Ensemble of multiple Pedestrian representations

In this paper, a new approach for pedestrian detection is presented. We design an ensemble of classifiers which employ different feature representation schemes of the pedestrian images: Laplacian EigenMaps; Gabor Filters; Invariant Local Binary Patterns. Each ensemble is obtained by varying the patterns used to train the classifiers and extracting from each image two feature vectors for each feature extraction method: one for the upper part of the image and one for the lower part of the image. A different Radial Basis Function Support Vector Machine classifier is trained using each feature vector, finally, these classifiers are combined by “Sum Rule”. Experiments are performed on a large data set consisting of 4,000 pedestrian and more than 25,000 non-pedestrian images captured in outdoor urban environments. Experimental results confirm that the different feature representations give complementary information which has been exploited by fusion rules and we have shown that our method outperforms the state-of-the-art approaches among the pedestrian detectors.