Partially occluded pedestrian classification using part-based classifiers and Restricted Boltzmann Machine model

Abstract

One of the main challenges in pedestrian detection is occlusion. This paper presents a new method for pedestrian classification with partial occlusion handling. The proposed system involves a set of component-based classifiers trained on features derived from non-occluded dataset. The scores of all component classifiers are statistically modeled to estimate the final score of pedestrian. A generative stochastic neural network model namely Restricted Boltzmann Machine (RBM) is learned to estimate the posterior probability of pedestrian given its components scores. The training data used to train RBM model is artificially generated occluded data which simulate real occlusion conditions appeared in pedestrians. Experimental results on real-world dataset, with both partially occluded and non-occluded data shows the effectiveness of the proposed method.