基于卷积神经网络的教室灯光识别算法研究  

Research on recognition algorithm of classroom light based on CNN

作　　者：徐微[1] 李彤 李守智[2] XU Wei;LI Tong;LI Shouzhi(Xi’an Jiaotong University City College,Xi’an 710018,China;School of Electrical Engineering,Xi’an University of Technology,Xi’an 710048,China)

机构地区：[1]西安交通大学城市学院,陕西西安710018 [2]西安理工大学电气工程学院,陕西西安710048

出　　处：《电子设计工程》2022年第17期28-31,36,共5页Electronic Design Engineering

基　　金：陕西省教育科学“十三五”规划2020年度课题(SGH20Y137)。

摘　　要：针对高校照明灯数量多、人工管理繁琐、电能浪费等问题,设计了一套高校照明灯自动识别系统。利用教室和图书馆监控截图,采用BP神经网络和卷积神经网络算法分别对照明灯使用情况进行识别。实验结果表明,卷积神经网络算法相对BP神经网络算法有较高的识别率,其识别准确率高达96.5%,能有效地进行照明灯识别。Aiming at the problems of the large number of university lighting,the tedious manual management and the waste of electric energy,an automatic identification system of university lighting is designed.Using the classroom and library monitoring screenshots,BP neural network and convolution neural network algorithm were used to identify the use of lights. The experimental results show that the convolution neural network algorithm has a higher recognition rate than the BP neural network algorithm,and its recognition accuracy is as high as 96.5%,which can effectively identify the lighting lamp.

关 键 词：图像识别 PYTHON BP神经网络 卷积神经网络 

分 类 号：TN391.41[电子电信—物理电子学]