Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling

Greg Olmschenk, Hao Tang, Zhigang Zhu, Zhigang Zhu

2020

Abstract

Gatherings of thousands to millions of people frequently occur for an enormous variety of events, and automated counting of these high-density crowds is useful for safety, management, and measuring significance of an event. In this work, we show that the regularly accepted labeling scheme of crowd density maps for training deep neural networks is less effective than our alternative inverse k-nearest neighbor (ikNN) maps, even when used directly in existing state-of-the-art network structures. We also provide a new network architecture MUD-ikNN, which uses multi-scale drop-in replacement upsampling via transposed convolutions to take full advantage of the provided ikNN labeling. This upsampling combined with the ikNN maps further improves crowd counting accuracy. Our new network architecture performs favorably in comparison with the state-of-the-art. However, our labeling and upsampling techniques are generally applicable to existing crowd counting architectures.

Paper Citation

in Harvard Style

Olmschenk G., Tang H. and Zhu Z. (2020). Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 185-195. DOI: 10.5220/0009156201850195

in Bibtex Style

@conference{visapp20,
author={Greg Olmschenk and Hao Tang and Zhigang Zhu},
title={Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={185-195},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009156201850195},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling
SN - 978-989-758-402-2
AU - Olmschenk G.
AU - Tang H.
AU - Zhu Z.
PY - 2020
SP - 185
EP - 195
DO - 10.5220/0009156201850195
PB - SciTePress