2017/05/02 by Brian Bauman, Bauman, Brian, Patrick Seeling +1
Computer Science · Social Sciences · #Advanced Computing and Algorithms #FOS: Computer and information sciences #Image and Video Quality Assessment #Multimedia (cs.MM) #Virtual Reality Applications and Impacts #Visual Attention and Saliency Detection
paper · pdf · doi:10.48550/arxiv.1705.01123
openalex publication_date 2017/05/02 · openalex created_date 2022/09/30 · openalex updated_date 2026/07/28
Augmented Reality (AR) devices are commonly head-worn to overlay\ncontext-dependent information into the field of view of the device operators.\nOne particular scenario is the overlay of still images, either in a traditional\nfashion, or as spherical, i.e., immersive, content. For both media types, we\nevaluate the interplay of user ratings as Quality of Experience (QoE) with (i)\nthe non-referential BRISQUE objective image quality metric and (ii) human\nsubject dry electrode EEG signals gathered with a commercial device.\nAdditionally, we employ basic machine learning approaches to assess the\npossibility of QoE predictions based on rudimentary subject data. Corroborating\nprior research for the overall scenario, we find strong correlations for both\napproaches with user ratings as Mean Opinion Scores, which we consider as QoE\nmetric. In prediction scenarios based on data subsets, we find good performance\nfor the objective metric as well as the EEG-based approach. While the objective\nmetric can yield high QoE prediction accuracies overall, it is limited i its\napplication for individual subjects. The subject-based EEG approach, on the\nother hand, enables good predictability of the QoE for both media types, but\nwith better performance for regular content. Our results can be employed in\npractical scenarios by content and network service providers to optimize the\nuser experience in augmented reality scenarios.\n