Using adaptive threshold to detect pedestrians crossing on a street for Advanced Driver Assistance Systems

Advanced Driver Assistance Systems (ADAS) are becoming of major relevance for driver assistance. Pedestrian Protection Systems are part of ADAS. It is well known that driver distraction on his/her driving is a major cause of traffic accidents, and giving the environment variability while driving it is a challenging area of research. This work shows that by reducing the search space to critical areas, not requiring background elimination, not ROI detection and selection, and as a result simplifying the algorithm for pedestrian detection giving a good approach. The algorithm parameterizes image resolution, thus allowing for different camera resolutions that surely will continue to improve. This work uses at its core the fact that a pedestrian has at least a shoe in contact with the pavement, together with the alarm zones to assist the driver is enough information for an ADAS to decide on actions for driver assistance. On a test set of 46 test images that were taken on a real urban environment this work has results that show an 89% correct detection on a real outdoor environment.