Cars could soon be better at warning drivers of upcoming pedestrians at night thanks to a new infra-red detection technology.
Spanish researchers have developed a system that analyses images from two thermal cameras to alert the driver of pedestrians in the path of the car or, in the case of self-driving vehicles, work out when to automatically come to a stop.
‘With the model being used in our research, pedestrians up to 40 meters away can be detected, although this distance could be extended if we substitute the lens with one that has greater focus range,’ said researcher Daniel Olmeda, from the Intelligent Systems Laboratory (LSI) at Charles III University of Madrid (UC3M).
The aim is to provide more information to the driver than they would be able to see with their own eyes using a process of pattern recognition.
‘In this situation, the sensitive cameras in the visible spectrum, which are already incorporated into some vehicles, can only be utilized in regions illuminated by the car’s headlights. But our system does not require any type of external lighting,’ said Olmeda.
‘The algorithm developed detects pedestrian presence according to certain silhouette features, because we have confirmed that the contour of objects in infrared images have congruent phase features that do not vary with temperature and contrasting.’
The researchers used a non-refrigerated microbolometer as the infrared sensor, which provided sufficient results at a lower price than other refrigerated sensors. They claim this type of device could be easily installed in a commercial vehicle as some cars already carry visible-light cameras.
‘Generalized implementation of this type of sensors is viable and its mass production would lower production costs,’ said Olmeda.
The researchers now want to study the best way to present the driver with the alert information without creating a dangerous distraction. ‘We are working to join external perceptions with internal ones so that the system knows if the driver has not seen something, and we only warn him about this obstacle,’ said LSI coordinator Prof Arturo de la Escalera.
The systems has been installed on the university’s test-bed car, the IVVI 2.0, which also incorporates other artificial vision systems that allow it detect other vehicles and highway lines, read traffic signals, alert the driver with a sound if he starts to fall asleep, and warn of any driving danger.
A paper on the research has been published in the journal Integrated Computer-Aided Engineering.