Dataset Optimization for Real-Time Pedestrian Detection

This paper tackles data selection for training set generation in the context of nearreal-time pedestrian detection through the introduction of a training methodology: FairTrain.After highlighting the impact of poorly chosen data on detector performance, we will introduce anew data selection technique utilizing the expectation-maximization algorithm for data weighting.FairTrain also features a version of the cascade-of-rejectors enhanced with data selection principles.Experiments on the INRIA and PETS2009 datasets prove that, when ne trained, a simple HoG-based detector can perform on par with most of its near real-time competitors.