Modeling Immersive Media Experiences by Sensing Impact on Subjects

As immersive technologies target to provide higher quality of multimedia experiences, it is important to understand the quality of experience (QoE) perceived by users from various multimedia rendering schemes, in order to design and optimize human-centric immersive multimedia systems. In this study, various QoE-related aspects, such as depth perception, sensation of reality, content preference, and perceived quality are being investigated and compared for presentation of 2D and 3D contents. Since the advantages of implicit over explicit QoE assessment have become essential, the way these QoE-related aspects influence brain and periphery is also investigated. In particular, two classification schemes using electroencephalography (EEG) and peripheral signals (electrocardiography and respiration) are carried out, to explore if it is possible to automatically recognize the QoE-related aspects under investigation. In addition, a decision-fusion scheme is applied to EEG and peripheral features, to explore the advantage of integrating information from the two modalities. The results reveal that the highest monomodal average informedness is achieved in the high beta EEG band (0.14% +/- 0.09, p<0.01), when recognizing sensation of reality. The highest and significantly non-random multimodal average informedness is achieved in when high beta EEG band is fused with peripheral features (0.17% +/- 0.1, p