Orientation filter enhanced pedestrian detection

Abstract

Presented is a novel method that can detect pedestrians in images based on the combination of AdaBoost learning with a local histogram's features. Instead of using the raw image for further processing, introduced is a layer enhanced by orientation filters which are superimposed to the original image. Experimental results obtained using the INRIA dataset show the superior performance of the presented method and thus demonstrate its robustness with the novel enhanced layer embedded pedestrian detector.