Crowd counting based on attention-guided multi-scale fusion networks

In this paper, we propose an attention-guided multi-scale fusion network (named as AMS-Net) for crowd counting in dense scenarios. The overall model is mainly comprised by the density and the attention networks. The density network is able to provide a coarse prediction of the crowd distribution (density map), while the attention network helps to distinguish crowded regions from backgrounds. The output of the attention network serves as a mask of the coarse density map. The number of persons in the scene is finally estimated by applying integration on the refined density map. In order to deal with persons of varied resolutions, we introduce a multi-scale fusion strategy which is built upon dilated convolution. Experiments are carried out on the standard benchmark datasets, covering varied over-crowded scenarios. Experimental results demonstrate the effectiveness of the proposed approach. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

This paper presents an attention-guided multi-scale fusion network (AMS-Net) for crowd counting in dense scenarios, comprising density and attention networks. The proposed approach effectively handles persons of varied resolutions through a multi-scale fusion strategy built upon dilated convolution, as demonstrated by experimental results on standard benchmark datasets.