基于卷积神经网络的学生课堂行为识别系统设计  

Design of student classroom behavior recognition system based on convolutional neural network

作　　者：刘琳 LIU Lin(Qinghai Normal University,Xining 810000,China;Qinghai Vocational College of Police Officers,Xining 810000,China)

机构地区：[1]青海师范大学,青海西宁810000 [2]青海警官职业学院,青海西宁810000

出　　处：《现代电子技术》2024年第6期142-146,共5页Modern Electronics Technique

摘　　要：精准的学生课堂行为识别结果有助于提升课堂教学效果,为此,设计一种基于卷积神经网络的学生课堂行为识别系统。系统的图像采集模块利用SZ-4K512M型摄像机,采集学生课堂行为的视频图像,并通过流式传输技术将标记后的采集图像传输至图像预处理模块;图像预处理模块对图像进行清洗和标准化处理后,传送至行为识别模块。行为识别模块通过卷积层、池化层和全连接层构建卷积神经网络,以已标记的学生课堂行为图像作为基础训练网络,利用完成训练的卷积神经网络识别学生课堂行为。实验结果表明,所设计系统可以精准识别学生玩手机、睡觉、举手等不同课堂行为,识别精度高于97%,说明该系统可以更好地掌握学生的心理活动变化。Accurate student classroom behavior recognition results can help improve classroom teaching effectiveness.Therefore,a student classroom behavior recognition system based on convolutional neural networks is designed.In the image acquisition module of the system,an SZ-4K512M camera is used to capture video images of students′ classroom behavior,and transmit the labeled collected images to the image preprocessing module by means of the streaming transmission technology.The image preprocessing module can clean and standardize the image and transmit it to the behavior recognition module.The behavior recognition module can construct a convolutional neural network by means of the convolutional layers,pooling layers,and fully connected layers.The network is trained based on labeled student classroom behavior images,and the trained convolutional neural network is used to recognize student classroom behavior.The experimental results show that the designed system can accurately recognize different classroom behaviors such as students playing with their phones,sleeping,and raising their hands,with a recognition accuracy of over 97%,indicating that this system can better grasp the changes in students′psychological activities.

关 键 词：学生课堂行为 识别系统 卷积神经网络 视频图像采集 流式传输 标准化处理 

分 类 号：TN711-34[电子电信—电路与系统] TP391.41[自动化与计算机技术—计算机应用技术]