New Stereo Video Quality Assessment Metric for Three Dimensional Video Systems

Since traditional two dimensional video quality metrics are not suitable for evaluating stereo video, a new stereo video quality metric based on support vector regression (SVR) for three dimensional video systems is proposed in this paper. Firstly, three factors affecting the quality of stereo video are analyzed, namely left-view video quality, right-view video quality and difference between two views. Then, each of these factors is calculated respectively with measuring the singular vectors’ similarity between original image blocks and distorted image blocks and with temporal weighting using fluctuations of video frames’ spatial quality. Then, SVR is used to learn the relationships between the factors and the overall perceived quality of stereo video. Finally, the relationship is applied to predict the objective quality of stereo video. By applying the proposed metric to stereo video database, Person’s linear correlation coefficient is higher than 0.82 for all types of distortions and 0.81 for individual distortion, which outperforms the other existing metrics. Experimental results also show that, the proposed metric can achieve stable performance for all kinds of distortions and predict human perception well.