Instance Segmentation-Driven Pose Estimation for Automated Classroom Behavior Analysis

Accurate extraction of student posture is essential for assessing classroom dynamics and teaching effectiveness. However, in complex classroom environments, challenges such as occlusions and overlapping students make pose estimation difficult. This paper presents a novel visual extraction model that combines instance segmentation with structured pose estimation to improve skeletal extraction accuracy and robustness. Leveraging the YOLO-SEG model, we efficiently segment individual students and apply a specialized pose estimation technique using discrete token representations to capture joint dependencies accurately. This dual approach ensures precise segmentation and detailed pose reconstruction, facilitated by a robust multilevel loss function that optimizes pose accuracy and quantization consistency. Our method enhances the automated analysis of student behaviors, offering significant implications for educational assessments.

I. Introduction

In educational environments, human pose estimation is crucial for understanding student behavior and engagement, offering key insights for assessing teaching effectiveness. However, accurately capturing human poses in dynamic and complex classroom settings presents significant challenges. These challenges include frequent occlusions, overlapping figures, and the diversity of student postures, all of which complicate the accurate extraction of skeletal structures [1]. Despite advances in pose estimation technology that have improved the interpretation of human postures, consistently extracting precise skeletal details in such complex scenarios remains a significant challenge [2].