摘要
Abstract
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Key words
student classroom behavior/recognition system/convolutional neural networks/video image acquisition/streaming transmission/standardized processing分类
信息技术与安全科学
