基于视频内容的QoE评价模型

Content-based Video Evaluation Model for Users′ Quality of Experience

提出一种基于视频内容的QoE评价模型.该模型除获取包头信息编码比特率和丢包率外,还从视频载荷信息中获取帧类型、宏块类型、运动矢量等信息,利用运动矢量和帧内编码宏块比例来代表视频的内容运动特性,将其与编码比特率和丢包率结合起来分别建立编码失真模型和传输失真模型并联合构建出基于视频内容的QoE评价模型.实验结果表明,该模型计算得到的客观评价分数与主观测试MOS分数的皮尔森相关性系数为0.964 4,均方根误差为0.349 0,该模型能够准确评价不同内容的网络视频QoE,具有良好的性能.

A content-based video evaluation model for users′QoE is proposed to achieve an accurate evaluation of the network video quality.In addition to obtain the coding bit rate and the packet loss rate from the packet headers,the model also obtain the frame type,the macro-block type and the motion vector from the payload information,using the motion vectors and the ratio of intra-coded macro-blocks to represent the motion characteristics of video content,combined it with the coding bit rate and the packet loss rate to establish the distortion model and transmission distortion model respectively,and the content-based video evaluation model for users′ QoE is then generated.Experimental results show that the Pearson Correlation Coefficient between objective score obtained from the model calculations and subjective MOS scores is as high as 0.964 4and the Root Mean Square Error of them is 0.349 0.The proposed model has a great accuracy on predicting users′QoE of networked videos of different content account with its good performance.