基于多类支持向量机的3D-HEVC深度视频帧内编码快速算法

刘晟; 彭宗举; 陈嘉丽; 陈芬; 郁梅; 蒋刚毅

doi:10.11959/j.issn.1000-436x.2016235

您当前的位置：

首页 >

文章列表页 >

基于多类支持向量机的3D-HEVC深度视频帧内编码快速算法

学术通信 | 更新时间：2024-06-05

- 基于多类支持向量机的3D-HEVC深度视频帧内编码快速算法
- Multi-class support vector machine-based fast algorithm for 3D-HEVC depth video intra coding
- 通信学报 2016年37卷第11期页码：181-188
- 作者机构：
  
  宁波大学信息科学与工程学院，浙江宁波315211
- 作者简介：
  
  [ "刘晟（1991-），男，安徽来安人，宁波大学硕士生，主要研究方向为视频信号处理与编码。" ]
  [ "彭宗举（1973-），男，四川南部人，博士，宁波大学教授、博士生导师，主要研究方向为多媒体信号处理与编码等。" ]
  [ "陈嘉丽（1993-），女，湖南邵阳人，宁波大学硕士生，主要研究方向为虚拟视点绘制与质量评价。" ]
  [ "陈芬（1973-），女，四川邻水人，博士，宁波大学副教授，主要研究方向为视频图像处理。" ]
  [ "郁梅（1968-），女，江苏无锡人，博士，宁波大学教授、博士生导师，主要研究方向为图像视频信息过程编码压缩与通信等。" ]
  [ "蒋刚毅（1964-），男，浙江绍兴人，博士，宁波大学教授、博士生导师，主要研究方向为立体/多视点视频信号处理、3DTV/自由视点视频系统编码与传输等。" ]
- 基金信息：
  
  国家高技术研究发展计划（“863”计划）基金资助项目(2015AA015901);国家自然科学基金资助项目(61620106012);国家自然科学基金资助项目(U1301257);国家自然科学基金资助项目(61271270);浙江省自然科学基金资助项目(LY16F010002);浙江省自然科学基金资助项目(LY15F010005);浙江省自然科学基金资助项目(LY17F010005);宁波市自然科学基金资助项目(2015A610127);宁波市自然科学基金资助项目(2015A610124);宁波大学科研基金(理)/学科基金资助项目(xkxl1502)
- DOI：10.11959/j.issn.1000-436x.2016235
  中图分类号： TN919.81
- 网络出版日期：2016-11，
  
  纸质出版日期：2016-11-25
- 稿件说明：
移动端阅览
刘晟, 彭宗举, 陈嘉丽, 等. 基于多类支持向量机的3D-HEVC深度视频帧内编码快速算法[J]. 通信学报, 2016,37(11):181-188.

Sheng LIU, Zong-ju PENG, Jia-li CHEN, et al. Multi-class support vector machine-based fast algorithm for 3D-HEVC depth video intra coding[J]. Journal on communications, 2016, 37(11): 181-188.
刘晟, 彭宗举, 陈嘉丽, 等. 基于多类支持向量机的3D-HEVC深度视频帧内编码快速算法[J]. 通信学报, 2016,37(11):181-188. DOI： 10.11959/j.issn.1000-436x.2016235.

Sheng LIU, Zong-ju PENG, Jia-li CHEN, et al. Multi-class support vector machine-based fast algorithm for 3D-HEVC depth video intra coding[J]. Journal on communications, 2016, 37(11): 181-188. DOI： 10.11959/j.issn.1000-436x.2016235.

摘要

深度视频编码中最优深度划分和模式选择过程具有非常高的计算复杂度。提出了基于多类支持向量机(MSVM

multi-class support vector machine)的深度视频帧内编码快速算法。该算法包括离线模型训练和快速编码2个部分。在离线模型训练中，用深度视频最大编码单元(LCU

largest coding unit)的最优划分深度作为标签，当前LCU的空域复杂度、空域相邻LCU的最优划分深度和彩色视频对应LCU的最优划分深度作为特征去构造MSVM模型。在编码时，提取LCU的特征，根据MSVM模型得到划分深度的预测值。根据该预测值提前终止编码单元递归划分和模式选择过程。实验结果表明，提出的算法在几乎不影响虚拟视点质量的情况下，平均节省35.91%的总体编码时间和40.04%的深度编码时间。

Abstract

The recursive splitting process of largest coding unit (LCU) and the mode search process of coding unit imposed enormous computational complexity on encoder. A multi-class support vector machine-based (MSVM) fast coding unit (CU) size decision algorithm for 3D-HEVC depth video intra-coding was proposed. The algorithm included two steps: off-line training and fast CU size and mode decision. In the process of off-line training

a MSVM model was constructed

where the texture complexity of current LCU

the optimal partition depth of its spatial neighboring LCU and co-located LCU in texture video were treated as feature vectors

and the optimal partition depth of LCU was utilized as corresponding class label. In the process of fast CU size and mode decision

features of LCU were extracted before cod-ing a LCU

then

a MSVM model was used to predict the class label. Finally

the class label that represents the largest parti-tion depth of the current LCU was employed to terminate the CU recursive splitting process and CU mode search process. Experimental results show that the proposed algorithm saves the encoding time of 3D-HEVC by 35.91% on average

and the encoding time of depth video by 40.04% on average

with negligible rendered virtual view image degradation.

关键词

Keywords

references

MÜLLER K , MERKLE P , WIEGAND T . 3-D video representation using depth maps [J ] . Proceedings of the IEEE , 2011 , 99 ( 4 ): 643 - 656 .

FEHN C . Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV [C ] // Electronic Imaging 2004. International Society for Optics and Photonics , 2004 : 93 - 104 .

TANIMOTO M , FUJII T , SUZUKI K . View synthesis algorithm in view synthesis reference software 2.0 (VSRS2.0) [S ] . ISO/IEC JTC1/SC29/WG11 M , 2009 , 16090 .

OHM J R . Overview of 3D video coding standardization [C ] // Proc of Three Dimensional Systems and Applications . 2013 : 1 - 4 .

SULLIVAN G J , OHM J R , HAN W J , et al . Overview of the high efficiency video coding (HEVC) standard [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2012 , 22 ( 12 ): 1649 - 1668 .

MULLER K R , SCHWARZ H , MARPE D , et al . 3D high-efficiency video coding for multi-view video and depth data [J ] . IEEE Transac-tions on Image Processing , 2013 , 22 ( 9 ): 3366 - 3378 .

MERKLE P , BARTNI C , MÜLLER K , et al . 3D video: depth coding based on inter-component prediction of block partitions [C ] // Picture Coding Symposium (PCS), 2012. IEEE , 2012 : 149 - 152 .

沈燕飞，李锦涛，朱珍民，等．高效视频编码 [J ] . 计算机学报 , 2013 , 36 ( 11 ): 2341 - 2355 .

SHEN Y F , LI J T , ZHU Z M , et al . High efficiency video coding [J ] . Chinese Journal of Computers , 2013 , 36 ( 11 ): 2341 - 2355 .

PAN Z , KWONG S , SUN M T , et al . Early MERGE mode decision based on motion estimation and hierarchical depth correlation for HEVC [J ] . IEEE Transactions on Broadcasting , 2014 , 60 ( 2 ): 405 - 412 .

CHIANG J C , CHEN W C , LIU L M , et al . A fast H. 264/AVC-based stereo video encoding algorithm based on hierarchical two-stage neu-ral classification [J ] . IEEE Journal of Selected Topics in Signal Proc-essing , 2011 , 5 ( 2 ): 309 - 320 .

CORREA G , ASSUNCAO P , AGOSTINI L V , et al . Fast HEVC encoding decisions using data mining [J ] . IEEE Transactions on Cir-cuits and Systems for Video Technology , 2015 , 25 ( 4 ): 660 - 673 .

SHEN L , AN P , ZHANG Z , et al . A 3D-HEVC fast mode decision algorithm for real-time applications [J ] . ACM Transactions on Multi-media Computing, Communications, and Applications (TOMM) , 2015 , 11 ( 3 ): 34 .

ZHANG Q , CHEN M , HUANG X , et al . Low-complexity depth map compression in HEVC-based 3D video coding [J ] . EURASIP Journal on Image and Video Processing, 2015 , 2015 ( 1 ): 1 - 14 .

PARK C S . Edge-based intra mode selection for depth-map coding in 3D-HEVC [J ] . IEEE Transactions on Image Processing , 2015 , 24 ( 1 ): 155 - 162 .

GU Z , ZHENG J , LING N , et al . Fast bi-partition mode selection for 3D HEVC depth intra coding [C ] // 2014 IEEE International Confer-ence on Multimedia and Expo (ICME) . 2014 : 1 - 6 .

SANCHEZ G , SALDANHA M , BALOTA G , et al . DMM fast: a complexity reduction scheme for three-dimensional high-efficiency video coding intra frame depth map coding [J ] . Journal of Electronic Imaging , 2015 , 24 ( 2 ): 023011 .

GU Z , ZHENG J , LING N , et al . Fast depth modeling mode selection for 3D HEVC depth intra coding [C ] // 2013 IEEE International Con-ference on Multimedia and Expo Workshops (ICMEW) . 2013 : 1 - 4 .

LEI J , LI S , ZHU C , et al . Depth coding based on depth-texture motion and structure similarities [J ] . IEEE Transactions on Circuits and Sys-tems for Video Technology , 2015 , 25 ( 2 ): 275 - 286 .

SHEN L , AN P , LIU Z , et al . Low complexity depth coding assisted by coding information from color video [J ] . IEEE Transactions on Broad-casting , 2014 , 60 ( 1 ): 128 - 133 .

LEI J , SUN J , PAN Z , et al . Fast mode decision using inter-view and inter-component correlations for multiview depth video coding [J ] . IEEE Transactions on Industrial Informatics , 2015 , 11 ( 4 ): 978 - 986 .

SCHÖLKOPF B , BURGES C J C . Advances in kernel methods: sup-port vector learning [M ] . MIT Press , 1999 .

张学工 . 关于统计学习理论与支持向量机 [J ] . 自动化学报 , 2000 , 26 ( 1 ): 32 - 42 .

ZHANG X G . Introduction to statistical learning theory and support vector machines [J ] . Acta Automatica Sinica , 2000 , 26 ( 1 ): 32 - 42 .

SHEN X , YU L . CU splitting early termination based on weighted SVM [J ] . EURASIP Journal on Image and Video Processing , 2013 ( 1 ): 1 - 11 .

MÜLLER K , VETRO A . Common test conditions of 3DV core ex-periments [C ] // JCT3V meeting, JCT3VG1100 . 2014 .

BJONTEGARDB G . Calculation of average PSNR differences be-tween RD-curves [R ] . Austin: Video Coding Experts Group . 2001 .

浏览量

683

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于纹理平滑度的视点合成失真优化快速算法