Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Assessment of the Microsoft Kinect v1 RGB-D Sensor and 3D Object Recognition as a Means of Drift Correction in Head mounted Virtual Reality Systems
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science and Engineering.
2015 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Context. The release of the Oculus Rift Development Kits and other similar hardware has led to something of a resurrection of interest in virtual reality hardware, but such hardware has problems in the form of, for example, drift errors, where the estimated forward direction veers of in an arbitrary direction. These drift errors accumulate over time and can lead to reduced user immersion and a need for the user to continuously calibrate the hardware. Objective. This study aims to investigate the possibility of drift error correction through the use of the Microsoft Kinect v1 RGB-D sensor and 3D object tracking technology. Method. Through the creation of a prototype application that utilizes object recognition to find the Oculus Rift DK1 on the user’s head and calculates its estimated six degrees of freedom, a "real world" forward vector can be produced. This vector’s authenticity can then be evaluated through an experiment that compares it to the forward direction reported by the Oculus Rift DK1. Result. The result is an application that can successfully recognize the Oculus Rift DK1 in a scene and deduce what its forward direction is. Due to what is suspected to be hardware malfunctions in the Oculus Rift DK1 the test results are not satisfactory, although observations still indicate that the application would perform within the set boundaries should the malfunctions not be present. Conclusion. Even though the experiment’s results are not ideal, the application shows promise and should be studied further with more accurate measuring equipment.

Place, publisher, year, edition, pages
2015. , p. 32
Keywords [en]
Object recognition, Oculus Rift DK1, Microsoft Kinect v1, Point Cloud Library
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:bth-11651OAI: oai:DiVA.org:bth-11651DiVA, id: diva2:905936
Subject / course
DV2524 Degree Project in Computer Science for Engineers
Educational program
PAACI Master of Science in Game and Software Engineering
Supervisors
Examiners
Available from: 2016-02-23 Created: 2016-02-23 Last updated: 2016-02-23Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Department of Computer Science and Engineering
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 335 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf