摘要： In this paper, we introduce PeQASO, a perceptual quality assessment framework for streamed videos using optical ?ow features. This approach is a reduced-reference pixel-based and relies only on the deviation of the optical ?ow of the corrupted frames. This technique compares an optical ?ow descriptor from the received frame against the descriptor obtained from the anchor frame. This approach is suitable for videos with complex motion patterns. Our technique does not make any assumptions on the coding conditions, network loss patterns or error concealment techniques. In this paper, we consider both sources of artifacts and distortions in streaming, including compression artifacts. We validate our proposed metric by testing it on a variety of distorted sequences from three proposed and commonly utilized video quality assessment databases. Our results show that our metric estimates the perceptual quality at the sequence level accurately. We report the correlation coef?cients with the differential mean opinion scores reported in the database. For compression artifacts, the results show Spearman’s and Pearson’s correlations of 0.96 and 0.94 for all the tested sequences, respectively. For channel-induced distortion, the results show Spearman’s and Pearson’s correlations of 0.88 and 0.89, respectively. For all other distortions, the average Spearman’s and Pearson’s correlations are 0.82 and 0.79, respectively.