Digital eye soon to help drivers avoid mishaps

WASHINGTON: With just half a second's notice, a driver can swerve to avoid a fatal accident or slam on the brakes to avoid 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 road accidents, says Shai Avidan, professor at Tel Aviv University's (TAU) faculty of engineering and an expert in image processing.

He is currently collaborating with researchers from General Motors Research Israel to keep cars on the road and people out of hospitals.

The challenge, says Avidan, is to develop a system that can recognise 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.

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 smart camera system by MobilEye, an Israeli start-up company. 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 pedestrians 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. Avidan hopes to realise 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 recognise 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.

Previously, detection systems used radar, which is expensive and not particularly sensitive to human beings, says a TAU release.

A smart camera fuelled by a powerful chip, on the other hand, could detect the activities of people and animals, and prompt the car to react accordingly, braking more or locking the doors, for example.

His research has been published in IEEE Transaction on Pattern Analysis and Machine Intelligence.