计算机科学 ›› 2017, Vol. 44 ›› Issue (2): 290-295.doi: 10.11896/j.issn.1002-137X.2017.02.049

• 图形图像与模式识别 • 上一篇    下一篇

适配分辨率动态变化的低复杂度视频场景切换检测方法

方宏俊,宋利,杨小康   

  1. 上海交通大学图像通信与网络传输研究所 上海200030,上海交通大学图像通信与网络传输研究所 上海200030;未来媒体网络协同创新中心 上海200030,上海交通大学图像通信与网络传输研究所 上海200030;未来媒体网络协同创新中心 上海200030
  • 出版日期:2018-11-13 发布日期:2018-11-13
  • 基金资助:
    本文受国家自然科学基金委国家重大科研仪器研制项目:面向泛在视频的感知质量评测仪(61527804),创新群体项目:数字媒体通信理论与关键技术(61521062)资助

Low Complexity Scene Change Detection Algorithm for Supporting Resolution Dynamic Change

FANG Hong-jun, SONG Li and YANG Xiao-kang   

  • Online:2018-11-13 Published:2018-11-13

摘要: 在数字电视图像后处理中,许多图像增强和指标检测算法模块需要参考前后帧的时域信息,因此当场景内容发生切换时,需要设计出一种准确且可靠的场景切换检测的方法,用以切断场景切换前和场景切换后的各种时域算法的前后关联性。针对网络电视播放视频节目前后帧经常出现的分辨率变化的特性以及场景切换检测中常见的问题,对数字电视图像后处理中的视频场景切换检测算法进行了优化设计,提出了一种基于动态阶数控制直方图分布的优化检测算法。实验结果表明, 相比传统算法,所提算法在场景切换检测的准确度上有显著的提升,针对暗场景下的场景切换以及网络电视中分辨率改变的情形具有较高的准确度。

关键词: 数字电视,直方图,场景切换,画质增强

Abstract: In digital video post processing of TV system,many video detection and enhancement IP blocks need refer temporal information between frames.For cutting off the temporal relationship when content scene change happens,an optimum design of scene change detector was proposed in this paper.According to the network TV dynamically changes the video resolutions based on the quality of network service,the design adopts an optimum method based on histogram distribution detection combined with dynamic weighting.The simulation results show that the design has improved the detection accuracy compares to the common design which is based on the average intensity level.And it improves the detection’s reliability and stability for low IRE scenes and resolution dynamic change case of network TV programs.

Key words: Digital television,Histogram,Scene change,Video enhancement

[1] WANG Y,XUE Y L.Rate Control Algorithm Based on Scene Change[J].Digital Video,2009,33(12):17-20.(in Chinese) 王悦,薛永林.基于场景切换的码率控制方法[J].电视技术,2009,33(12):17-20.
[2] SHI J G,XU L,ZHANG C.Scene adaptive frame-layer rate control algorithm for H.264[J].Application Research of Computers,2010,27(5):1968-1973.(in Chinese) 史久根,许林,张超.一种场景自适应的H.264帧层码率控制算法[J].计算机应用研究,2010,27(5):1968-1973.
[3] LUPATINI G,SARACENO C,LEONARDI R.Scene break detection:a comparison[C]∥Proc of the 8th International Workshop on Continuous-Media Databases and Applications.Florida:IEEE Press,1998:34-41.
[4] LIANG C T,XUE Z M,LI C Y,et al.Scene Cut of HDTV Vi-deo Encoder[J].Journal of Shanghai Jiaotong University,1998,32(9):24-26.(in Chinese) 梁昌钛,薛震民,李朝阳,等.HDTV视频编码器的场景切换[J].上海交通大学学报,1998,32(9):24-26.
[5] CAO Y X,WANG B.Translucent Material Estimation Based on Color Histogram Matching[J].Journal of Computer-Aided Design & Computer Graphics,2015,27(3):441-450.(in Chinese) 曹一溪,王斌.基于颜色直方图估计的半透明材质估计[J].计算机辅助设计与图形学学报,2015,27(3):441-450.
[6] TANG J,JIANG B,LUO B.Graph Matching Based on Graph Histogram and Path Similarity[J].Journal of Computer-Aided Design & Computer Graphics,2011,23(9):1481-1489.(in Chinese) 汤进,江波,罗斌.基于图的直方图及路径相似性的图匹配方法[J].计算机辅助设计与图形学学报,2011,23(9):1481-1489.
[7] LI G B,WU H F.Weighted Fragments-Based Meanshift Trac-king Using Color-Texture Histogram[J].Journal of Compu-ter-Aided Design & Computer Graphics,2011,23(12):2059-2066.(in Chinese) 李冠彬,吴贺丰.基于颜色纹理直方图的带权分块均值漂移目标跟踪算法[J].计算机辅助设计与图形学学报,2011,23(12):2059-2066.
[8] WANG Z,HUANG Y P,LUO S W,et al.A Pairwise Cumulant-Based Model for Topographic Representations of Nature Image[J].Chinese Journal of Computers,2012,35(4):817-826.(in Chinese) 王哲,黄雅平,罗四维,等.基于成对累计量的自然图像拓扑表示模型[J].计算机学报,2012,35(4):817-826.
[9] QUAN H Y,WANG C B.A New Effective Method of Calcula-ting Fluid Motion Vector[J].Chinese Journal of Computer,2013,36(9):1889-1897.(in Chinese) 全红燕,王长波.一种流体运动矢量计算的有效方法[J].计算机学报,2013,36(9):1889-1897.
[10] MAS J,FERNANDEZ G.Video shot boundary detection based on color histogram[J/OL].http://www-nlpir.nist.gov/projects/tvpubs/tvpapers03/ramonlull.paper.pdf.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!