福建电脑2025，Vol.41Issue(5)：7-12,6.DOI:10.16707/j.cnki.fjpc.2025.05.002
神经网络在校园人流量检测系统中的应用
The Application of Neural Networks in Campus Pedestrian Flow Detection Systems
摘要
Abstract
To achieve dynamic monitoring of pedestrian flow in key areas of campus buildings,this paper designs a campus pedestrian flow detection system based on C/S architecture.The system adopts a lightweight model PP-YOLO Tiny,combined with the Person Re identification in the Wild and MARS datasets,as well as the unique data features of campus scenes,to deeply fine tune and optimize the model using the crowd data collected by cameras to meet real-time monitoring needs.The experimental results show that the system still has good detection accuracy and response speed in complex scenes such as occlusion and dense crowds,and can effectively monitor changes in pedestrian flow on campus,providing support for campus safety management and resource allocation.关键词
校园人流量/动态监控/校园安全Key words
Campus Pedestrian Flow/Dynamic Monitoring/Campus Safety分类
计算机与自动化引用本文复制引用
胡振东,侯文庆,荣江..神经网络在校园人流量检测系统中的应用[J].福建电脑,2025,41(5):7-12,6.基金项目
本文得到基于多源数据融合的目标人群人像识别检索可视化关键技术研究(No.XZZK2022010)资助. （No.XZZK2022010）
