Vehicle Pedestrian Detection Algorithm Based on AdaBoost

Pedestrian detection is a hot research topic in the fields of image processing and computer vision. It has a lot of important applications in intelligent transportation, human action analysis, robot development, video surveillance and so on. We propose a kind of feature extraction method for pedestrian detection, which is motivated by the good merits of the Local Binary Patterns (LBP). Cascade AdaBoost classifier is used to detect pedestrian. Experiment results show that the proposed pedestrian detection algorithm has a good performance.