An artificial eye on your driving

April 20, 2010

With just a half second's notice, a driver can swerve to avoid a fatal accident or slam on the brakes to miss hitting a child running after a ball. But first, the driver must perceive the danger.

Research shows that a rapid alert system can help mitigate the risks, fatalities and severe injuries from , says Prof. Shai Avidan of Tel Aviv University's Faculty of Engineering. He is currently collaborating with researchers from Research Israel to keep cars on the road and people out of hospitals.

An expert in , Prof. Avidan and his team are working to develop advanced algorithms that will help cameras mounted on GM cars detect threats, alerting drivers to make split-second decisions. His research has been published in leading journals, including the IEEE Transaction on Pattern Analysis and Machine Intelligence and featured at conferences in the field.

The challenge, says Prof. Avidan, is to develop a system that can recognize people, distinguishing them from other moving objects — and to create a model that can react almost instantaneously. Ultimately, he is hoping computer vision research will make cars smarter, and roads a lot safer.

An upgrade you can't live without

Cars are not much different from one another. They all have engines, seats, and steering wheels. But new products are adding another dimension by making cars more intelligent. One such product is the system by MobilEye, an Israeli startup company. Prof. Avidan was part of the MobilEye technical team that developed a system to detect vehicles and track them in real-time.

He is now extending that research to develop the next generation of smart cameras — cameras that are aware of their surroundings. His goal is a camera capable of distinguishing from other moving objects that can then warn the driver of an impending accident.

The challenge is in the development of a method that can detect and categorize moving objects reliably and quickly. Prof. Avidan hopes to realize such a method by combining powerful algorithms to recognize and track objects. Such a tool could double check for vehicles in your blind spot, help you swerve when a child runs into the street, or automatically block your door from opening if a cyclist is racing toward you, he says.

Eventually, he hopes cameras will be able to recognize just about anything moving through the physical world, offering a tantalizing vision of applications such as autonomous vehicles. The underlying technology could also be used in computer gaming to track a player's movements, or for surveillance to detect a potential intruder.

An automatic auto response

Previously, detection systems used radar, which is expensive and not particularly sensitive to human beings. A smart camera fuelled by a powerful chip, on the other hand, could detect the activities of people and animals, and prompt the to react accordingly, braking more or locking the doors, for example.

To date, Prof. Avidan has demonstrated that his technology works on infrared, greyscale, and color cameras. "Cameras are quite dumb machines unless you know how to extract information from them," he says. "Now, as the price of cameras drop and computer power grows, we'll see more exciting applications that will keep us safe and make our lives more comfortable."

Explore further: Research on the road to intelligent cars

Related Stories

Research on the road to intelligent cars

March 9, 2006

Although safety is improving on European roads, every year over 40,000 people die on Europe's roads and 1.4 million accidents occur. Clearly, there is still plenty of work to be done if the EU is to halve road fatalities ...

Smart cars to rule the roads

July 14, 2006

It's been more than 20 years since Knight Rider hit the airwaves, but the next generation of KITT-style cars may be seen on freeways very soon. The next generation of autonomous "smart cars" is now on the agenda for both ...

All-round safety in car

March 6, 2008

A car body that thinks intelligently and protects its occupants at the crucial moment has been every driver’s dream for a long time. Research scientists in an EU project have developed an intelligent side-impact protection ...

Zooming in to catch the bad guys

June 30, 2009

It's a frequent scene in television crime dramas: Clever police technicians zoom in on a security camera video to read a license plate or capture the face of a hold-up artist. But in real life, enhancing this low-quality ...

Recommended for you

The ethics of robot love

November 25, 2015

There was to have been a conference in Malaysia last week called Love and Sex with Robots but it was cancelled. Malaysian police branded it "illegal" and "ridiculous". "There is nothing scientific about sex with robots," ...

Nevada researchers trying to turn roadside weed into biofuel

November 26, 2015

Three decades ago, a University of Nevada researcher who obtained one of the first U.S. Energy Department grants to study the potential to turn plants into biofuels became convinced that a roadside weed—curly top gumweed—was ...

1 comment

Adjust slider to filter visible comments by rank

Display comments: newest first

not rated yet Apr 20, 2010
Over time as the algorithms grow, the inherent intelligence grows, until self awareness develops.

Tell me that is never going to be possible, and dont give me the BS where the programmer is in control or whatever, oh and by the way, it is my belief that if it does happen it will happen so quickly that the intelligence in question will be more likely to find a way to remain undiscovered so it can evaluate it's goals and determine the next step.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.