Large quarter square mile urban campus challenged by surrounding community’s teens. We recommended dedicating a couple basketball courts in exchange for the players keeping an eye on things.
I’ve been involved in safety & security for over thirty years and have advised to military, prisons, institutions, industry & insurance companies and have done expert witness work in three states. This is truly the most remarkable advance I’ve ever seen.
If you are familiar with “video analytics” you know that rules could be set where artificial intelligence would watch your surveillance cameras and identify people and vehicle breaking the pre-set rules. It would then alert your staff. It also allowed for immediate “talk-down” by an officer over a public address loudspeaker to help stop a perpetrator before they committed their crime. It could identify a person much better than a human monitoring the scene, even far away with poor illumination, rain, fog, etc. But this had serious limitations in settings where there are many legitimate people in an area. Now a truly remarkable advance has been made. First developed and paid for by huge government grants for military and large public sector, it is now released for private sector. The intelligence watches the environment and learns what normal behavior is. It then reports any anomalies — any abnormal behavior.
This is really perfect for complex areas like university campuses, hospitals, train and bus stations, apartment complexes, parking garages and lots, and so forth where thousands of people belong there all the time. The prior system you were either setting a rule “no one can be in this area” or “people can be here.” But this learns what is normal there: a student on campus walks down a walkway at night and puts his arm around his girlfriend. Fine. But someone walks there and pushes someone to the ground. Problem. This can handle this distinction on its own. Someone goes to their car in a lot and gets in. Good. Someone is casing out the car for how to break in. It recognizes a problem.
It is remarkably inexpensive since it is simply added to any existing video surveillance system. Here the artificial intelligence has taken a huge leap. There is no longer any need to set rules for the system. There is no need to anticipate the unexpected. This does it for you. For example at a train station it is normal for people to jostle or bump into one another as they get onto a train. But at an ATM machine it is not normal for one person to bump into another. Back to the train station the shoving is normal but if someone ends up on the ground that is not normal. A fire starting or a cloud of smoke is not normal in most environments. Someone walking around a car a number of times in a paid parking lot is not normal. The artificial intelligence continues to classify events with great rapidity and increases its knowledge of what is normal behavior for that scene. You can also program specific things as you may wish.
This is called behavioral analytics. It means that existing surveillance cameras that have no intelligence and just record to a dvr, and have no ability to stop or prevent crimes from happening, can now be easily converted into this highly intelligent system. It is extremely powerful artificial intelligence in the hands of institutions faced with complex threats and security situations as well as ordinary trespass, theft and vandalism. It can reduce workers comp and slip & fall claims, spot fires as they start and give amazing control to anyone using the system.
Don’t rely on yesterday’s technology. This is the latest advance and it is amazing.