Multi Stereo-based Pedestrian Detection by means of Daylight and Far Infrared Cameras

This article presents a tetra-vision (4 cameras) system for the detection of pedestrians by means of the simultaneous use of two far infrared and visible cameras stereo pairs. The main idea is to exploit the advantages of both far infrared and visible cameras to develop a system that combines the advantages of using far infrared or daylight technologies. Different approaches are used to process the two stereo flows in an independent fashion to produce a list of areas of attention that potentially contain pedestrians. Then, four different following approaches are used to refine and filter this list and to validate the presence of a pedestrian. Preliminary results show that the combined use of two vision systems as well as the use of different and independent validation steps enable the system to effectively detect pedestrians in different conditions of illumination and background.