An Empirical Evaluation of Cross-scene Crowd Counting Performance

Rita Delussu, Lorenzo Putzu, Giorgio Fumera

2020

Abstract

Crowd counting and density estimation are useful but also challenging tasks in many video surveillance systems, especially in cross-scene settings with dense crowds, if the target scene significantly differs from the ones used for training. This also holds for methods based on Convolutional Neural Networks (CNNs) which have recently boosted the performance of crowd counting systems, but nevertheless require massive amounts of annotated and representative training data. As a consequence, when training data is scarce or not representative of deployment scenarios, also CNNs may suffer from over-fitting to a different extent, and may hardly generalise to images coming from different scenes. In this work, we focus on real-world, challenging application scenarios when no annotated crowd images from a given target scene are available, and evaluate the cross-scene effectiveness of several regression-based state-of-the-art crowd counting methods, including CNN-based ones, through extensive cross-data set experiments. Our results show that some of the existing CNN-based approaches are capable of generalising to target scenes which differ from the ones used for training in the background or lighting conditions, whereas their effectiveness considerably degrades under different perspective and scale.

Paper Citation

in Harvard Style

Delussu R., Putzu L. and Fumera G. (2020). An Empirical Evaluation of Cross-scene Crowd Counting Performance. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 373-380. DOI: 10.5220/0008983003730380

in Bibtex Style

@conference{visapp20,
author={Rita Delussu and Lorenzo Putzu and Giorgio Fumera},
title={An Empirical Evaluation of Cross-scene Crowd Counting Performance},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={373-380},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008983003730380},
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 4: VISAPP
TI - An Empirical Evaluation of Cross-scene Crowd Counting Performance
SN - 978-989-758-402-2
AU - Delussu R.
AU - Putzu L.
AU - Fumera G.
PY - 2020
SP - 373
EP - 380
DO - 10.5220/0008983003730380
PB - SciTePress