Person Detection in Collaborative Group Learning Environments Using Multiple Representations

TL;DR

This paper presents a multi-representation approach combining FM, AM-FM, and YOLO techniques to accurately detect and separate student groups in long classroom videos, outperforming YOLO alone.

Contribution

The paper introduces a novel multi-representation method for group detection in classroom videos, integrating FM, AM-FM, and YOLO for improved accuracy.

Findings

Multi-representation approach outperforms YOLO alone in accuracy.

Effective separation of student groups from background in long videos.

Validated on videos from four different groups.

Abstract

We introduce the problem of detecting a group of students from classroom videos. The problem requires the detection of students from different angles and the separation of the group from other groups in long videos (one to one and a half hours). We use multiple image representations to solve the problem. We use FM components to separate each group from background groups, AM-FM components for detecting the back-of-the-head, and YOLO for face detection. We use classroom videos from four different groups to validate our approach. Our use of multiple representations is shown to be significantly more accurate than the use of YOLO alone.