基于边缘计算的智能监考系统

doi:10.3969/j.issn.1006-2475.2025.12.004

计算机与现代化 ›› 2025, Vol. 0 ›› Issue (12): 26-31.doi: 10.3969/j.issn.1006-2475.2025.12.004

基于边缘计算的智能监考系统

(1.新疆师范大学计算机科学技术学院，新疆乌鲁木齐 830054; 2.铜陵学院数学与计算机学院,安徽铜陵 244061;
3.中国科学院新疆理化技术研究所,新疆乌鲁木齐 830011)

出版日期:2025-12-18 发布日期:2025-12-18
作者简介: 作者简介：李京阳(1997—),男,吉林公主岭人,硕士研究生,研究方向:计算机视觉,边缘计算,E-mail: 845134358@qq.com; 通信作者:薛化建(1978—),男,河南孟州人,教授级高级工程师,博士,研究方向:边缘计算,自然语言处理,E-mail: xuehj@tlu.edu.cn; 杨勇(1978—),男,陕西汉中人,教授,博士,研究方向:自然语言处理,智慧教育; 任鸽(1986—),女,河南兰考人,副教授,硕士,研究方向:自然语言处理,数据挖掘。
基金资助:
基金项目：新疆维吾尔自治区重点研发专项(2020B02018-2); 铜陵学院校级教学研究项目(2023xj022)

Intelligent Proctoring System Based on Edge Computing

(1. College of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China;
2. College of Mathematics and Computer Science, Tongling University, Tongling 244061, China;
3. Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, Urumqi 830011, China)

Online:2025-12-18 Published:2025-12-18

摘要/Abstract

摘要：
摘要：针对远程网络考试中缺乏远程监管技术手段、考场行为不可追溯和考生身份难以实时验证等问题，提出一种基于边缘计算的智能监考系统。该系统由考试机、教师机、考点服务器和省服务集群组成。在考试机上利用CLAHE方法对图像进行光照的均匀化，然后将图像传送到模型中，并借助OpenVINO来加速检测过程；考试过程中，摄像头随机捕捉带有考生图像的桌面信息，图像经过考试终端上的模型进行检测，这些考生桌面图像临时存储在考点服务器；考试结束后，统一将本次考试的记录发送到省集群服务器上，作为后续查验的证明。实验结果表明，系统对硬件性能要求低，提高了对光照的鲁棒性，模型准确率达到95%左右，网络方面表现出更好的容错性。目前，该系统已在某边疆地区得到了推广应用。

关键词: 关键词：边缘计算, 人脸识别, 行为检测, 实时监考, 深度学习

Abstract: Abstract: To address the lack of remote supervision technologies, non-traceability of exam behavior, and difficulty in real-time verification of examinee identities in online remote examinations, this paper proposes an intelligent proctoring system based on edge computing. The system consists of exam terminals, teacher terminals, exam site servers, and a provincial service cluster. On the exam terminals, the CLAHE method is used to equalize image illumination before the images are transmitted to the model, with OpenVINO employed to accelerate the detection process. During the examination, the camera randomly captures desktop images containing the examinee’s face, and these images are processed by the model on the exam terminal. These images are temporarily stored on the exam site server, and after the exam, the records are sent to the provincial cluster server for post-exam verification. Experimental results demonstrate that the system has low hardware performance requirements, improves robustness to lighting variations, achieves a model accuracy of approximately 95%, and shows better fault tolerance in network performance. The system has already been deployed and applied in a remote border region.

Key words: Key words: edge computing, face recognition, behavior detection, real time invigilation, deep learning

中图分类号:

中图分类号:TP391.41

李京阳1, 薛化建2, 3, 杨勇1, 任鸽1. 基于边缘计算的智能监考系统[J]. 计算机与现代化, 2025, 0(12): 26-31.

LI Jingyang1, XUE Huajian2, 3, YANG Yong1, REN Ge1. Intelligent Proctoring System Based on Edge Computing[J]. Computer and Modernization, 2025, 0(12): 26-31.

参考文献

[1] 陈晋音,王桢,陈劲聿,等. 基于深度学习的智能教学系统的设计与研究[J]. 计算机科学, 2019,46(6A):550-554.
[2] 李伟,金梁. 基于WAMP架构的Web在线考试系统设计 [J]. 自动化技术与应用, 2023,42(5):162-165.
[3] 尹力威,王瀚林,雷奕达,等. 基于计算机视觉的学校智能监考系统[J]. 物联网技术, 2020,10(12):46-48.
[4] XUE J, WU W, CHENG Q K. Intelligent invigilator system based on target detection[J]. Multimedia Tools and Applications, 2023,23(82):44673-44695.
[5] 封彦,鲁磊. 基于YOLOV5和Dlib的在线违规行为监控识别算法[J]. 光电子技术, 2023,43(3):276-282.
[6] SU W X, LI L F, LIU F, et al. AI on the edge: A comprehensive review[J]. Artificial Intelligence Review, 2022,55(8):6125-6183.
[7] 李亚国,李冠良,张凯,等. 基于人工智能与边缘代理的物联网框架设计[J]. 计算机工程, 2023,49(10):313-320.
[8] LIN R P, XIE T Z, LUO S, et al. Energy-efficient computation offloading in collaborative edge computing[J]. IEEE Internet of Things Journal, 2022,9(21):21305-21322.
[9] SONG S X. Construction of university online examination system based on cloud computing technology[J]. Scientific Programming, 2021,2021. DOI: 10.1155/2021/7849255.
[10] DENG C L, FANG X M, WANG X B, et al. Software orchestrated and hardware accelerated artificial intelligence: Toward low latency edge computing[J]. IEEE Wireless Communications, 2022,29(4):110-117.
[11] OMETOV A, MOLUA O L, KOMAROV M, et al. A survey of security in cloud, edge, and fog computing[J]. Sensors(Basel), 2022,22(3). DOI: 10.3390/s22030927.
[12] 肖国亮,李汉才,程煜. 大规模考试信息化监考系统的设计与应用 [J]. 中国考试, 2019,324(4):41-45.
[13] 熊宗杨,薛学斌,王欣,等. 基于过程化考核的在线考试系统的研究与实现[J]. 重庆师范大学学报(自然科学版), 2018,35(6):75-81.
[14] SPARKS J. Enabling Docker for HPC [J]. Concurrency and Computation: Practice and Experience, 2019,31(16):e5018.
[15] DENG S G, ZHAO H L, FANG W J, et al. Edge intelligence: The confluence of edge computing and artificial intelligence [J]. IEEE Internet of Things Journal, 2020,7(8):7457-7469.
[16] OROCEO P P, KIM J I, CALIWAG E M F, et al. Optimizing face recognition inference with a collaborative edge-cloud network[J]. Sensors (Basel), 2022,22(21). DOI: 10.3390/s22218371.
[17] DENG J K, GUO J, YANG J, et al. ArcFace: Additive angular margin loss for deep face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022,44(10):5962-5979.
[18] JIAO J C, LIU W L, MO Y K, et al. Dyn-arcFace: Dynamic additive angular margin loss for deep face recognition[J]. Multimedia Tools and Applications, 2021,80(17):25741-25756.
[19] ROBERTO M D, HORMANN K. Histogram equalization using a selective filter[J]. The Visual Computer, 2023,39(12):6221-6235.
[20] IBRAHIM M H, SAYAGH M, HASSAN A E. A study of how Docker compose is used to compose multi-component systems[J]. Empirical Software Engineering, 2021,26(6). DOI: 10.1007/S10664-021-10025-1.
[21] 陈轶阳,王小宁,卢莎莎,等. 面向高性能计算系统的容器技术综述[J]. 计算机科学, 2023,50(2):353-363.
[22] DEMIDOVSKIJ A, GORBACHEV Y, FEDOROV M, et al. OpenVINO deep learning workbench: Comprehensive analysis and tuning of neural networks inference[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops. IEEE, 2019:783-787.
[23] 吴逸文,张洋,王涛,等. 从Docker容器看容器技术的发展:一种系统文献综述的视角[J]. 软件学报, 2023,34(12):5527-5551.
[24] MENG Q, ZHAO S C, HUANG Z D, et al. MagFace: A universal representation for face recognition and quality assessment[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2021:14225-14234.
[25] HUANG Y G, WANG Y H, TAI Y, et al. CurricularFace: Adaptive curriculum learning loss for deep face recognition[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE， 2020:5901-5910.
[26] JAISWAL S K, AGRAWAL R. A comprehensive review of YOLOv5: Advances in real-time object detection[J]. International Journal of Innovative Research in Computer Science and Technology, 2024,12(3):75-80.

基于边缘计算的智能监考系统

Intelligent Proctoring System Based on Edge Computing

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王晶鹏, 崔雨勇, 蔡长霖, 赫明骜, 李颖浩, 唐中和. 一种改进的跨模态交互和多尺度聚合的SOD算法[J]. 计算机与现代化, 2025, 0(11): 71-79.
[2]	苏衍森, 牟莉. 改进YOLOv8的课堂行为检测算法[J]. 计算机与现代化, 2025, 0(08): 76-81.
[3]	白佳, 谷林. 基于改进YOLOv7-tiny算法的学生课堂行为检测[J]. 计算机与现代化, 2025, 0(06): 9-15.
[4]	马永, 王俊, 张子健, 赵煜阳, 张靖, 周明. 面向智慧运维系统的改进YOLOv8行为检测算法[J]. 计算机与现代化, 2024, 0(08): 43-48.
[5]	赵晨伊1, 赵欣2. 一种基于元宇宙的边缘端资源配置方案[J]. 计算机与现代化, 2024, 0(04): 121-126.
[6]	马彩莎, 焦立男, 柳有权, 李欣. 基于扩张卷积融合时序特征异常行为检测[J]. 计算机与现代化, 2024, 0(02): 75-80.
[7]	王鑫, 肖韬睿. 基于生成对抗网络的人脸识别对抗攻击[J]. 计算机与现代化, 2023, 0(10): 115-120.
[8]	沈加炜, 陆一鸣, 陈晓艺, 钱美玲, 陆卫忠, . 基于深度学习的人体行为检测方法研究综述[J]. 计算机与现代化, 2023, 0(09): 1-9.
[9]	张芸, 白开峰, 王星, 仓甜, 周通, 段锦文, 苏晗. 智能电网环境下窃电行为检测[J]. 计算机与现代化, 2023, 0(03): 60-65.
[10]	盛江岸, 陈淑荣. 融合双重注意力机制的戴口罩人脸识别方法[J]. 计算机与现代化, 2023, 0(02): 72-77.
[11]	陈凯,祖莉,欧屹. 基于YOLOv3与ResNet50的摄影机器人人脸识别跟踪系统[J]. 计算机与现代化, 2020, 0(04): 30-.
[12]	李硕1，卞青山2，刘传文2，刘鸣涛1，张林涛1 . 基于DCNN的证件照人脸验证及应用研究[J]. 计算机与现代化, 2020, 0(02): 104-.
[13]	崔娟娟1，张蕾1,侯谢炼2，陈才扣2，张海燕1. 基于鉴别性低秩表示的2阶段人脸识别算法[J]. 计算机与现代化, 2019, 0(12): 55-.
[14]	李垒，任越美. 基于多任务联合判别稀疏表示的人脸识别[J]. 计算机与现代化, 2019, 0(10): 72-.
[15]	黄武飞1，曾吉昌1，黄锦权1，李思寒1，陈育均1，陈钊1，郑志硕1,2. 基于实验室安保服务型机器人的人脸识别[J]. 计算机与现代化, 2019, 0(07): 61-.