Attention Guided Region Division For Crowd Counting

Crowd counting has drawn more and more attention in computer vision. There are two mainstream approaches to deal with crowd counting tasks, regression and detection. Regression-based methods usually overestimate the count in sparse areas, while detection-based methods tend to underestimation in dense areas. In this paper, we propose a two-branch network combining regression and detection. We introduce the attention mechanism to make the network adaptively divide dense and sparse areas and employ appropriate methods on them respectively. The regression branch predicts density map in extremely dense areas. An improved detection network is applied to detect multi-scale heads in relatively sparse areas. Our method is able to obtain precise head bounding boxes in sparse areas with ensuring counting accuracy in dense areas. Experimental results show that our method achieves state-of-the-art on challenging public crowd counting datasets.