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

TL;DR

This paper introduces inverse k-nearest neighbor maps and a multiscale upsampling network architecture to improve the accuracy of dense crowd counting with deep neural networks, outperforming existing methods.

Contribution

The authors propose a novel inverse k-nearest neighbor labeling scheme and a multiscale upsampling architecture, enhancing crowd counting performance over traditional density map approaches.

Findings

Inverse k-NN maps outperform traditional density maps.

The MUD-i$k$NN architecture achieves superior accuracy.

Labeling and upsampling techniques are broadly applicable.

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 (i$k$NN) maps, even when used directly in existing state-of-the-art network structures. We also provide a new network architecture MUD-i$k$NN, which uses multi-scale upsampling via transposed convolutions to take full advantage of the provided i$k$NN labeling. This upsampling combined with the i$k$NN 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.