@article{ref1,
title="Towards reaching human performance in pedestrian detection",
journal="IEEE transactions on pattern analysis and machine intelligence",
year="2018",
author="Zhang, Shanshan and Benenson, Rodrigo and Omran, Mohamed and Hosang, Jan and Schiele, Bernt",
volume="40",
number="4",
pages="973-986",
abstract="Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods and the &quot;perfect single frame detector&quot;. We enable our analysis by creating a human baseline for pedestrian detection (over the Caltech pedestrian dataset). After manually clustering the frequent errors of a top detector, we characterise both localisation and backgroundversus- foreground errors. To address localisation errors we study the impact of training annotation noise on the detector performance, and show that we can improve results even with a small portion of sanitised training data. To address background/foreground discrimination, we study convnets for pedestrian detection, and discuss which factors affect their performance. Other than our in-depth analysis, we report top performance on the Caltech pedestrian dataset, and provide a new sanitised set of training and test annotations.<p /> <p>Language: en</p>",
language="en",
issn="0162-8828",
doi="10.1109/TPAMI.2017.2700460",
url="http://dx.doi.org/10.1109/TPAMI.2017.2700460"
}