计算机科学 ›› 2026, Vol. 53 ›› Issue (8): 191-200.doi: 10.11896/jsjkx.251200195

• 计算机图形学 & 多媒体 • 上一篇    下一篇

基于多源融合的智慧教室教师巡视轨迹识别及重建方法

王一凡1,2, 杨佩璇2, 卢远索3, 刘梦君2,3   

  1. 1 湖北省教育科学研究院 武汉 430079
    2 湖北大学师范学院 武汉 430062
    3 湖北大学计算机学院 武汉 430062
  • 收稿日期:2025-12-31 修回日期:2026-04-16 出版日期:2026-08-15 发布日期:2026-08-17
  • 通讯作者: 卢远索(704548601@qq.com)
  • 作者简介:(1054570173@qq.com)
  • 基金资助:
    2021年度全国教育科学规划教育部重点课题:“大数据智能采集终端赋能区域教育质量评测实践研究”阶段性成果(DHA210338)

Teacher Trajectory Recognition and Reconstruction in Smart Classrooms via Multi-source Fusion

WANG Yifan1,2, YANG Peixuan2, LU Yuansuo3, LIU Mengjun2,3   

  1. 1 Hubei Academy of Educational Sciences, Wuhan 430079, China
    2 College of Teacher Education, Hubei University, Wuhan 430062, China
    3 School of Computer Science, Hubei University, Wuhan 430062, China
  • Received:2025-12-31 Revised:2026-04-16 Published:2026-08-15 Online:2026-08-17
  • About author:WANG Yifan,born in 1973,Ph.D,professor,Ph.D supervisor.His main research interests include education big data and educational assessment.
    LU Yuansuo,born in 2001,postgra-duate.His main research interests include machine vision and multimodal data fusion.
  • Supported by:
    Phased Research Achievements of the Key Project of National Education Science Planning(Ministry of Education) and 2021:Practical Research on Empowering Regional Education Quality Evaluation with Big Data Intelligent Collection Terminals(DHA210338).

摘要: 在教师课堂教学行为分析中,教师轨迹识别及重建是刻画教学活动时空特征的重要基础。然而,真实课堂环境中普遍存在的动态遮挡、视角差异及复杂交互,使得单摄像头目标跟踪方法在轨迹连续性与稳定性方面难以满足实际应用需求。针对上述问题,提出一种面向智慧教室场景的多摄像头教师轨迹识别与重建方法,通过多源观测融合、统一平面映射以及跨视角约束,实现多视角轨迹信息的稳健关联与连续重建。对不同方法在遮挡与视角切换条件下的轨迹识别及重建性能进行对比分析。实验结果表明,所提方法在复杂动态场景中能够有效降低轨迹中断频率,并在整体轨迹连续性与运动平滑性等指标上取得更优表现,验证了所提方法在真实智慧教室环境中执行教师巡视轨迹重建任务的有效性与鲁棒性。

关键词: 多摄像头跟踪, 教师轨迹, 轨迹重建, 轨迹连续性, 运动平滑性

Abstract: Teacher trajectory reconstruction is fundamental for modeling the spatio-temporal characteristics of teaching activities in video-based classroom behavior analysis.However,real classrooms involve frequent occlusions,viewpoint variations,and complex interactions,which make single-camera tracking methods struggle to maintain trajectory continuity and stability.To address these challenges,this paper proposes a multi-camera teacher trajectory tracking and reconstruction approach for smart classroom scenarios.By integrating multi-source observations,unified ground-plane mapping,and cross-view constraints,the proposed methodenables robust cross-view association and continuous reconstruction of multi-view trajectories.Moreover,it establishes an eva-luation framework focusing on trajectory continuity,interruption frequency,and motion smoothness to comparatively analyze different methods under occlusion and viewpoint transition conditions.Experimental results show that the proposed approach effectively reduces trajectory interruptions in complex dynamic scenes and achieves better trajectory continuity and motion smoothness,demonstrating its effectiveness and robustness for teacher trajectory reconstruction in real smart classroom environments.

Key words: Multi-camera tracking, Teacher trajectory, Trajectory reconstruction, Trajectory continuity, Motion smoothness

中图分类号: 

  • TP391.41
[1] YIN B Y,WANG X J,SUN X,et al.Multimodal decoding ofteachers’ classroom management behaviors:Behavioral features,classification and recognition,and temporal evolution[J].Chinese Journal of Educational Technology,2024,45(10):101-109.
[2] PAN W Y,LI Y T,MA M.Research progress on intelligentanalysis and understanding of teachers’ classroom behaviors[J].Computer Science,2026,53(5):41-49.
[3] ZHANG P,LEI W M,ZHAO X L,et al.A survey of cross-camera multi-object tracking methods[J].Chinese Journal of Computers,2024,47(2):287-309.
[4] RAO Y Q,ZHAO X J,CAI J H.Multi-feature fusion and detection methods for trajectory data[J].Mini-Micro Systems,2021,42(2):264-270.
[5] LIU H,ZHU Y,LI C P.Cross-network user identity recognition based on multi-type spatio-temporal trajectory features[J].Computer Science,2023,50(3):114-120.
[6] YOU S,YAO H,XU C.Multi-Target Multi-Camera TrackingWith Optical-Based Pose Association[J].IEEE Transactions on Circuits and Systems for Video Technology,2021,31(8):3105-3117.
[7] ARULAMPALAM M S,MASKELL S,GORDON N,et al.A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking[J].IEEE Transactions on Signal Processing,2002,50(2):174-188.
[8] YASSIN A,NASSER Y,AWAD M,et al.Recent advances in indoor localization:A survey on theoretical approaches and applications[J].IEEE Communications Surveys & Tutorials,2017,19(2):1327-1346.
[9] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[10] CIAPARRONE G,SÁNCHEZ F L,TABIK S,et al.Deep learning in video multi-object tracking:A survey[J].Neurocomputing,2020,381:61-88.
[11] ZHANG Y,SUN P,JIANG Y,et al.ByteTrack:Multi-Object Tracking by Associating Every Detection Box[C]//Proceedings of the European Conference on Computer Vision(ECCV).Cham:Springer,2022:1-21.
[12] CAO J,PANG J,WENG X,et al.Observation-Centric SORT:Rethinking SORT for Robust Multi-Object Tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2023:9686-9696.
[13] RISTANI E,SOLERA F,ROGERS R,et al.Performance measures and a data set for multi-target,multi-camera tracking[C]//Computer Vision-ECCV 2016 Workshops.Cham:Springer,2016:17-35.
[14] MEINHARDT T,KIRILLOV A,LEAL-TAIXÉ L,et al.Track-Former:Multi-object tracking with transformers[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2022:8844-8854.
[15] XIE Z,NI Z,YANG W,et al.A Robust Online Multi-Camera People Tracking System With Geometric Consistency and State-aware Re-ID Correction[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).2024:7007-7016.
[16] NGUYENP,QUACH K G,DUONG C N,et al.Multi-camera multi-object tracking on the move:A single-stage global association approach[J].Pattern Recognition,2024,152:110457.
[17] MIAO J,WU Y,LIU P,et al.Pose-guided feature alignment for occluded person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision(ICCV).2019:542-551.
[18] IGUERNAISSI R,MERAD D,AZIZ K,et al.People tracking in multi-camera systems:a review[J].Multimedia Tools and Applications,2019,78(8):10773-10793.
[19] CHEN Z,ZHANG Z,ZHANG H,et al.Multi-camera people tracking with asynchronous cameras[J].Sensors,2018,18(11):1-19.
[20] ZHOU Y S,CHEN G,SONG Z,et al.Research on the concept,architecture,and construction of smart language laboratories[J].Modern Educational Technology,2022,32(8):119-126.
[21] HU Q T,WEI M.A study on teachers’ digital classroom teach-ing behaviors from a phenomenological perspective[J].Chinese Journal of Educational Technology,2025,46(3):79-86.
[22] WANG D Q,LIU H,QIU M L.Analysis methods and application validation of teacher behavior data in smart classrooms[J].China Educational Technology,2020(5):120-127.
[23] LIU M J,ZOU W L,ZONG M,et al.How Generative Artificial Intelligence Empowers Teaching:An Empirical Study on Middle School Students’ English Writing Teaching[J].China Educational Technology,2025(6):70-79.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!