基于深度学习的教室人体行为识别模型设计
|
摘要
人体行为识别和分析是计算机视觉领域的研究热点,考虑到环境的复杂性和人体行为的多样性,行为识别在处理速度、识别准确率等方面还有很大的提升空间。近年来,深度学习技术的发展和在人工智能领域的成功应用,为人体行为识别提供了全新的解决方法。本文主要研究将深度学习中的卷积神经网络技术应用于人体行为识别,结合具体的教室应用场景,设计能够主动学习的智能化人体行为识别模型,对量化分析教室的学生的学习情况和教学情况具有重要的现实意义。
Human behavior recognition and analysis is a research hotspot in the field of computer vision. Considering the complexity of the environment and the diversity of human behavior,there is still much room to improve the processing speed and recognition accuracy of human behavior recognition. In recent years,the development of in-depth learning technology and its successful application in the field of artificial intelligence have provided a new solution for human behavior recognition. This paper mainly studies the application of convolutional neural network technology in deep learning to human behavior recognition,and combines with specific classroom application scenarios,designs an intelligent human behavior recognition model that can actively learn,which has important practical significance for quantitative analysis of classroom students' learning and teaching situation.
Human behavior recognition and analysis is a research hotspot in the field of computer vision. Considering the complexity of the environment and the diversity of human behavior,there is still much room to improve the processing speed and recognition accuracy of human behavior recognition. In recent years,the development of in-depth learning technology and its successful application in the field of artificial intelligence have provided a new solution for human behavior recognition. This paper mainly studies the application of convolutional neural network technology in deep learning to human behavior recognition,and combines with specific classroom application scenarios,designs an intelligent human behavior recognition model that can actively learn,which has important practical significance for quantitative analysis of classroom students' learning and teaching situation.
引文
[1]陆霖霖.基于改进ISA深度网络的人体行为识别研究与实现[D].成都:电子科技大学,2016.
[2] BOUZOUANE A,BOUCHARD B,GIROU XS.Action Description Logic for Smart Ho me Agent Recognition[J].Journal of the American Society of Echocardiography Official Publication of the A merican Society of Echocardiography,2005,22(11):1269-74.
[3]惠通.基于轨迹和卷积神经网络的人体行为识别方法[D].西安:西安电子科技大学,2017.
[4]余兴.基于深度学习的视频行为识别技术研究[D].成都:电子科技大学,2018.
[5]王明.基于卷积神经网络的网络入侵检测系统[D].北京:北京邮电大学,2018.
[6]孔令爽.基于深度学习和迁移学习的入侵检测研究[D].济南:山东大学,2018.
[2] BOUZOUANE A,BOUCHARD B,GIROU XS.Action Description Logic for Smart Ho me Agent Recognition[J].Journal of the American Society of Echocardiography Official Publication of the A merican Society of Echocardiography,2005,22(11):1269-74.
[3]惠通.基于轨迹和卷积神经网络的人体行为识别方法[D].西安:西安电子科技大学,2017.
[4]余兴.基于深度学习的视频行为识别技术研究[D].成都:电子科技大学,2018.
[5]王明.基于卷积神经网络的网络入侵检测系统[D].北京:北京邮电大学,2018.
[6]孔令爽.基于深度学习和迁移学习的入侵检测研究[D].济南:山东大学,2018.