people.
"Security theatre," indeed.
I design security systems just like that one and I know that the video analysis software is not yet good enough to pick out "suspect packages". Sadly, relying on the passengers in the airport or commuters in the rail/subway stations is still the most-effective method of identifying suspect/left packages.
I wonder how it detects an unattended package. If said package is left in a crowded area, will the system be confused that such package is still being "attended" by moving traffic?
Please stop entering code 2,2,7,6,6,4
"Similarly if the system detects queues growing beyond a pre-defined length in the security zone staff will be alerted of the need to open another lane"
Mondays incur serious bottlenecks here at IAH Terminal C (Houston). The security staff seems stymied by their limited empowerment to work the crowd. Often, the line extends out the door, and sometimes into traffic. In fact, it's often more expedient (though no less "secure") to check into a different terminal altogether, then walk or take a tram to Terminal C's gates. The idea that we could open several lines seems beyond the security personnel.
The odd thing to me is that this airport seems the *least* offensive of several majors. Perhaps it's just my familiarity with Houston's particular brand of inefficiency.
I know that the security measures in most were put in place *after* 9-11; therefore, they didn't benefit from any really modern analysis of their security methods (Denver is the most egregious that I've found, to date). However, true to "government droid" stereotypes, the people manning the lines can't seem to think adaptively *and* provide equivalent security.
Ah well, getting to the airport 2 hours early is supposed to be relaxing, somehow....
In the UK over the past few years there've been various rights-eroding laws put in place (e.g. warrantless searches and arrests if they suspect you're a terrorist), and then this happened.
What worries me is that the security staff are going to blindly believe the computer's "this is suspicious", causing the person huge inconvenience despite any actual evidence of him being a terrorist on his person. See the link - just because someone matched enough random, minor items on (presumably) some sort of mental checklist in the security staff's head, they put him through huge inconvenience, arrested him, searched his house, took his cellphone's SIM card, took computers from his home, all without a warrant, simply because they had enough things crossed off to be able to mark him as "suspicious" (and thus use the Terrorism Act), despite there being absolutely no proof on his person.
If this gets done, thus moving the mental checklist into the computer, I can only hope there WILL be regular false positives (so that the security staff take it with a pinch of salt and use it as a guideline only), else they might suspect people unduly despite there being no cause for suspicion other than "the computer says so".
I know of one security system where it just has a picture of a room and then when the camera is on it just looks for things that don't match the original, if those areas of non-matching do not move for more than X amount of time the system then draws a yellow outline around the object, if it still does not move in another X amount of time, the outline becomes red. The system is pretty good and adapts to furniture/plants being moved around by staff. Myself and others even joked about the cheese factor of using colours like that, but it was/is a very robust method of surveillance.
This system was in place in a casino, all the way back in 1998.
Why are these things being labled as new technolgy?
I'd be more impressed if they had a system that could scan and tag/match all faces/voices that it sees and hears in an airport.
Airport security in the US, under the TSA, is anything but prevention. Its a stupid feel good charade. It would be better let to a machine to make false positives because at least then you know its not being done out of spite or bias as is now.
I have never figured out why my mother (63 years old) gets singled out at the security checkpoints as often as she does. Twice she was stopped because of the dog carrier (small dog - soft carrier) - once because she had to explain that you cannot put the carrier through the x-ray machine with the dog in it.
The real reason to find a way to let a machine make the call is because at least it can be viewed as impartial. It would be about the only way to have security instead of political correct neutered "security" we have now. Then again, in the US at least how can we have airport security if we don't even bother to police our own borders?
* Winners compare their achievements to their goals, losers compare theirs to that of others.
...once these cameras are connected to Skynet.
Based on my first hand experience as a Finn, I must say we do tolerate diversity very well. But there is a difference between not tolerating diversity and profiling suspects. Look at the photographs of people who have committed terrorist attacks in the last few years. See from which countries they come from. What is their religion. Thirty years ago, when the Baader-Meinhof gang was a terrorist threat, people with pale skin, blond hair, and blue eyes were tagged as terrorist suspects as well.
Of course, the fact that fundamentalist Islamic terrorists have black hair and olive skin doesn't mean that everyone with that description is a terrorist, but when the police must find a few terrorists among six billion people it helps if they can narrow their search somehow. One terrorist among a billion people is still a needle in a haystack, but it's six times easier to find him with an ethnic profile than without one.
Now, if the technology is tried, tested and improved enough, why not put 'em everywhere. You know, juste like in London, to prevent crimes. Then vote some laws that says doing this or that is terrorist-like and then illegal. Then arrest more people.
Yeah, I'm stretching it. But you know, when the technology's there, available and working, there is no reason not to use it. Then you can mix techs and end up with nicer cocktails. Like an "ID tag canon" that shoots a tiny RFID tag on someone when the camera decides he looks suspicious -- it'll be easy to follow him. Then you bust his ass when he gets home and hope to find some pot or porn.
Ok, ok. Sci-fi gibberish. But still, if *I* can think of this, I'm sure many others can come up with worse than that. And apply it.
You are more than the sum of what you consume. Desire is not an occupation.
Several years ago I spoke with a friend of mine who went to work in the security department of a major retailer as a programmer. The project that he was working on was to design a system that would detect motions that would identify shoplifters, thieves, and other bad guys (like thieving employees). They used things like furtive movements and a person's route through the store to trigger the system that would sound the alarm and bring the camera online to a security officer. They used hundreds of hours of security video showing crooks doing their work to vet the system and they had it working pretty well. I would imagine that this is a system similar to what they are doing at the airport.
He did share some humorous observations about this work. The system would frequently target completely innocent little old ladies as potential shoplifters. Apparently their movements while on a routine shopping trip were quite similar to a crooks and the system was not able to differentiate between them.