Posterior probability based Multi-Classifier fusion in pedestrian detection

Abstract

This paper presents a novel method for pedestrian detection at measurement level. At feature extraction stage, we use Histogram of Oriented Gradient to describe the feature of pedestrian and non-pedestrian. To decrease the time cost, we reduce the dimension by using PCA. The base classifiers used in posterior probability based multi-classifier fusion are posterior probability based SVM, Naıve Bayesian and Minimum Distance Classifier, respectively. To estimate the accuracy of fusion result, stratified cross-validation is used. Experimental results on pedestrian databases prove the efficiency of this work.