针对大班课堂行为分析难题，构建新数据集并提出高效检测框架。
A Smart Classroom Behavior Analysis Framework with a New Highly Congested Classroom Dataset
- 基于YOLO改进，引入抗遮挡边界增强与高阶关系融合机制
- 在新数据集上达到80.12% mAP50，显著优于主流方法
- 适合智能教室、行为识别研究者参考
学生行为检测对智能课堂分析至关重要，但在大班场景下因密集实例共现、非对称遮挡、尺度变化和远距离目标语义退化而面临挑战。现有数据集与通用检测器难以应对这些难题。本文构建了高度拥挤课堂行为（HCCB）数据集，包含50,229个行为实例，涵盖阅读、书写、抬头、睡觉、环顾、低头、使用手机七类。该数据集融合密集分布、严重遮挡、尺度变化与细粒度语义特征。为此提出ODER-HSFNet，一种专为高密度课堂设计的YOLO检测框架。核心创新包括：面向遮挡的可变形边缘修正器（ODER），强化遮挡下的边界信息；超图状态空间融合模块（HSSF），整合局部结构增强、状态空间建模与高阶关系聚合；遮挡校准检测头（OCDetect），抑制低质量候选框，减少遮挡边界与邻近实例带来的误检。在两个课堂行为检测数据集上的实验表明，该框架性能超越主流YOLO系列方法，在HCCB上达到60.60%/80.12% mAP50:95/mAP50，SCB-D3-S上达57.36%/74.65%。消融实验验证了各模块的有效性。
原文摘要 · Abstract (English)
Student behavior detection is important for intelligent classroom analysis but remains challenging in large-class scenarios due to dense instance co-occurrence, asymmetric occlusion, depth-wise scale variation, and fine-grained semantic degradation in distant targets. Existing classroom behavior datasets and general-purpose detectors are insufficient to characterize and address these challenges. This paper constructs the Highly Congested Classroom Behavior (HCCB) dataset, containing 50,229 student behavior instances across seven categories: reading, writing, heads up, sleeping, looking around, bowing head, and using phone. HCCB provides a challenging benchmark that integrates dense distributions, severe occlusion, scale variation, and fine-grained behavioral semantics. To address these issues, we propose ODER-HSFNet, a YOLO-based detection framework tailored to highly crowded classrooms. At its core, ODER-HSFNet introduces three task-specific innovations: the Occlusion-aware Deformable Edge Rectifier (ODER), which strengthens boundary evidence under occlusion; the Hypergraph-State Spatial Fusion (HSSF) module, which integrates local structure enhancement, state-space contextual modeling, and high-order relation aggregation; and the Occlusion-Calibrated Detection Head (OCDetect), which suppresses low-quality Pre-NMS candidates and reduces false positives from occlusion boundaries and neighboring instances. Experiments on two classroom behavior detection datasets show that ODER-HSFNet outperforms mainstream YOLO-series methods, achieving 60.60%/80.12% mAP50:95/mAP50 on HCCB and 57.36%/74.65% on SCB-D3-S. Ablation studies further verify the effectiveness of the proposed design for highly crowded classroom behavior detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。