计算机科学与探索 ›› 2021, Vol. 15 ›› Issue (3): 423-437.DOI: 10.3778/j.issn.1673-9418.2008009

• 综述·探索 • 上一篇    下一篇

基于深度学习的视频质量评价研究综述

谭娅娅,孔广黔   

  1. 贵州大学 计算机科学与技术学院,贵阳 550025
  • 出版日期:2021-03-01 发布日期:2021-03-05

Review of Research on Video Quality Assessment Based on Deep Learning

TAN Yaya, KONG Guangqian   

  1. School of Computer Science and Technology, Guizhou University, Guiyang 550025, China
  • Online:2021-03-01 Published:2021-03-05

摘要:

视频质量评价(VQA)是以人眼的主观质量评估结果为依据,使用算法模型对失真视频进行评估。传统的评估方法难以做到主观评价结果与客观评价结果相一致。基于深度学习的视频质量评价方法无需加入手工特征,通过模型自主学习即可进行评估,对视频质量的监控和评价有重要意义,已成为计算机视觉领域的研究热点之一。首先对视频质量评价的研究背景和主要研究方法进行介绍;其次从全参考型和无参考型两方面介绍基于深度学习的客观质量评价方法,并且从所用的卷积神经网络模型对无参考型评价方法进行了分类比较;接着介绍视频质量评价算法的相关数据库和评价算法性能指标,并对算法性能进行比较;最后对目前视频质量评价研究存在的问题进行总结,并展望了该领域面临的挑战和未来发展方向。

关键词: 深度学习, 视频质量评价(VQA), 客观评价, 无参考, 卷积神经网络(CNN)

Abstract:

Video quality assessment (VQA) is based on the subjective quality assessment results of the human eye, using models to evaluate distorted videos. It is difficult for traditional assessment methods to make subjective assessment results consistent with objective assessment results. The VQA methods based on deep learning can be evaluated through independent learning of the model without adding manual features. It is of great significance to video quality monitor and assessment, and has become one of the research hotspots in computer vision. First, this paper introduces the research background and main research methods of VQA. Second, it introduces the VQA methods based on deep learning from both the full-reference and no-reference ones, and uses the convolutional neural network model to classify and compare the no-reference evaluation methods. Then it introduces the related databases and performance evaluation indices of the VQA models and compares the algorithm performance. Finally, this paper summarizes the existing problems in the current VQA researches and looks forward to the challenges and development directions in this field.

Key words: deep learning, video quality assessment (VQA), objective evaluation, no-reference, convolutional neural network (CNN)