Objective Evaluation of Presence in Virtual Reality Based on Visual Features

The sense of presence in virtual reality is a crucial factor for evaluating the quality and effectiveness of virtual reality products. In order to assess it accurately, an objective assessment method for virtual reality presence was proposed. An analysis of influencing factors was conducted. Features such as texture, color, and contrast from virtual reality videos were extracted. Discomfort experienced during virtual reality immersion can divert user attention, break the immersive experience and affect the sense of presence. Therefore, VR sickness scores were introduced as a feature in the assessment. We establish a virtual reality presence assessment model based on Support Vector Regression (SVR). Experimental results indicate that texture features have a significant impact on the sense of presence in virtual reality, and color and contrast also play a role. The inclusion of the sickness score in the model improved assessment accuracy. The assessment results showed a high level of consistency with subjective evaluations of the sense of presence in virtual reality, achieving performance metrics higher than other related studies, with a PLCC of 0.781.