计算机与现代化Issue(1)：7-16,10.DOI:10.3969/j.issn.1006-2475.2026.01.002
基于混合专家网络的人群定位方法
Crowd Localization Based on Mixture of Experts Network
摘要
Abstract
In recent years,stampede incidents caused by crowd gatherings have frequently occurred,leading to increased atten-tion on monitoring crowd activities in public places.As a result,crowd analysis research has gained significant social importance.The task of crowd localization,as one of the key issues in the field of crowd analysis,aims to locate the positions of individual heads within an image.However,a single crowd image often contains visual features of varying scales,such as different head sizes and varying crowd densities and so on,making it challenging for existing methods to handle these complex situations.To ad-dress the aforementioned issues,this paper leverages the strong contextual feature association capability of the Transformer to propose a novel Transformer-based crowd localization model.Additionally,a mixed expert module is introduced to assign local-ization tasks of different scales to different experts for decoupling,thereby improving the accuracy and robustness of crowd local-ization.Finally,the proposed method is compared with existing methods on three public datasets,verifying its superior perfor-mance.关键词
深度学习/人群计数/人群定位/混合专家/计算机视觉Key words
deep learning/crowd counting/crowd localization/mixture of experts/computer vision分类
信息技术与安全科学引用本文复制引用
林欣扬,陈衍琛,何仁杰,刘文犀..基于混合专家网络的人群定位方法[J].计算机与现代化,2026,(1):7-16,10.基金项目
国家自然科学基金"海峡联合基金"重点项目(U21A20471) （U21A20471）
国家自然科学基金面上项目(62072110) （62072110）
