期刊论文

Liu, Tingting

英文

Infrared Physics & Technology

1350-4495

2020

111

103464

10.1016/j.infrared.2020.103464

To demonstrate the performance of proposed model, 100 short infrared videos are selected as the dataset in this paper. The IR videos come from the two sources, namely, downloading from the internet and capturing by ourselves. In the videos, the teachers stand in front of the electronic display and teach the new courses in the classroom. With the permission of the students, teachers, and schools, our research group capture the infrared videos during the past three semesters. The key frames are

本校为第一且通讯机构

Infrared hand gesture images can capture the human accurate gesture information in the weak illumination environment. In this article, we propose a novel hand gesture recognition model with convolutional neural networks for the human behavior analysis in “double teachers” classroom instruction and learning scenario. The recognized instructors’ hand gestures can be utilized to analyze teachers’ non-verbal behaviors which attract learners’ attention as well as enhance their learning outcomes. To extract the features of the infrared hand gest...