教室监控下学生异常行为检测系统

doi:10.3778/j.issn.1002-8331.2009-0486

摘要/Abstract

摘要： 针对教室监控中学生异常行为无法实时检测并反馈的现状，设计了一套基于YOLO v3算法的教室监控学生异常行为检测系统，包括摄像头硬件采集、异常行为识别和响应三个模块。其中采用基于数据标签的随机擦除预处理方法模拟图像中的目标被遮挡的情形，提高网络的泛化能力，使得网络仅通过学习局部特征即可完成目标的检测和识别；其次改进了YOLO v3算法的骨干网络Darknet，扩充浅层网络，使网络不容易忽略图片边缘或小目标物体。改进后网络的精准度、召回率以及运算速度分别提升4.2%、4.8%和8?frame/s；最后将检测功能集成于Qt编写的可视化软件，降低使用检测模型的成本，满足实时检测任务的要求，一定程度上减轻教员工作量并且提升课堂效率。

关键词: 深度学习, 异常行为, 教室监控, 随机擦除, YOLO v3算法, GIoU

Abstract: Aiming at the status quo that abnormal behaviors of students in classroom monitoring cannot be detected and feedback in real time, a classroom monitoring student abnormal behavior detection system based on YOLO v3 algorithm is designed, which includes three modules：camera hardware acquisition, abnormal behavior recognition and response. Among them, the random erasure preprocessing method based on data labels is used to simulate the situation where the target in the image is occluded, and the generalization ability of the network is improved, so that the network can complete the detection and recognition of the target only by learning local features. Secondly, it improves YOLO v3 algorithm’s backbone network, Darknet, expands the shallow network so that it is not easy for the network to ignore the edges of pictures or small target objects. The improved algorithm effectively increases the speed and accuracy of student abnormal behavior detection and reduces the missed detection rate, basically meeting the requirements of real-time detection tasks, which reduces the teachers’ workload to a certain extent and improving classroom efficiency.

Key words: deep learning, abnormal behavior, classroom monitoring, random erasers, YOLO v3 algorithm, GIoU

谭暑秋, 汤国放, 涂媛雅, 张建勋, 葛盼杰. 教室监控下学生异常行为检测系统[J]. 计算机工程与应用, 2022, 58(7): 176-184.

TAN Shuqiu, TANG Guofang, TU Yuanya, ZHANG Jianxun, GE Panjie. Classroom Monitoring Students Abnormal Behavior Detection System[J]. Computer Engineering and Applications, 2022, 58(7): 176-184.

参考文献

[1] LINDEBERG T.Scale invariant feature transform[J].Scholarpedia，2012，7（5）：10491.
[2] RUBLEE E，RABAUD V，KONOLIGE K，et al.ORB：An efficient alternative to SIFT or SURF[C]//Proceedings of 2011 International Conference on Computer Vision，2011：2564-2571.
[3] SUYKENS J A K，VANDEWALLE J.Least squares support vector machine classifiers[J].Neural Processing Letters，1999，9（3）：293-300.
[4] FREUND Y，SCHAPIRE R E.A decision-theoretic generalization of on-line learning and an application to boosting[J].Journal of Computer and System Sciences，1997，55（1）：119-139.
[5] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[6] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1440-1448.
[7] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：91-99.
[8] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：Unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[9] REDMON J，FARHADI A.YOLO9000：Better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：7263-7271.
[10] REDMON J，FARHADI A.YOLOv3：An incremental improvement[J].arXiv：1804.02767，2018.
[11] LIU W，ANGUELOV D，ERHAN D，et al.SSD：Single shot multibox detector[C]//Proceedings of European Conference on Computer Vision，2016：21-37.
[12] ZHONG Z，ZHENG L，KANG G，et al.Random erasing data augmentation[C]//Proceedings of AAAI Conference，2020：13001-13008.
[13] REZATOFIGHI H，TSOI N，GWAK J Y，et al.Generalized intersection over union：A metric and a loss for bounding box regression[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019：658-666.
[14] 杜金航，何宁.基于改进的YOLOv3道路车辆实时检测[J].计算机工程与应用，2020，56（11）：26-32.
DU J H，HE N.Real-time road vehicles detection based on improved YOLOv3[J].Computer Engineering and Applications，2020，56（11）：26-32.
[15] LI X，LI J，ZHANG X，PENG X.Detection method of robot optimal grasp posture based on deep learning[J].Chinese Journal of Scientific Instrument，2020，41（5）：108-117.
[16] 邹承明，薛榕刚.融合GIoU和Focal loss的YOLOv3目标检测算法[J].计算机工程与应用，2020，56（24）：214-222.
ZOU C M，XUE R G.Improved YOLOv3 object detection algorithm：Combining GIoU and Focal loss[J].Computer Engineering and Applications，2020，56（24）：214-222.
[17] 王兵，李文璟，唐欢.改进YOLO v3算法及其在安全帽检测中的应用[J].计算机工程与应用，2020，56（9）：33-40.
WANG B，LI W J，TANG H.Improved YOLO v3 algorithm and its application in helmet detection[J].Computer Engineering and Applications，2020，56（9）：33-40.