Measuring 3D Video Quality of Experience (QoE) Using A Hybrid Metric Based on Spatial Resolution and Depth Cues

Area of Science:

• Computer Vision
• Human-Computer Interaction
• Visual Perception

Background:

• 3D video quality assessment often relies on costly subjective tests.
• Existing objective methods lack accurate modeling of the human vision system (HVS).
• There is a need for efficient, objective methods to evaluate 3D video Quality of Experience (QoE).

Purpose of the Study:

• To propose a novel hybrid method for objective 3D video QoE evaluation.
• To develop a model that accurately reflects HVS perception of 3D video.
• To provide a reliable and efficient alternative to subjective quality assessment.

Main Methods:

• A hybrid QoE evaluation method was developed for 3D video.
• The method incorporates spatial resolution and key depth cues (motion, blurriness, retinal-image size, convergence).
• The approach models parameters directly influencing depth perception in stereoscopic vision.

Main Results:

• The proposed hybrid method demonstrates superior performance compared to existing 3D video QoE evaluation techniques.
• The method shows a high correlation with human vision system (HVS) measurements.
• Experimental results validate the effectiveness of the new evaluation approach.

Conclusions:

• The developed hybrid method offers a convenient and accurate approach for 3D video QoE evaluation.
• This method is particularly suitable for real-time applications requiring rapid quality assessment.
• The findings support the utility of integrating spatial resolution with depth cues for objective 3D video quality measurement.