Two-stage part-based pedestrian detection

Abstract

This paper introduces a part-based two-stage pedestrian detector. The system finds pedestrian candidates with an AdaBoost cascade on Haar-like features. It then verifies each candidate using a part-based HOG-SVM doing first a regression and then a classification based on the estimated function output from the regression. It uses the Histogram of Oriented Gradients (HOG) computed on both the full, upper and lower body of the candidates, and uses these in the final verification. The system has been trained and tested on the INRIA dataset and performs better than similar previous work, which uses full-body verification.