改进的低比特率压缩视频的块失真检测算法

A New Algorithm for Measuring Blocking Artifacts at Low Bit-Rate Videos

在多媒体通信系统的研究中,实时的视频质量检测在信道估计和编解码器优化中起着重要作用。然而大多数被提议的视频质量评估方法需要参考序列,在实时多媒体通信中往往是不可能实现的。为实现实时性测量,提出了低比特率压缩视频的块失真检测方法。结合人类视觉系统(HVS)特点,算法简单,不需要原始参考视频,并且可有效避免解码器解码时,后滤波对失真检测带来的影响。通过对标准视频序列的仿真实验,证明算法可有效检测不同压缩视频的块失真状况,并且更接近人类主观感受,可以用来进行无参考的视频质量评估和监测各种视频系统传输信道的实时性能。

Video quality assessment in real time is a critical requirement for channel evaluation and codec optimization in multimedia communications system.However,most proposed approaches for video quality assessment need reference sequences,which is quite impossible in real time multimedia communications.An algorithm for measuring blocking artifacts at low bit-rate videos is proposed in this paper.Concerning human visual system（HVS） physiological characteristic,the proposed algorithm is very simple computationally and does not require the original video sequence as a comparative reference.It can avoid the influence of blocking artifacts reduction by employing different post-processing techniques in decoder.Experimental results show that the proposed algorithm can measure the distortion of blocking artifacts in compressed videos efficiently and has good consistency with subjective perceive.It can offer no-reference video quality assessment and be applied to monitor the performance of the transmission channel in various video systems to ensure video quality.