欢迎访问《图学学报》 分享到:

图学学报

• 视觉与图像 • 上一篇    下一篇

一种运动矢量和DCT 融合的无参考视频质量评价模型

摘 要:网络丢包引发的视频失真是网络视频流媒体服务质量评价的研究重点。#br# 网络丢包引发的人眼视觉感受与丢包所在帧类型、视频帧的运动剧烈状态和纹理丰富程度有#br# 着显著关联,提出了一种运动矢量和DCT 融合的无参考视频质量评价模型,以发生丢包的#br# 宏块为基本研究对象,以运动矢量表征其运动剧烈程度,以DCT 直流系数刻画其纹理丰富#br# 程度,无需获取原始视频任何信息,无需完全解码,关联运动矢量和DCT 完成视频质量的#br# 客观评价。实验结果表明,该模型的评价结果与主观评价结果有较好的一致性。#br# 关 键 词:无参考视频质量评价;丢包;运动剧烈程度;DCT 直流系数;空域复杂度   

  • 出版日期:2015-06-30 发布日期:2015-05-05

An Associated Quality Assessment Model of Motion Vector and DCT without Reference Video

Abstract: Network video distortion caused by packet loss is a research priority of online#br# video streaming service quality evaluation. An associated quality assessment model of motion#br# vector and DCT without reference video is provided. This model associates the human visual#br# perception caused by network packet loss with the frame type whose packet is lost, the movement#br# state and the richness of texture. This model takes the macro blocks that are lost as the basic study#br# object. And it calculates the motion intenseness by using the macro blocks? motion vector and#br# calculates the richness of its texture by using the DCT coefficients. And this model evaluates#br# videos? quality objectively by associating the motion vector and DCT without any information of#br# the original video and doesn?t need decoding completely. Experimental results show that this#br# model's evaluation results have a good consistency with the subjective evaluation results.#br# Key words: quality assessment without reference; packet loss; motion intenseness; DC#br# coefficient of DCT; spatial complexity   

  • Online:2015-06-30 Published:2015-05-05

摘要: 网络丢包引发的视频失真是网络视频流媒体服务质量评价的研究重点。
网络丢包引发的人眼视觉感受与丢包所在帧类型、视频帧的运动剧烈状态和纹理丰富程度有
着显著关联,提出了一种运动矢量和DCT 融合的无参考视频质量评价模型,以发生丢包的
宏块为基本研究对象,以运动矢量表征其运动剧烈程度,以DCT 直流系数刻画其纹理丰富
程度,无需获取原始视频任何信息,无需完全解码,关联运动矢量和DCT 完成视频质量的
客观评价。实验结果表明,该模型的评价结果与主观评价结果有较好的一致性。

关键词: 无参考视频质量评价, 丢包, 运动剧烈程度, DCT 直流系数, 空域复杂度

Abstract: Network video distortion caused by packet loss is a research priority of online
video streaming service quality evaluation. An associated quality assessment model of motion
vector and DCT without reference video is provided. This model associates the human visual
perception caused by network packet loss with the frame type whose packet is lost, the movement
state and the richness of texture. This model takes the macro blocks that are lost as the basic study
object. And it calculates the motion intenseness by using the macro blocks motion vector and
calculates the richness of its texture by using the DCT coefficients. And this model evaluates
videos quality objectively by associating the motion vector and DCT without any information of
the original video and doesnt need decoding completely. Experimental results show that this
model's evaluation results have a good consistency with the subjective evaluation results.

Key words: quality assessment without reference, packet loss, motion intenseness, DC
coefficient of DCT,
spatial complexity