Business your connection to The Boston Globe

Surveillance cameras' latest job: interpret the threats they see

Professor Rama Chellappa and his students are working on cameras to do things like analyze suspicious movements. Professor Rama Chellappa and his students are working on cameras to do things like analyze suspicious movements. (JACQUELYN MARTIN/ASSOCIATED PRESS)

COLLEGE PARK, Md. -- The next time you walk by a shop window, glance at your reflection. How much do you swing your arms? Is the weight of your bag causing you to hunch over? Do you still have a bit of that 1970s disco strut?

Look around -- you might not be the only one watching. Never-blinking surveillance cameras, rapidly becoming a part of daily life in public and even private places, may be sizing you up, as well. And they may soon get a lot smarter.

Researchers and security companies are developing cameras that not only watch, but interpret what they see. Soon, some cameras may be able to find unattended bags at airports, guess your height, or analyze the way you walk to see if you are hiding something.

Most of the cameras used today are used to identify crooks after-the-fact. (Think grainy video on local TV news of convenience store robberies gone wrong.) But so-called intelligent video could transform cameras from passive observers to eyes with brains, able to detect suspicious behavior and potentially prevent crime.

The innovations could mean fewer people would be needed to watch what cameras record, and make it easier to install more in public places and private homes.

"Law enforcement people in this country are realizing they can use video surveillance to be in a lot of places at one time," said Roy Bordes, who runs an Orlando, Fla., security consulting company.

Some advancements have already been put to work. Baltimore, for instance, installed cameras that can play a recorded message and snap pictures of graffiti sprayers or illegal dumpers. The gaming industry uses systems that can detect facial features, Bordes said. Casinos use their vast banks of security cameras to hunt cheating gamblers who have been flagged before.

In London, one of the largest users of surveillance, cameras provided key photos of the men who bombed the underground system in July 2005 and four more who failed in a second attempt just days later.

But the cameras were only able to help with the investigation, not prevent the attacks.

Companies that make the latest cameras say the systems, if used broadly, could make video surveillance much more powerful. Cameras could monitor airports and ports, help secure homes, and watch over vast borders.

Intelligent surveillance uses computer algorithms to interpret what a camera records. The system can be programmed to look for particular things.

"If you think of the camera as your eye, we are using computer programs as your brain," said Patty Gillespie, branch chief for image processing at the Army Research Laboratory in Adelphi, Md.

At the University of Maryland, engineering professor Rama Chellappa and graduate students have worked on systems that can analyze the way someone walks to determine if he is a threat.

With two cameras and a laptop computer, Chellappa recently demonstrated how intelligent surveillance works. A student walked into the room, dropped a laptop case, then walked away. On the laptop screen, a green box popped up around him as he moved into view, then a second focused on the case when it was dropped. After a few seconds, the box around the case went red, signaling an alert.

In another video, a car pulled into a parking lot and the driver got out, a box springing up around him. It moved with the driver as he went from car to car, looking in the windows instead of heading into the building.

In both cases, the camera knew what was normal: the layout of the room, and the location of the office door and parking spots in the parking lot. Alerts were triggered when the unknown bag was added and when the driver didn't go directly into the building.

Still, industry officials say the technology needs to improve before it can be widely used. There are liability issues, such as if someone is wrongly tagged as a threat.

And the cameras only see so much. They can't see what you are wearing under your jacket -- yet.