Long-term Human Participation Assessment In Collaborative Learning Environments Using Dynamic Scene Analysis

TL;DR

This paper introduces datasets and methods for assessing student participation in real-life collaborative learning environments, focusing on group detection and dynamic participant tracking amidst challenging conditions, achieving high accuracy and robustness.

Contribution

It presents a novel approach combining multiple image representations for group detection and a dynamic tracking system, outperforming existing methods on large real-life datasets.

Findings

Proposed method achieved an F1 score of 0.85, surpassing YOLO's 0.80.

Dynamic participant tracking missed only 1 out of 35 students, outperforming state-of-the-art.

Achieved 82.3% accuracy in long-term real-life collaborative videos.

Abstract

The paper develops datasets and methods to assess student participation in real-life collaborative learning environments. In collaborative learning environments, students are organized into small groups where they are free to interact within their group. Thus, students can move around freely causing issues with strong pose variation, move out and re-enter the camera scene, or face away from the camera. We formulate the problem of assessing student participation into two subproblems: (i) student group detection against strong background interference from other groups, and (ii) dynamic participant tracking within the group. A massive independent testing dataset of 12,518,250 student label instances, of total duration of 21 hours and 22 minutes of real-life videos, is used for evaluating the performance of our proposed method for student group detection. The proposed method of using multiple image representations is shown to perform equally or better than YOLO on all video instances. Over the entire dataset, the proposed method achieved an F1 score of 0.85 compared to 0.80 for YOLO. Following student group detection, the paper presents the development of a dynamic participant tracking system for assessing student group participation through long video sessions. The proposed dynamic participant tracking system is shown to perform exceptionally well, missing a student in just one out of 35 testing videos. In comparison, a state of the art method fails to track students in 14 out of the 35 testing videos. The proposed method achieves 82.3% accuracy on an independent set of long, real-life collaborative videos.