基于深度学习的教室照明系统研究与设计  

Research and design of classroom lighting system based on deep learning

作　　者：林小涵 侯典立[1] 赛耀樟 刘莉[1] LIN Xiaohan;HOU Dianli;SAI Yaozhang;LIU Li(School of Information and Electrical Engineering,Ludong University,Yantai 264025,China)

机构地区：[1]鲁东大学信息与电气工程学院,山东烟台264025

出　　处：《电子设计工程》2025年第1期176-180,185,共6页Electronic Design Engineering

基　　金：烟台市智慧城市创新实验室科研课题项目(SDGP370600000202302000504);山东省高等学校科技计划项目(J16LN31)。

摘　　要：针对传统传感器教室照明控制方式灵敏度差以及教室人员检测算法存在错检、漏检的问题,为了充分且合理利用教室照明设备资源,提出一种基于改进YOLOv5和区域定位的教室照明系统,该系统判定出教室人员所处的子区域,并生成照明设备的控制信息。通过在自制数据集训练、测试,并搭建LED点阵模拟教室照明,结果表明,YOLOv5的精度达到93%,召回率达到96%,可以准确实时地控制教室中的照明设备,系统具有更好的照明便捷性,更节能。Aiming at the poor sensitivity of classroom lighting control method by the traditional sensor,as well as the misdetection and omission problem of personnel detection algorithm in the classroom,in order to fully and reasonably use the classroom lighting equipment resource,a classroom lighting system based on improved YOLOv5 and regional positioning is proposed.The system judges the sub⁃region where classroom personnel are located and generates control information for lighting equipment.Through training and testing on the self⁃made data set,and the build LED dot matrix simulates the lighting equipment in the classroom.The results show that the accuracy of YOLOv5 reaches 93%and the recall rate reaches 96%.It can accurately control the lighting equipment in the classroom in real time.The system has convenience to lighting,and saves energy.

关 键 词：深度学习 YOLOv5 教室人员检测 区域定位 

分 类 号：TN02[电子电信—物理电子学]