BNU-LCSAD: A video database for classroom student action recognition

摘要

With the development and application of digital cameras, especially in education, a great number of digital videorecordings are produced in classrooms. Taking Beijing Normal University as an example, 3.4 TB of videos are recordedevery day in more than 200 classrooms. Such huge data is beneficial for us, computer vision researchers, toautomatically recognize students' classroom actions and even evaluate the quality of classroom teaching. To focus actionrecognition on students, we propose Beijing Normal University Large-scale Classroom Student Action Database version1.0(BNU-LCSAD) which is the first large-scale classroom student action database for student action recognition andconsists of 10 classroom student action classes from digital camera recordings at BNU. We introduce the construct andlabel Processing of this database in detail. In Addition , we provide baseline of student action recognition results basedour new database using C3D network.