首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221016--1)

基于神经网络的学生行为检测算法研究

Algorithm for Student Behavior Detection Based on Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

关于行为检测的算法有很多,但针对教室场景下的学生行为检测算法却略显缺乏。为了使学生行为检测算法具有较好的准确率和实时性,在MTCNN的基础上改进了网络结构,并提出了一种新的激活函数和损失函数以检测学生图像和关键点。同时,提出了通过图像分类网络和关键点分类网络对学生行为进行联合分类的策略。实验结果表明,所提出的改进措施均有效提升了学生行为检测的准确率,最终模型的检测准确率为78.6%。在嵌入式开发板Jetson TX2上,所提算法的实时检测准确率和速度优于YOLOv3和SSD等算法。

Abstract

There are many algorithms for behavior detection in different datasets, but there is a little lack of algorithms for student behavior detection in classroom. In order to achieve better accuracy and real-time of student behavior detection, this paper improves the network structure based on MTCNN, and proposes a new activation function and a loss function to detect student images and landmark localization. Meanwhile, this paper proposes the strategy of joint classification of student behaviors through the image classification network and the landmark localization classification network. The experimental results show that the proposed improvement actions effectively improve the accuracy of student behavior detection and the final detection accuracy of the model is 78.6%. On the embedded development board of Jetson TX2, the proposed algorithm has the real-time detection accuracy and speed superior to those of the other algorithms such as YOLOv3 and SSD.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP57.221016

所属栏目:图像处理

基金项目:广州市科技计划;

收稿日期:2020-03-19

修改稿日期:2020-04-20

网络出版日期:2020-11-01

作者单位    点击查看

苏寒松:天津大学电气自动化与信息工程学院, 天津 300072
刘腾腾:天津大学电气自动化与信息工程学院, 天津 300072
刘高华:天津大学电气自动化与信息工程学院, 天津 300072
田曦初:天津大学电气自动化与信息工程学院, 天津 300072

联系人作者:刘高华(suppig@126.com)

备注:广州市科技计划;

【1】Simonyan K. -11-12)[2019-12-21] . https:∥arxiv. 2014, org/abs/1406: 2199.

【2】Ng JoeY H, Hausknecht M, Vijayanarasimhan S, et al. Beyond short snippets: deep networks for video classification . [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 2015, 4694-4702.

【3】Hochreiter S, Schmidhuber J. Long short-term memory [J]. Neural Computation. 1997, 9(8): 1735-1780.

【4】Wang L M, Xiong Y J, Wang Z, et al. Temporal segment networks: towards good practices for deep action recognition [M]. ∥ Leibe B, Matas J, Sebe N, et al. Computer Vision—— ECCV 2016. Lecture Notes in Computer Science. Cham: Springer. 2016, 9912: 20-36.

【5】Tran D, Bourdev L, Fergus R, et al. Learning spatiotemporal features with 3D convolutional networks [J]. 2015 IEEE International Conference on Computer Vision (ICCV). 2015, 4489-4497.

【6】Zhou P P, Ding Q H, Luo H B, et al. Anomaly detection and location in crowded surveillance videos [J]. Acta Optica Sinica. 2018, 38(8): 0815007.
周培培, 丁庆海, 罗海波, 等. 视频监控中的人群异常行为检测与定位 [J]. 光学学报. 2018, 38(8): 0815007.

【7】Hu T, Zhu X, Guo W, et al. Human action recognition based on scene semantics [J]. Multimedia Tools and Applications. 2019, 78(20): 28515-28536.

【8】Hu L Q, Cai Z Q, Xing L N, et al. Human action recognition via learning joint points information toward big AI system [J]. Journal of Visual Communication and Image Representation. 2019, 102688.Hu L Q, Cai Z Q, Xing L N, et al. Human action recognition via learning joint points information toward big AI system [J]. Journal of Visual Communication and Image Representation. 2019, 102688.

【9】Zhang K P, Zhang Z P, Li Z F, et al. Joint face detection and alignment using multitask cascaded convolutional networks [J]. IEEE Signal Processing Letters. 2016, 23(10): 1499-1503.

【10】Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision . [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30,2016, Las Vegas, NV, USA. New York: IEEE. 2016, 2818-2826.

【11】Ramachandran P, Zoph B. -10-16)[2019-12-21] . https:∥arxiv.org/abs/1710.05941v1. 2017.

【12】Howard A, Sandler M, Chen B, et al. Searching for MobileNetV3 . [C]∥2019 IEEE/CVF International Conference on Computer Vision (ICCV), October 27-November 2, 2019, Seoul, Korea (South). New York: IEEE. 2019, 1314-1324.

【13】Glorot X, Bordes A. -01-17)[2019-12-21] . https:∥wenku.baidu.com/view/7822feb5770bf78a65295450.html. 2010.

【14】Liu W, Anguelov D, Erhan D, et al. SSD: single shot MultiBox detector [M]. ∥ Leibe B, Matas J, Sebe N, et al. Computer Vision—— ECCV 2016. Lecture Notes in Computer Science. Cham: Springer. 2016, 9905: 21-37.

【15】Redmon J. -04-08)[2019-12-21] . https:∥arxiv. 2018, org/abs/1804: 02767.

【16】Sandler M, Howard A, Zhu M L, et al. MobileNetV2: inverted residuals and linear bottlenecks . [C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 2018, 4510-4520.

【17】Chen L L, Zhang Z D, Peng L. Real-time detection based on improved single shot MultiBox detector [J]. Laser & Optoelectronics Progress. 2019, 56(1): 011002.
陈立里, 张正道, 彭力. 基于改进SSD的实时检测方法 [J]. 激光与光电子学进展. 2019, 56(1): 011002.

【18】Cui H, Dahnoun N. Real-time stereo vision implementation on Nvidia Jetson TX2 . [C]∥2019 8th Mediterranean Conference on Embedded Computing (MECO), June 10-14, 2019, Budva, Montenegro. New York: IEEE. 2019, 1-5.

【19】Jose E. M G, Haridas M T P, et al. Face recognition based surveillance system using FaceNet and MTCNN on jetson TX2 . [C]∥2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), March 15-16 , 2019, Coimbatore, India. New York: IEEE. 2019, 608-613.

【20】Giubilato R, Chiodini S, Pertile M, et al. An evaluation of ROS-compatible stereo visual SLAM methods on a nVidia Jetson TX2 [J]. Measurement. 2019, 140: 161-170.

【21】Wang Z W, Han J, Sun X B, et al. Method for orientation determination of transmission line tower based on visual navigation [J]. Laser & Optoelectronics Progress. 2019, 56(8): 081006.
王祖武, 韩军, 孙晓斌, 等. 基于视觉导航的输电线杆塔方位确定方法 [J]. 激光与光电子学进展. 2019, 56(8): 081006.

【22】He K, Zhang X, Ren S, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification . [C]∥ 2015 IEEE International Conference on Computer Vision, December 7-13 , 2015, Santiago, Chile. New York: IEEE. 2015, 15802053.

引用该论文

Su Hansong,Liu Tengteng,Liu Gaohua,Tian Xichu. Algorithm for Student Behavior Detection Based on Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221016

苏寒松,刘腾腾,刘高华,田曦初. 基于神经网络的学生行为检测算法研究[J]. 激光与光电子学进展, 2020, 57(22): 221016

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF