融合空时感知特性的无参考视频质量评估算法  

Blind VQA Pooling Spatial-Temporal Perceptual Characteristics

作　　者：吴泽民[1] 彭韬频 田畅[1] 胡磊[1] 王露萌 

机构地区：[1]中国人民解放军理工大学通信工程学院,江苏南京210007 [2]电子科技大学外国语学院,四川成都611731

出　　处：《电子学报》2017年第3期557-564,共8页Acta Electronica Sinica

基　　金：光电控制技术重点实验室和航空科学基金联合资助项目(No.20125286005);国家自然科学基金青年基金(No.61501509)

摘　　要：本文通过简化视频质量评估中人眼感知模型的复杂性,提出了一种新的无参考视频质量评估模型.首先通过分别抽取视频的空间域和时间域特征,然后按照视频局部块、视频帧、视频段等从细到粗的不同粒度,模拟人眼感知特性进行多重加权汇聚,最终得到整段视频的特征向量描述.本方法以支持向量回归器为评估模型训练工具,通过有监督的视频样本库训练,以无参考方式完成未知视频的质量评估.实验结果表明,该评估算法的性能不但要优于当前已知最经典的无参考评估算法Video BLLINDS,而且与部分参考评估算法相当.This paper proposes a no-reference video quality assessment model by reducing the complexity of the human visual system（ HVS）. The characteristics of spatial domain and temporal domain of the videos are firstly extracted. Then multiweight convergence is conducted by simulating visual perception according to different granularity from fine-grained to coarsegrained of video local block,video frame,video segment,etc. Finally the feature vector of the whole video is achieved. The support vector regression（ SVR） is taken as quality assessment tool in this algorithm. The quality assessment of the unknown video is obtained without reference after supervised training. The experiments we have done showthat the algorithm is not only superior to all of the other no-reference quality assessment algorithms,but also can be compared to part-reference algorithms.

关 键 词：视频质量评估 人眼视觉系统 离散余弦变换 支持向量回归器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]