A classroom concentration model based on computer vision

With the development of computer vision technology, automatic classroom behavior analysis has attracted more and more attention and the estimation of students' head pose is the most essential one of them. This paper proposed a classroom concentration model based on the head pose and position information collected by convolution neural networks. On the self-built dataset, the accuracy of the head pose classification model is 94.6%. In the real scene test, the results of our method are consistent with the manual analysis of the corresponding teaching videos. It means that the method can efficiently reflect real students' concentration situation during class and help teachers and experts carry out teaching analysis and rethink.

[1]  Lianwen Jin,et al.  Detecting Heads using Feature Refine Net and Cascaded Multi-scale Architecture , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[2]  Yang Liu,et al.  A People Counting Method Based on Universities' Surveillance Videos and Its Application on Classroom Query , 2014, CCBR.

[3]  Ned A. Flanders,et al.  Analyzing Teaching Behavior , 1970 .

[4]  Ruan Zongcai.  Head Behavior Recognition Based on Analysis of Trajectory , 2012 .

[5]  Luca Benini,et al.  Brain-Inspired Classroom Occupancy Monitoring on a Low-Power Mobile Platform , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[6]  Ruimin Shen,et al.  Hand-Raising Gesture Detection in Real Classroom , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[7]  Xiaochun Cao,et al.  Deep People Counting in Extremely Dense Crowds , 2015, ACM Multimedia.

[8]  Wei Liu,et al.  Behavior detection and analysis for learning process in classroom environment , 2017, 2017 IEEE Frontiers in Education Conference (FIE).

[9]  Sang-Hyun Bae,et al.  Detection of Face Direction by Using Inter-Frame Difference , 2016 .

[10]  Kristy Elizabeth Boyer,et al.  Automatically Recognizing Facial Expression: Predicting Engagement and Frustration , 2013, EDM.

[11]  Xiaogang Wang,et al.  Cross-scene crowd counting via deep convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Hou Ligang,et al.  The design of intelligent crowd attention detection system based on face detection technology , 2017, 2017 13th IEEE International Conference on Electronic Measurement & Instruments (ICEMI).

[13]  James M. Rehg,et al.  Fine-Grained Head Pose Estimation Without Keypoints , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[14]  Noel E. O'Connor,et al.  ResnetCrowd: A residual deep learning architecture for crowd counting, violent behaviour detection and crowd density level classification , 2017, 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[15]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.