Occlusions, complex backgrounds, scale variations and non-uniform distributions present great challenges for crowd counting in practical applications. In this paper, we propose a novel method using an attention model to exploit head locations which are the most important cue for crowd counting. The attention model estimates a probability map in which high probabilities indicate locations where heads are likely to be present. The estimated probability map is used to suppress non-head regions in feature maps from several multi-scale feature extraction branches of a convolution neural network for crowd density estimation, which makes our method robust to complex backgrounds, scale variations and non-uniform distributions. In addition, we introduce a relative deviation loss to compensate a commonly used training loss, Euclidean distance, to improve the accuracy of sparse crowd density estimation. Experiments on Shanghai-Tech, UCF_CC_50 and World-Expo'10 data sets demonstrate the effectiveness of our method.
@article{arxiv.1806.10287,
title = {Attention to Head Locations for Crowd Counting},
author = {Youmei Zhang and Chunluan Zhou and Faliang Chang and Alex C. Kot},
journal= {arXiv preprint arXiv:1806.10287},
year = {2018}
}