New night vision system reduces car accidents

September 27, 2007

About 42% of fatal car accidents happen at night, according to the European Commission for the Automobile Industry. This figure is extremely worrying bearing in mind that there is about 60% less traffic during at night time. This is largely due to the reduced visual acuity and field of vision at night as a consequence of the illumination from the headlights -- these factors are currently being studied by a group of researchers from the Department of Computer Architecture and Technology at the University of Granada.

This group created an electronic system that significantly improves driving ability at night by using information extracted automatically from night visors. Researchers are working within a European project called DRIVSCO, whose participants include researchers from different countries who work on real-time vision and its application to the car industry. The study conducted at UGR developed a microchip which, when installed in a car, makes it easier to extract the information from cameras to elements involved in driving (bends, pedestrians, cars, etc.) which may be present on the road. In other words, this system will inform drivers by means of visual, acoustic or other signs about the obstacles appearing in their way, making intelligent cars even more sophisticated than is currently the case.

Improving visibility

The researcher who carried out this study is Eduardo Ros Vidal, who explained that the aim of this chip is to support the illumination of the car, which is insufficient for ideal vision. "Dipped headlights only illuminate about 56 meters when the breaking distance at 100 km/h is about 80 meters," says Professor Ros Vidal. The system created by his group uses two infrared cameras placed on the car which record the scene even further than the illumination of conventional headlights. Therefore, the chip extracts information about factors such as movement or depth in real time to improve the detection of specific elements and situations of interest.

Current artificial vision systems use this basic information to detect objects, pedestrians, bends etc. For instance, the system generates information about the depth of the scene in real time codifying the distance of every object -- warm colours for close objects (reddish and more dangerous) and cold colours for distant objects (bluish and safer). The system also processes real-time movements, indicating the direction in which the object moves in the scene and how everything changes due to the movement of the car.

Other participants in DRIVSCO include the University of Münster (Germany), which is currently studying where drivers look when driving by using eye-tracking systems. This project is the continuation of ECOVISION, which also focused on the development of Advanced Driving Assistant Systems (ADAS), which are currently applied to high range cars and which will undoubtedly be improved thanks to the progress of DRIVSCO.
-end-


University of Granada

Related Driving Articles from Brightsurf:

Driving behavior less 'robotic' thanks to new Delft model
Researchers from TU Delft have now developed a new model that describes driving behaviour on the basis of one underlying 'human' principle: managing the risk below a threshold level.

Warming temperatures are driving arctic greening
As Arctic summers warm, Earth's northern landscapes are changing. Using satellite images to track global tundra ecosystems over decades, a new study found the region has become greener, as warmer air and soil temperatures lead to increased plant growth.

Software of autonomous driving systems
Researchers at TU Graz and AVL focus on software systems of autonomous driving systems.

Driving immunometabolism to control lung infection
When drugs to kill microbes are ineffective, host-directed therapy uses the body's own immune system to deal with the infection.

Representation of driving behavior as a statistical model
A joint research team from Toyohashi University of Technology has established a method to represent driving behaviors and their changes that differ among drivers in a single statistical model, taking into account the effect of various external factors such as road structure.

Improving the vision of self-driving vehicles
There may be a better way for autonomous vehicles to learn how to drive themselves: by watching humans.

Impaired driving -- even once the high wears off
McLean researchers have discovered that recreational marijuana use affects driving ability even when users are not intoxicated.

Self-driving microrobots
Most synthetic materials, including those in battery electrodes, polymer membranes, and catalysts, degrade over time because they don't have internal repair mechanisms.

AI to determine when to intervene with your driving
Can your AI agent judge when to talk to you while you are driving?

Cooperating may result in better self-driving experience
To better understand and predict the outcomes of the steering wheel control dilemma, contrary to many previous studies, in a paper published in IEEE/CAA Journal of Automatica Sinica, Dr.

Read More: Driving News and Driving Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.