Artificial vision system detects pedestrians in front of cars

An artificial vision system designed to detect pedestrians in front of vehicles has been developed by researchers in Germany and Spain.

Soon to be integrated into the top of the range Mercedes vehicles, the device consists of two visible spectrum cameras and a unit that processes information supplied in real time by all image points. The newest feature of the device, according to University of Alcalá lecturer David Fernández Llorca, is the use of a dense stereo system. The term stereo refers to the use of two cameras, which are arranged 30cm apart in a structure below the rear view mirror. "The system is called dense because it collects information from all the points making up each one of the images that the cameras capture," explained Llorca. "When information is collected from just some points, the term non-dense is used." It is claimed that pedestrian recognition is improved by a factor of up to 7.5 compared with non-dense systems. Llorca says animate objects can be detected in less than 200milliseconds. In the researchers' sytem, the two cameras are connected to a processing unit that executes the artificial vision algorithm. The complex hardware is based on FPGA (field programmable gate array) technology – an electronic system with logic blocks which can be configured on-site using specialised language. Images can be seen live on a screen with 'heads up displays' or through projections on the inner side of the windscreen. According to Llorca, different response elements can also be added to warn or assist the driver. These include alarms that warn of the presence of a pedestrian, break activation systems and even devices that take control of the wheel to avoid knocking someone down. "The new system can detect pedestrians from within vehicles using visible spectrum cameras and can do so even at night," Llorca concluded. ""It is possible that we will see this pedestrian recognition system very shortly in the new Mercedes models."