Subjective quality assessment of 3D videos

Abstract

Colour plus depth map based stereoscopic video has attracted significant attention in the last 10 years, as it can reduce storage and bandwidth requirements for the transmission of stereoscopic content over wireless channels such as mobile networks. However, quality assessment of coded 3D video sequence can currently be performed reliably using expensive and inconvenient subjective tests [1]. The main goal of many subjective video quality metrics is to automatically estimate average user or viewer opinion on a quality of video processed by the system. However, measurement of subjective video quality can also be challenging because it may require a trained expert to judge it. Many subjective video quality measurements are described in ITUT recommendation BT.500. Their main idea is the same as in Mean Opinion Score for video sequences which are showed to the group of viewers and then their opinion is recorded and averaged to evaluate the quality of each video sequence. Optimization of 3D video systems in a timely manner is very important, it is therefore necessary that reliable subjective measures are calculated based on statistical analysis. This paper investigates subjective assessment for four standard 3D video sequences. Subjective tests are performed to verify the 3D video quality and depth perception of a range of differently coded video sequences, with packet loss rates ranging from 0% to 20%. The subjective quality results are used to determine more accurately the objective quality assessment metrics for 3D video sequences such as the Average PSNR, Structural similarities (SSIM), Mean Square Error (MSE) etc.The proposed measure of 3D perception and 3D quality of experience (QoE) is shown to correlate well with human perception of quality on a publicly available dataset of 3D videos and human subjective scores. The proposed measure extracts statistical features from depth and 3D videos to predict the human perception and 3D QoE.