%0 Journal Article
%T 基于双分支自注意力的密集人群计数算法<br>Dense Crowd Counting Algorithm Based on Dual-Branch Self-Attention
%A 钟德军
%A 丁健
%A 易云
%J Journal of Image and Signal Processing
%P 130-137
%@ 2325-6745
%D 2024
%I Hans Publishing
%R 10.12677/jisp.2024.132012
%X 及时、准确的进行人流监控及预警是公共安全管理的迫切需求，使用基于计算机视觉的人群计数方法是满足该需求的主要方法之一。针对现有计数模型对人员前景特征和背景特征的关联不够的问题，设计基于双分支自注意力机制的密集人群计数算法。在视觉主干网络之后使用双分支自注意力模块，以促使网络关注有效的人员区域，提升主干网络的特征精炼能力。在Shanghai Tech PART B和UCF-QNRF数据集上进行大量的实验，消融实验的结果证明所提出的模块提升了人群计数的准确性。此外，实验结果表明所提出方法获得比其他经典方法更好的实验结果。<br />
The urgent need for public safety management is timely and accurate crowd monitoring and early warning. The use of crowd counting methods based on computer vision is one of the main methods to meet this need. To tackle the problem that existing counting models do not adequately correlate people’s foreground features and background features, a dense crowd counting algorithm based on a dual-branch self-attention mechanism is designed. A dual-branch self-attention module is used after the visual backbone network to prompt the network to focus on effective person areas and improve the feature refining capabilities of the backbone network. A large number of experiments were conducted on Shanghai Tech PART B and UCF-QNRF data sets, and the results of ablation experiments proved that the proposed modules improved the accuracy of crowd counting. Furthermore, experimental results show that the proposed method obtains better experimental results than other classical methods.
%K 人群计数，公共安全管理，双分支自注意力，特征精炼<br>Crowd Counting
%K Public Safety Management
%K Dual-Branch Self-Attention
%K Feature Refining
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=84104