Attention to Head Locations for Crowd Counting

Youmei Zhang, Chunluan Zhou, Faliang Chang, Alex C. Kot, Wei Zhang

Abstract: 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 convolutional neural network for crowd density estimation, which makes our method robust to complex backgrounds, scale variations and non-uniform distributions. Experiments on ShanghaiTech dataset demonstrate the effectiveness of our method.