Implementation of Gaze Tracking Based on Head Pose Estimation to Determine Consumer Point of Interest Using Depth-Camera

Yulius, Yulius and Purnama, James and Galinium, Maulahikmah (2015) Implementation of Gaze Tracking Based on Head Pose Estimation to Determine Consumer Point of Interest Using Depth-Camera. Bachelor thesis, Swiss German University.

[img]
Preview
Text
Yulius 12111014 TOC.pdf

Download (537kB) | Preview
[img] Text
Yulius 12111014 1.pdf
Restricted to Registered users only

Download (334kB)
[img] Text
Yulius 12111014 2.pdf
Restricted to Registered users only

Download (465kB)
[img] Text
Yulius 12111014 3.pdf
Restricted to Registered users only

Download (723kB)
[img] Text
Yulius 12111014 4.pdf
Restricted to Registered users only

Download (638kB)
[img] Text
Yulius 12111014 5.pdf
Restricted to Registered users only

Download (407kB)
[img]
Preview
Text
Yulius 12111014 Ref.pdf

Download (411kB) | Preview

Abstract

A gaze is an indicator what people focused on or interested in. The research purpose is to implement a gaze tracking application so that people know which part of a wide view target is the most interesting by people. This research uses Kinect Xbox 360 as a tracking device and Visual Studio 2013 as development environment (IDE). The research can be applied in an advertisement usability, to know which the point of interest is for consumer so retailers or advertisement designers can put their best on it. Using the source code of Facetracking from Microsoft Kinect SDK to get drawings of face models, then modifying them to determine gaze of the subjects and their ID. There are several scenarios to supervise experiment result with help of volunteers. The research results between 70% and 80% accuracy percentage in practical experiment scenarios (ideal condition), and 50-60% in real experiment scenario. From the results, graph and statistics can be generated so the user can know which the point of interest is based on view order, view frequency or view duration.

Item Type: Thesis (Bachelor)
Uncontrolled Keywords: Kinect SDK; Kinect Xbox 360; Eye gaze tracking; head pose estimation; point of interest; C# Visual Studio.
Subjects: T Technology > T Technology (General) > T58.5 Information technology
T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing
Divisions: Faculty of Engineering and Information Technology > Department of Information Technology
Depositing User: Atroridho Rizky
Date Deposited: 20 Jan 2021 15:17
Last Modified: 20 Jan 2021 15:17
URI: http://repository.sgu.ac.id/id/eprint/1728

Actions (login required)

View Item View Item