考虑丢包特性的无参考网络视频质量评估模型

A No-Reference Assessment Model for Quality of Networked Video Based on Features of Packets Loss

针对相同丢包率条件下不同的包丢失集中度对视频质量影响不同的问题,提出一种考虑丢包特性并且不需要对视频解码的无参考网络视频质量评估模型.首先依据码流信息在压缩域计算视频的时域复杂度,然后在压缩域计算包丢失集中度和包丢失率对视频质量的影响因子.考虑到人眼视觉系统的空域掩盖效应和时域掩盖效应,进而提出由于丢包引起的视频质量下降的视频质量评估模型.该模型不需要对视频进行完全解码,具有资源开销小、实时性好的特点,适合对实时传输的视频流进行质量评估.实验结果表明,使用该视频质量评估模型测得的视频包丢失质量评分与其主观质量评分有很好的一致性,相比于国际标准G.1070中的丢包视频质量评价模型,无参考网络视频质量评价模型与主观质量评价的相关性平均提高了6.18%.

A novel no-reference video quality assessment model is proposed based on the effect of concentrative degree of packet loss ratio and features of packet ratio on video quality.Without decoding,the temporal complexity is calculated in terms of the effect of packet loss ratio on video quality.The concentrative degree of packet loss ratio is calculated in compression domain to determine the effect of concentrative degree of packet loss ratio on video quality.Then,the present video quality assessment model is proposed by taken spatial and temporal error concealment artifacts of human visual system,packet loss ratio,and the degree of concentration packet loss ratio into account.The proposed model can assess video qualities without fully decoding networked video,thus reduces the cost and time delay.Experimental results show that the scores obtained by the proposed model are highly consistent with the subjective assessment scores.Compared with the video quality evaluation model in G.1070,a gain of 6.18% in the average performance is achieved by the proposed model in terms of relativity to subjective results.