Spherical Image QoE Approximations for Vision Augmentation Scenarios

Patrick Seeling, B. Bauman

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Augmented Reality (AR) devices are commonly head-worn to overlay context-dependent information into the field of view of the device operators. One particular scenario is the overlay of still images, for which we evaluate the interplay of user ratings as Quality of Experience (QoE) with (i) the non-referential BRISQUE objective image quality metric as Quality of Service (QoS) and (ii) human subject dry electrode EEG signals gathered with a commercial off-the-shelf device. We employ basic machine learning approaches to perform QoE and QoS predictions based on this data. We find strong correlations for QoS inputs with aggregated user ratings as Mean Opinion Scores with spherical images. For subject-specific EEG portfolios, overall predictability of the QoE for both media types can be attained. Our overall results can be employed in practical scenarios by content and network service providers to optimize the user experience in augmented reality scenarios with a passive human in-the-loop in the future.
Original languageEnglish
Pages (from-to)18113-18135
Number of pages23
JournalMultimedia Tools and Applications
Volume78
Issue number13
DOIs
StatePublished - Jan 2019

Keywords

  • Augmented reality
  • Electroencephalography
  • Image quality
  • Quality of experience
  • Quality of service

Fingerprint

Dive into the research topics of 'Spherical Image QoE Approximations for Vision Augmentation Scenarios'. Together they form a unique fingerprint.

Cite this