PDANet: Pyramid density-aware attention based network for accurate crowd counting

Crowd counting, i.e., estimating the number of people in crowded areas, has attracted much interest in the research community. Although many attempts have been reported, crowd counting remains an open real-world problem due to the vast density variations and severe occlusion within the interested crowd area. In this paper, we propose a novel Pyramid Density-Aware Attention based network, abbreviated as PDANet, which leverages the attention, pyramid scale feature, and two branch decoder modules for density-aware crowd counting. The PDANet utilizes these modules to extract features of different scales while focusing on the relevant information and suppressing the misleading information. We also address the variation of crowdedness levels among different images with a Density-Aware Decoder (DAD) modules. For this purpose, a classifier is constructed to evaluate the density level of the input features and then passes them to the corresponding high and low density DAD modules. Finally, we generate an overall density map by considering the summation of low and high crowdedness density maps. Meanwhile, we employ different losses aiming to achieve a precise density map for the input scene. Extensive evaluations conducted on the challenging benchmark datasets well demonstrate the superior performance of the proposed PDANet in terms of the accuracy of counting and generated density maps over the wellknown state-of-the-art approaches. (c) 2021 Published by Elsevier B.V.

Automated summary

This paper proposes a novel Pyramid Density-Aware Attention based network, PDANet, for density-aware crowd counting. By leveraging attention, pyramid scale feature, and two branch decoder modules, PDANet aims to extract features of different scales while focusing on relevant information and suppressing misleading information. It addresses the variation of crowdedness levels among different images with a Density-Aware Decoder (DAD) modules and achieves superior performance in accurate counting and generated density maps.