Title

Attention Detection using Kinect

Poster Number

27

Lead Author Affiliation

Computer Science

Introduction

After the invention of the Microsoft Kinect in 2009, many developers began researching possible applications of Kinect that go beyond the system’s original intended use in playing video games. The Kinect is an input device that helps researchers develop immersive applications that harness voice, movement and gesture recognition. The appeal of the Kinect to researchers stems from its affordability and the extensive built-in image processing capabilities of the device. In this research Microsoft Kinect is used to collect facial and posture information from the users and implement a machine learning algorithm to detect the level of attention in students.

Purpose

The purpose of this research is to use data collected from Kinect to determine the most important factors that affect the level of attention in students.

Method

For testing the methodology, Kinect was used to record data while subjects were given multiple ways to learn a topic. Subjects were given a lecture on specific topic and then they were given time to go through a set of questions to asset their level of attention in class. The whole time the subject was monitored using a Kinect v2 which recorded their facial features as well as body positions. Facial features that were recorded included eye details such as which eyes were open, how much were the right and left eye open, where was the subject looking and what their mouth position was, were they frowning, smiling or neutral. For body features we looked which direction was the subjects body leaning (towards the screen or away from it), what was the head position(was the subject's head leaning toward the right or left shoulder).

Results

In this research we are implementing a machine learning algorithm that uses the data collected from Kinect to determine whether the subject was attentive in the class or not.

Significance

By specifying the most important factors that affect the level of attention in class, more active learning methods can be implemented by instructors to help the learning process of students.

Location

DeRosa University Center, Stockton campus, University of the Pacific

Format

Poster Presentation

This document is currently not available here.

Share

COinS
 
Apr 25th, 2:00 PM Apr 25th, 4:00 PM

Attention Detection using Kinect

DeRosa University Center, Stockton campus, University of the Pacific

After the invention of the Microsoft Kinect in 2009, many developers began researching possible applications of Kinect that go beyond the system’s original intended use in playing video games. The Kinect is an input device that helps researchers develop immersive applications that harness voice, movement and gesture recognition. The appeal of the Kinect to researchers stems from its affordability and the extensive built-in image processing capabilities of the device. In this research Microsoft Kinect is used to collect facial and posture information from the users and implement a machine learning algorithm to detect the level of attention in students.