Pedestrian Detection via Mixture of CNN Experts and Thresholded Aggregated Channel Features

In this paper, we propose a two stage pedestrian detector. The first stage involves a cascade of Aggregated Channel Features (ACF) to extract potential pedestrian windows from an image. We further introduce a thresholding technique on the ACF confidence scores that segregates candidate windows lying at the extremes of the ACF score distribution. The windows with ACF scores in between the upper and lower bounds are passed on to a Mixture of Expert (MoE) CNNs for more refined classification in the second stage. Results show that the designed detector yields better than state-of-the-art performance on the INRIA benchmark dataset and yields a miss rate of 10.35% at FPPI=10^-1.