Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SCB-Dataset3: A Benchmark for Detecting Student Classroom Behavior

Fan Yang, Tao Wang

TL;DR

SCB-Dataset3 addresses the lack of public datasets for student classroom behavior by introducing a six-class dataset with 5686 images and 45578 annotations, spanning kindergarten to university. The authors adopt an object-detection-based approach using YOLO variants and augment the university subset with frame interpolation, also introducing a Behavior Similarity Index (BSI) to quantify cross-behavior similarity. Key contributions include the dataset, benchmark results with a maximum $mAP$ of 80.3% on SCB-Dataset3-S, and validation of frame interpolation for university data. The dataset provides a foundation for future systems to monitor and analyze classroom engagement, with public download availability.

Abstract

The use of deep learning methods to automatically detect students' classroom behavior is a promising approach for analyzing their class performance and improving teaching effectiveness. However, the lack of publicly available datasets on student behavior poses a challenge for researchers in this field. To address this issue, we propose the Student Classroom Behavior dataset (SCB-dataset3), which represents real-life scenarios. Our dataset comprises 5686 images with 45578 labels, focusing on six behaviors: hand-raising, reading, writing, using a phone, bowing the head, and leaning over the table. We evaluated the dataset using the YOLOv5, YOLOv7, and YOLOv8 algorithms, achieving a mean average precision (map) of up to 80.3$\%$. We believe that our dataset can serve as a robust foundation for future research in student behavior detection and contribute to advancements in this field. Our SCB-dataset3 is available for download at: https://github.com/Whiffe/SCB-dataset

SCB-Dataset3: A Benchmark for Detecting Student Classroom Behavior

TL;DR

SCB-Dataset3 addresses the lack of public datasets for student classroom behavior by introducing a six-class dataset with 5686 images and 45578 annotations, spanning kindergarten to university. The authors adopt an object-detection-based approach using YOLO variants and augment the university subset with frame interpolation, also introducing a Behavior Similarity Index (BSI) to quantify cross-behavior similarity. Key contributions include the dataset, benchmark results with a maximum of 80.3% on SCB-Dataset3-S, and validation of frame interpolation for university data. The dataset provides a foundation for future systems to monitor and analyze classroom engagement, with public download availability.

Abstract

The use of deep learning methods to automatically detect students' classroom behavior is a promising approach for analyzing their class performance and improving teaching effectiveness. However, the lack of publicly available datasets on student behavior poses a challenge for researchers in this field. To address this issue, we propose the Student Classroom Behavior dataset (SCB-dataset3), which represents real-life scenarios. Our dataset comprises 5686 images with 45578 labels, focusing on six behaviors: hand-raising, reading, writing, using a phone, bowing the head, and leaning over the table. We evaluated the dataset using the YOLOv5, YOLOv7, and YOLOv8 algorithms, achieving a mean average precision (map) of up to 80.3. We believe that our dataset can serve as a robust foundation for future research in student behavior detection and contribute to advancements in this field. Our SCB-dataset3 is available for download at: https://github.com/Whiffe/SCB-dataset
Paper Structure (10 sections, 5 equations, 6 figures, 8 tables)

This paper contains 10 sections, 5 equations, 6 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. SCB-Dataset
  4. Behavioral similarity analysis
  5. Experiments
  6. Experimental Environment and Dataset
  7. Model Training
  8. Evaluation Metric
  9. Analysis of experimental results
  10. Conclusion

Figures (6)

  • Figure 1: Process for creating SCB-Dataset3-S.
  • Figure 2: Overlapping results of detection for reading and writing behavior.
  • Figure 3: Challenges in the SCB-Dataset3-S include dense environments, similar behaviors, and pixel differences..
  • Figure 4: Challenges in the SCB-Dataset3-S include varying shooting angles, class differences, and different learning stages.
  • Figure 5: Process for creating SCB-Dataset3-U.
  • ...and 1 more figures