西安电子科技大学通信工程学院导师教师师资介绍简介-杨付正

删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

本站小编 Free考研考试/2021-06-27

基本信息
杨付正　
教授
硕士生/博士生导师
学科：通信与信息系统　
工作单位：通信工程学院

联系方式
通信地址：西安电子科技大学108信箱
电子邮箱：fzhyang@mail.xidian.edu.cn
办公电话：**
办公地点：老科技楼A202

个人简介
2000年7月获西安电子科技大学“通信工程”专业本科学位，2003年3月及2005年6月分别获西安电子科技大学“通信与信息系统专业”硕士及博士学位。2005年6月博士毕业后留校任教，2006年6月破格晋升为副教授，并于同年12月获硕士生研究生导师资格，2012年6月晋升为教授。2006年9月至2007年9月访问英国伦敦大学Queen Mary学院多媒体与视觉实验室，进行博士后研究。

主要研究方向
主要研究方向为人工智能、虚拟现实、全景视频、点云处理、光场处理、视频编码、视频质量评估、多媒体通信等。
主要合作对象包括华为、OPPO、阿里、小米、Google、三星、联永、高通等。
详细信息请见“科学研究”。

承担科研项目
目前研究团队承担的科研项目：
国家自然科学基金，提高多视点视频编码效率的技术研究（**），2008-2010。
国家自然科学基金，基于码流的网络视频无参考质量评估方法研究（**），2010-2012。
中芬国际合作项目，未来移动通信泛在业务与应用研究（2010DFB10570），2010-2012。
陕西自然科学基金，多视点视频压缩算法研究（SJ08F03），2008-2010。
XX公司合作项目， UMTS系统视频传输QoE研究，2011-2012。
XX公司合作项目，视频通信技术合作，2011-2013。
XX公司合作项目，HiMEMC 算法技术合作，2012-2014。
XX公司合作项目，多媒体质量评估及处理技术研究项目，2011-2013。
XX公司合作项目，高性能多帧图像融合方法研究与实现，2012-2013。
XX公司合作项目，HEVC编码算法/解码模型技术合作项目，2012-2014。
XX公司合作项目，VP9 Codec PV模型合作项目，2013-2014。
XX公司合作项目，QoE以及图象处理技术研究项目，2013-2015。
Google research project，Optimization for vp9 coder under computatioal complexity constraint, 2015-2016.
XX公司合作项目，VP9实时编码器优化项目，2014-2016。
XX公司合作项目，隔逐行电影源检测技术合作项目，2015-2016.
国家自然科学基金，通信生态系统中DASH视频业务QoE评估研究，2016-2020.
XX公司合作项目，视频通话MOS标准研究，2016-2017.
XX公司合作项目，VR编码与传输系统, 2017-2018.
XX公司合作项目，VR多视角QoE, 2017-2018.
XX公司合作项目，QUIC视频传输质量研究与空口优化技术, 2017-2018.
XX公司合作项目，vMOS ITU-T 标准化研究，2018-2019.
XX公司合作项目，六自由度VR, 2018-2020.
XX公司合作项目，vMOS（P.QUIT） ITU-T 标准化研究，2018-2020.
XX公司合作项目，VR体验标准化研究，2018-2020.
XX公司合作项目，未来视频标准技术合作项目，2019-2020.
XX公司合作项目，cloud VR用户体验智能评测系统，2019-2020
XX公司合作项目，基于视点追踪的VR视觉显示系统，2019-2020
XX公司合作项目，云VR系统平台，2020-2021
XX公司合作项目，Efficient Prediction between Chroma and Luma components for AV2，2020-2021
XX公司合作项目，基于深度学习的视频优化，2021-2022
XX公司合作项目，基于深度学习的联合率失真优化，2021-2022

研究方向
多媒体通信实验室属于ISN国家重点实验室，长期从事图像和视频编码、处理和多媒体通信研究。主要合作对象包括华为、OPPO、阿里、小米、Google、三星、高通、大唐、联永等。课题组和华为技术公司建立了长期合作关系，2005年成立了西电-华为多媒体通信联合实验室。
主要研究领域包括：视频采集、视频处理、视频压缩、视频传输、视频质量控制、视频播放等多媒体通信的所有环节。

目前重点研究方向：新一代视频压缩标准、基于深度学习的视频处理、虚拟现实VR
1、3DOF——360全景视频
360度全景视频是环绕某个中心点的球形视频，其原理如图2所示。在VR应用中，360视频以观看者为中心，利用HMD准确跟踪到观看者的头部运动信息，HMD实时显示360视频相应的视角区域，为观看者提供了360度的自由观看视角，使用户获得良好的临场感（Presence）体验。360度全景视频可以匹配用户的三个运动自由度（3DOF），如图3所示。

图2 360视频示意图
图3 3DOF
由于人眼视角的限制，同一时刻只能观看360视频的部分区域，因此观看视角优先的传输策略是360视频DASH的核心技术，即根据观看视角分区域下载360视频，从而有效地利用信道带宽。观看视角优先的360视频DASH系统如图4所示。服务器端首先将360视频投影变换为二维平面视频，然后分割成多个区域，对不同区域使用已有的视频压缩标准（如H.265/HEVC）进行编码，使每个区域都具有多个不同质量等级的编码数据，并将区域划分及质量等级等信息在MPD（Media Presentation Description）文件中进行标识。客户端首先通过获取MPD文件了解服务器端存储了哪些视频数据，进而根据信道带宽以及用户的观看行为选择合适的视频数据下载观看。

图4 观看视角优先的360视频DASH系统
相关具体研究方向:
（1）360全景视频映射变换

（2）360全景视频编码

（3）360全景视频渲染
（4）基于Tile的360全景视频传输
（5）360全景视频自适应下载

2、3DOF+
3DoF+ (3 Degrees of Freedom Plus)除了为用户提供三个维度旋转带来的视听体验效果外，还提供向前/向后、向左/向右、向上/向下三个位置维度在有限范围内的头部运动体验（不允许脚步走动）。借助混合现实MR头盔、轻型化HMD等显示设备，可以为用户提供具有立体视差、运动视差、不同角度光照具有变化效果的有限范围内互动3DoF+体验，增加用户的临场感（Presence）和沉浸感（Immersion）。图1给出3DoF+视点范围示意图以及视点范围内两个不同的视角视图，相比3DoF，3DoF+更符合人感知事物的真实过程。此外，3DoF+可以兼容MR/AR，具有广阔的发展前景。

由于采集和存储条件限制，无法获得任意视点内图像信息。采集过程往往会因位移、遮挡等原因造成信息的缺失。在这种情况下，如何有效利用已知视点预测出目标视点图像是3DoF+需要解决的一项重要问题。针对深度未知以及深度已知的场景，可以采用有效的技术手段对目标虚拟视点图像进行合成。

深度估计

虚拟视点合成

VR感知体验逐渐提升的三个阶段

3DoF+与3DoF以及6DoF之间的差异示意图。

3、6DOF——True3D、点云、光场
True3D技术
传统的stereoscopic 3D是利用左右眼之间的视差来让视觉系统产生立体感知的显示技术。与之相区别，True3D技术是一种具有物理景深的立体显示技术，也是多媒体通信与计算机视觉领域最新的研究方向。用户在体验过程中具有三个头部自由度和三个位置自由度（DOF，Degree of Freedom）, 可以通过与视觉场景的交互获得更好的临场感和沉浸感。True3D可通过点云重建、光场成像和全息投影等技术实现。目前，实验室已围绕点云、光场等6DOF场景的重要表现形式进行了大量研究，已在点云生成、点云压缩和光场成像等领域获得突出的研究成果。
True3D游戏场景
点云生成
点云是指包含了空间坐标、颜色等丰富信息的点的数据集，用于对三维物体和场景进行表示，主要通过三维扫描和基于二维影像的三维重建方式获取。实验室主要研究基于视觉传感器（如相机）的三维点云生成方法，已在视觉SLAM、SfM以及视觉信号与惯性传感器信号融合的点云重建等领域开展研究，提出多种高精度、低复杂度的点云重建算法。

三维重建
基于视觉信号的点云重建示意图
点云压缩
用以表示三维场景的点云数据通常具有数据体量大、数据结构零散等特点。研究高效的点云压缩编码算法成为了True3D领域的重要课题之一。点云压缩编码是去除点云几何、颜色信息的冗余量而获得小体积、高保真点云数据的过程。
目前正在参与最新的点云压缩编码标准GPCC，已有多项提案被接收。

VPCC

GPCC
光场成像
光场即空间中任意点发出的任意方向光线的集合。区别于传统成像技术，光场所包含的信息不再是简单的2D像素阵列，而是三维空间中的光线。由于光场包含了一定范围内三维场景中的所有信息，因此我们可以通过计算成像的方式获得不同景深、不同视点的视觉场景。
目前主要研究方向：光场相机的内外参标定、基于光场相机的三维重建。
利用光场成像技术实现的新视点合成和重聚焦过程示意图

内参标定
云VR
已经完成了端到端Cloud VR平台，包括游戏模块、服务器、客户端。
当前主要研究方向：基于视线追踪的云VR、云VR的体验质量监测、面向云VR的视频压缩。
Cloud VR
基于视点追踪的VR系统
4、基于深度学习的视频处理及编码
当前主要方向，基于深度学习的图像处理、视频质量优化、智能识别

质量增强：超分、去模糊、去雾等
基于深度学习的图像编码

基于AR的肝脏手术引导
传统研究方向
1、相机前处理
相机的前处理技术是保证拍摄视频高质量的关键，如自动聚焦、防抖。这款量产摄像机的关键前处理技术（自动白平衡、自动曝光、自动聚焦）是我们开发的。
2、相机后处理
相机的后处理技术可以大大提高相机的使用性能，背景行人去除可以轻松留念。

3、视频压缩
视频压缩可以有效降低视频的数据量，累计向ISO/ITU的视频压缩标准提出30多项标准化提案，2006年有两项提案被ISO/ITU的国际视频压缩标准H.264接收。目前正在参与新的国际标准VVC/H.266，有多项技术提案被接收。
目前的主要研究方向：VVC/H.266的率失真优化、快速算法，基于深度学习的图像、视频压缩。

264中被接收的方案
VVC/H.266标准中被接收的提案之一
4、视频质量监测
视频质量监测是保证视频通信质量的关键环节，在网络视频流的质量评估领域具有国际领先水平，核心技术被国际标准ITU-T P.1201、P.1203、G.1071采纳。
当前的主要研究方向：云VR的体验质量监测设备（黑边、时延、抖动等）、监测系统，VR临场感体验质量，VR渲染美学质量评价。
质量监测

VR临场感体验质量评价
Cloud VR 质量评测系统

学术论文
Jiarun Song;Fuzheng Yang;Wei Zhang;Wenjie Zou;Yuqun Fan;Peiyun Di, “A Fast FoV-Switching DASH System Based on Tiling Mechanism for Practical Omnidirectional Video Services,” IEEE Transactions on Multimedia, Dec. 2019.
Wenjie Zou;Wei Zhang;Jiarun Song;Fuzheng Yang;Patrick Le Callet, “A Novel Method for Assessing the Spatial Presence of Omnidirectional Videos: Comparing Virtual and Real World,” IEEE Access, 2019
Zhang, Wei; Zou, Wenjie;Yang, Fuzheng, Linking visual saliency deviation to image quality degradation: A saliency deviation-based image quality index, Signal Processing: Image Communication, 2019.7, 75: 168~177
Jing He, En-hui Yang, Fuzheng Yang, and Kehu Yang, “Adaptive quantization parameter selection for H.265/HEVC by employing inter-frame dependency,” IEEE Transactions on Circuits and Systems for Video Technology, vol.28, no. 12, pp. 3424– 3436, Dec. 2018.
Wenjie Zou,Fuzheng Yang,Shuai Wan, “Perceptual video quality metric for compression artefacts: from two-dimensional to omnidirectional,” IET Image Processing, 12(3), pp. 374–381, March 2018.
Wenjie Zou,Fuzheng Yang,Wei Zhang,Yi Li,Haoping Yu, “A Framework for Assessing Spatial Presence of Omnidirectional Video on Virtual Reality Device,” IEEE Access, pp. 44676–44684, vol.6, 2018.
W. Zou, F. Yang, J. Song, S. Wan, W. Zhang, H. R. Wu. “Event-based Perceptual Quality Assessment for HTTP-based Video Streaming with Playback Interruption,” IEEE Transaction on Multimedia, 20(6), 1475-1488, June. 2018.
Hui Yuan,Xuekai Wei, Fuzheng Yang,Jimin Xiao,Sam Kwong, “Cooperative bargaining game-based multiuser bandwidth allocation for dynamicAdaptive Streaming Over HTTP,” IEEE Trans. on Multimedia, 2018, 20(1), 183-197.
Jing He, Fuzheng Yang, “Efficient frame-level bit allocation algorithm for H.265/HEVC,” IET Image Processing, 11(4), pp 245-257, 2017/4.
Peng Ren, Fuzheng Yang, Wei Li, “Rate model considering inter-symbol dependency for HEVC inter-frame coding,” Signal Image and Video Processing, 11(4), pp 643-650, 2017/5.
Jiarun Song, Fuzheng Yang, Yicong Zhou, and Shan Gao, “Parametric Planning Model for Video Quality Evaluation of IPTV Services Combining Channel and Video Characteristics,” IEEE Trans. on Multimedia, 2017, 19(5), 1015-1029.
Wenjie Zou, Jiarun Song, and Fuzheng Yang, “Perceived Image Quality on Mobile Phones with Different Screen Resolution,”Mobile Information Systems, Volume2016(2016), Article ID**, 17 pages.
Jiarun Song, Fuzheng Yang, Yicong Zhou, Shuai Wan, Hong Ren Wu, QoE Evaluation of Multimedia Services Based on Audiovisual Quality and User Interest, IEEE Trans.on Multimedia,2016,18(3),444-457.
Jing He, Fuzheng Yang, and Yicong Zhou，“High-speed implementation of rate-distortion optimised quantisation for H.265/HEVC,” IET Image Processing, Volume 9, Issue 8, August 2015, p. 652 – 661
Jing He, Fuzheng Yang, “High-speed implementation of rate-distortion optimized quantization for H.264/AVC,” Signal, Image and Video Processing, vol.9, no.3, pp.543-551, MAR 2015
Jiarun Song, Fuzheng Yang, “No-reference video quality assessment model for distortion caused by packet loss in the real-time mobile video services,”Advances in Multimedia, v 2014, December 11, 2014
Honglei Su, Fuzheng Yang, “Content-adaptive bitstream-layer model for coding distortion assessment of H.264/AVC networked video,” Journal of visual communication and image representation, vol. 25, no. 5, pp. 1199-1208, July 2014.
Fuzheng Yang, Shuai Wan, “Bitstream-Based Quality Assessment for Networked Video - A Review,” IEEE Communications Magazine, vol 50, no.11, pp.203-209, Nov. 2012..（2011 IF：3.785）
Fuzheng Yang, Jiarun Song, Shuai Wan and Hong Ren Wu, “Content-adaptive packet-la[ant]yer model for quality assessment of networked video services,” IEEE Journal of Selected Topics in Signal Processing, vol.6, no. 6, Oct. 2012. （2011 IF：2.88）
Honglei Su, Fuzheng Yang, Jiarun Song, “Packet-la[ant]yer Quality Assessment for Networked Video,”International Journal of Computers, Communications & Control, no.3, Sep. 2012.
Fuzheng Yang, Liangliang Jiang, Xiao Li, “Real-time Quality Assessment for Voice over IP,”Concurrency and Computation: Practice and Experience, DOI: 10.1002/cpe.1907，2011
Xu Yang, Yilin Chang, Bingbing Li and Fuzheng Yang, “Adaptive Wiener Filter based Chrominance Up-Sampling Enhancement Method for Video Coding,” IEEE Transactions on Consumer Electronics,Vol.57, No. 4, 1851-1856, Nov. 2011
Peng Li, Yilin Chang, Nina Feng, and Fuzheng Yang, “A Cross-la[ant]yer Algorithm of Packet Scheduling and Resource Allocation for Multi-User Wireless Video Transmission,” IEEE Transactions on Consumer Electronics,Vol.57, No. 3, 1128-1134, Aug. 2011
Fuzheng Yang, and Shuai Wan, “Quality of experience measurement of 3G video services,”Recent Patents on Computer Science, vol. 4, no. 2, pp. 134-142, May 2011.
Hui Yuan, Yilin Chang, Junyan Huo, Fuzheng Yang, and Zhaoyang Lu, Model based Joint Bit Allocation between Texture Videos and Depth Maps for 3D Video Coding, IEEE Trans. CSVT, vol.21, no.4, pp:485-497, April 2011
Fuzheng Yang, Shuai Wan, Qingpeng Xie and Hong Ren Wu, “No-reference Quality Assessment for Networked Video via Primary Analysis of Bit-stream,” IEEE Trans. CSVT, vol.20, no. 11, pp.1544-1554, Nov. 2010.
Ming Li, Yilin Chang, Fuzheng Yang, Shuai Wan. Rate-Distortion Criterion Based Picture Padding for Arbitrary Resolution Video Coding Using H.264/MPEG-4 AVC, IEEE Trans. CSVT, vol.20, no. 9, pp. 1233-1241, Sep. 2010.
Nina Feng, Yilin Chang, Fuzheng Yang, Zhaoyang Lu, and Peng Li, “Picture-group-based priority sorting method for H.264/AVC video transmission over wireless channels,” Optical Engineering, Vol. 49, 080501(2010); doi:10.1117/1.**.
Fuzheng Yang, Shuai Wan, Yilin Chang and Qingpeng Xie, “Coding distortion assessment for streaming video,” Journal of Multimedia, vol. 5, no. 2, April, 2010.
Fuzheng Yang and Shuai Wan, “Spatial-temporal video quality assessment based on two-level temporal pooling, International Journal of Image and Graphics, vol.10, no. 4, Dec. 2010.
Shuai Wan, Fuzheng Yang, and Ebroul Izquierdo, “Lagrange multiplier selection in wavelet-based scalable video coding for quality scalability,” Signal Processing: Image Communication, vol. 24, no. 9, Oct. 2009.
Li Ming, Chang Yilin, Yang Fuzheng, ShuaiWan, SixinLin, and Lianhuan Xiong, “fr[ant]ame la[ant]yer rate control for H.264/AVC with hierarchical B-fr[ant]ames,” Signal Processing: Image Communication, vol. 24, no. 3, Mar. 2009.
Fuzheng Yang, Shuai Wan and Yilin. Chang, “A no-reference blocking artifact metric for B-DCT video”, Journal of Zhejiang University (Science), v 7, pp. 95-100, May 2006.
Fuzheng Yang, Shuai Wan, Yilin Chang et al. A novel objective no-reference metric for digital video quality assessment. IEEE Signal Processing Letters, 12(10), pp.685-689, 2005.
Fuzheng Yang, Shuai Wan and Yilin Chang, “Improved method for gradient-threshold edge detector based on HVS”, Lecture Notes in Computer Science, Dec. 2005, pp. 1051-1056.
Shuai Wan, Fuzheng Yang and Yilin Chang, “Error concealment for video transmission based on content adaptive block matching,” Lecture Notes in Computer Science, Dec. 2005, pp. 97-604.
Fuzheng Yang, Yilin Chang and S. Wan, “Gradient-threshold edge detection based on the human visual system”, Optical Engineering, vol. 44, no. 2, 2005.

标准提案
J.-Y. Huo, X.-W. Li, J.-L. Wang, Y.-Z. Ma, F.-Z. Yang, S. Wan, Y.-F. Yu, Y. Liu, “Non-CE3: Current luma related-CCLM (CCCLM)”, JVET-L0108, 12nd JVET Meeting: Macao, CN, 3–12 Oct. 2018.
J.-Y. Huo, J.-L. Wang, X.-Y. Chai, F.-Z. Yang, S. Wan, Y.-F. Yu, Y. Liu, “Non-CE3: (LM only) + (CCCLM) coding performance”, JVET-L0109, 12nd JVET Meeting: Macao, CN, 3–12 Oct. 2018.
J.-Y. Huo, X.-W. Li, X.-Y. Chai, J.-L. Wang, Y.-Z. Ma, F.-Z. Yang, S. Wan, Y.-F. Yu, Y. Liu, “CE3-related: Fixed Reference Samples Design for CCLM”, JVET-M0211, 13rd JVET Meeting: Marrakesh, MA, 9-18 January 2019. （进入核心实验）
Y.-Z. Ma, J.-L. Wang, X.-W. Li, J.-Y. Huo, F.-Z. Yang, S. Wan, Y.-F. Yu, Y. Liu, “CE3-related: Chroma intra candidates modification based on directional DM”, JVET-M0213, 13rd JVET Meeting: Marrakesh, MA, 9-18 January 2019.
Y.-Z. Ma, X.-W. Li, J.-L. Wang, J.-Y. Huo, F.-Z. Yang, S. Wan, Y.-F. Yu, Y. Liu, “CE3-related: Uniform chroma intra candidates modification based on DM”, JVET-M0214, 13rd JVET Meeting: Marrakesh, MA, 9-18 January 2019.
J.-Y. Huo, J.-L. Wang, X.-W. Li, Y.-Z. Ma, F.-Z. Yang, S. Wan, Y.-F. Yu, Y. Liu, “CE3-related: Chroma intra candidates modification based on non-directional DM”, JVET-M0258, 13rd JVET Meeting: Marrakesh, MA, 9-18 January 2019.
J.-Y. Huo, Y.-Z. Ma, F.-Z. Yang, X.-W. Li, J.-L. Wang, X.-Y. Chai, S. Wan, Y.-F. Yu, Y. Liu, “CE3: Offset-based reference sample reduction for CCLM (Tests 1.2.1 and 1.2.2)”, JVET-N0131, 14th JVET Meeting: Geneva, CH, 19–27 March 2019. （被H.266/VVC采纳）
J.-Y. Huo, J.-L. Wang, X.-W. Li, Y.-Z. Ma, W. Zhang, F.-Z. Yang, S. Wan, Y.-F. Yu, Y. Liu, “Non-CE3: Simplification of DC Prediction”, JVET-N0132, 14th JVET Meeting: Geneva, CH, 19–27 March 2019.
J.-Y. Huo, J.-L. Wang, X.-W. Li, Y.-Z. Ma, F.-Z. Yang, S. Wan, Y.-F. Yu, Y. Liu, “CE13-related: Integrated in-loop filter based on CNN”, JVET-N0133, 14th JVET Meeting: Geneva, CH, 19–27 March 2019. （进入核心实验）
J. Huo, Y. Ma, S. Wan, Y. Yu , M. Wang, K. Zhang, L. Zhang, H. Liu, J. Xu, Y. Wang, J. Li, S. Wang, W. Gao, “CE3-1.5: CCLM derived from four neighbouring samples”, JVET-N0271, 14th JVET Meeting: Geneva, CH, 19–27 March 2019. （被H.266/VVC采纳）
J.-Y. Huo, Y.-Z. Ma, X.-W. Li, F.-Z. Yang , S. Wan , Y.-F. Yu, Y. Liu , “Non-CE3: CCLM simplification”, JVET-O0320, 15th JVET Meeting: Gothenburg, SE, 3–12 July 2019.
J.-Y. Huo, Y.-Z. Ma, X.-W. Li, H.-X. Wang, F.-Z. Yang , S. Wan , Y.-F. Yu, Y. Liu , “Non-CE3: Removal of MIP mapping table”, JVET-O0321, 15th JVET Meeting: Gothenburg, SE, 3–12 July 2019. （被H.266/VVC采纳）
J.-Y. Huo , S. Wan, J.-K. Guo , Y.-Z. Ma, F.-Z. Yang , Y.-F. Yu, Y. Liu , “Non-CE3: Simplification of PDPC for chroma component”, JVET-O0322, 15th JVET Meeting: Gothenburg, SE, 3–12 July 2019.
J.-Y. Huo , S. Wan, J.-K. Guo , Y.-Z. Ma, H.-X. Wang, F.-Z. Yang , Y.-F. Yu, Y. Liu , “Non-CE3: Unification of shifting for MIP mode”, JVET-O0323, 15th JVET Meeting: Gothenburg, SE, 3–12 July 2019. （进入核心实验）
J.-Y. Huo , S. Wan, J.-K. Guo , Y.-Z. Ma, H.-X. Wang, F.-Z. Yang , Y.-F. Yu, Y. Liu , “Non-CE3: MIP Simplification”, JVET-O0324, 15th JVET Meeting: Gothenburg, SE, 3–12 July 2019.
J.-Y. Huo, Y.-Z. Ma, F.-Z. Yang , K. Kondo, M. Ikeda, T. Suzuki, S. Wan , Y.-F. Yu , “Non-CE3：Fixed downshifting for 8-bit MIP”, JVET-O1127, 15th JVET Meeting: Gothenburg, SE, 3–12 July 2019. （进入核心实验）
Wei Zhang, Sujun Zhang, Zexing Sun, Fuzheng Yang, yuanfang Yu, Yang Liu，“[G-PCC][CE13.2-related] An improvement for the uniform-geometry slice partition along the longest edge”，M49121, 127th MPEG Meeting: Gothenburg, SE, 3–12 July 2019. （被MPEG-PCC采纳）
Wei Zhang, Sujun Zhang, Lihui Yang, Na Dai, Fuzheng Yang, yuanfang Yu, Yang Liu，“[G-PCC][new proposal] The effect of RAHT transform order on the attribute coding performance”，M49126, 127th MPEG Meeting: Gothenburg, SE, 3–12 July 2019
J.-Y. Huo, H.-X. Wang, Y. Sun, Y.-Z. Ma, F.-Z. Yang, S. Wan, Y.-F. Yu, Y. Liu, “Non-CE3: MIP simplification”, JVET-P0136, 16th JVET Meeting: Geneva, CH, 2–12 Oct. 2019. （被H.266/VVC采纳）
J.-Y. Huo, H.-X. Wang, Y.-Z. Ma, F.-Z. Yang, S. Wan, Y.-F. Yu, Y. Liu, “Non-CE4: On coding of merge triangle index”, JVET-P0137, 16th JVET Meeting: Geneva, CH, 2–12 Oct. 2019.
Wei Zhang, Na Dai, Fuzheng Yang, Zexing Sun, Yuanfang Yu, Yang Liu, “[G-PCC]On RAHT transform order”, M50750, 128th MPEG Meeting: Geneva, CH, 6–12 Oct. 2019. （进入核心实验）
Junyan Huo, Haixin Wang, Yu Sun, Yanzhuo Ma, Fuzheng Yang, Shuai Wan, Yuanfang Yu, Yang Liu, “On fixed sW and fO in MIP”, JVET-Q0450, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020. （被H.266/VVC采纳）
Junyan Huo, Haixin Wang, Xinwei Li, Yanzhuo Ma, Fuzheng Yang, Shuai Wan, Yuanfang Yu, Yang Liu, “On mipSizeId modification for 8x8 blocks”, JVET-Q0451, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020.
Junyan Huo, Xinwei Li, Qihong Ran, Yanzhuo Ma, Fuzheng Yang, Shuai Wan, Yuanfang Yu, Yang Liu, “Modification of up-sampling in MIP”, JVET-Q0452, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020.
Junyan Huo, Wenhan Qiao, Xinwei Li, Yanzhuo Ma, Fuzheng Yang, Shuai Wan, Yuanfang Yu, Yang Liu, “Modification of LFNST for MIP coded block”, JVET-Q0453, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020.
Yanzhuo Ma, Qihong Ran, Ruipeng Qiu, Menglin Zhang, Junyan Huo, Fuzheng Yang, Shuai Wan, Yuanfang Yu, Yang Liu, “Non-CE4: reduced LUT for GEO blending weights generation”, JVET-Q0456, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020.
Junyan Huo, Shuai Wan, Xinwei Li, Haixin Wang, Fuzheng Yang, Yanzhuo Ma, Yuanfang Yu, Yang Liu, “Harmonization of JVET-Q0451 and JVET-Q0453 for MIP & LFNST design”, JVET-Q0582, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020.
Fuzheng Yang, Zexing Sun, Shuai Wan, Zhecheng Wang, Yuanfang Yu, Yang Liu, “[G-PCC][New proposal] A unification of Morton code LUTs”, M52300, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020.
Fuzheng Yang, Lihui Yang, Shuai Wan, Zexing Sun, Yuanfang Yu, Yang Liu, “[G-PCC][New proposal] A neighbour search method for predlift transform”, M52302, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020. （进入核心实验）
Fuzheng Yang, Zexing Sun, Shuai Wan, Lihui Yang, Yuanfang Yu, Yang Liu, “[G-PCC][New proposal] A content-adaptive LOD generation scheme combined with the neighbour search method in m52302”, M52303, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020. （进入核心实验）
Wei Zhang, Sujun Zhang, Honglei Su, Fuzheng Yang, Shuai Wan, “[G-PCC][New proposal] A bug fix of slice partition along the longest edge”, M52319, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020.（被MPEG-PCC采纳）
Wei Zhang, Shuai Wan, Zhecheng Wang, Yuanfang Yu, Yang Liu, “[G-PCC] EE13.14 report on geometry sub-nodes weighting for intra-prediction”, M52339, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020.
Wei Zhang, Na Dai, Fuzheng Yang, Zexing Sun, Yuanfang Yu, Yang Liu, “[G-PCC] CE13.26 Report On RAHT transform order”, M52340, 129th MPEG Meeting: Brussels, BE, 7–17 January 2020. （进入核心实验）
Junyan Huo, Wenhan Qiao, Haixin Wang, Yanzhuo Ma, Fuzheng Yang, Shuai Wan, Yuanfang Yu, Yang Liu, “Unified primary transform kernel for ISP mode”, JVET-R0345, 130th MPEG Meeting: by teleconference, 15–24 April 2020.
Yanzhuo Ma, Qihong Ran, Ruipeng Qiu, Haixin Wang, Junyan Huo, Fuzheng Yang, Shuai Wan, Yuanfang Yu, Yang Liu, “Simplified disLut for GPM”, JVET-R0366, 130th MPEG Meeting: by teleconference, 15–24 April 2020.
Yanzhuo Ma, Qihong Ran, Ruipeng Qiu, Menglin Zhang, Junyan Huo, Fuzheng Yang, Shuai Wan, Yuanfang Yu, Yang Liu, “Adjustment of shiftHor calculation in GPM”, JVET-R0367, 130th MPEG Meeting: by teleconference, 15–24 April 2020.
Yanzhuo Ma, Qihong Ran, Ruipeng Qiu, Junyan Huo, Fuzheng Yang, Shuai Wan, Yuanfang Yu, Yang Liu, “GPM merge list construction modification”, JVET-R0368, 130th MPEG Meeting: by teleconference, 15–24 April 2020.
Yanzhuo Ma, Qihong Ran, Ruipeng Qiu, Junyan Huo, Fuzheng Yang, Shuai Wan, Yuanfang Yu, Yang Liu, “Combination of JVET-R0367 and JVET-R0368 for GPM”, JVET-R0369, 130th MPEG Meeting: by teleconference, 15–24 April 2020.
Fuzheng Yang, Lihui Yang, Shuai Wan, Zexing Sun, Yuanfang Yu, Yang Liu, “CE13.6 report on neighbour search method for predlift transform”, M53330, 130th MPEG Meeting: by teleconference, 15–24 April 2020.（进入核心实验）
Fuzheng Yang, Zexing Sun, Shuai Wan, Lihui Yang, Yuanfang Yu, Yang Liu, “CE13.6 report on LoD generation scheme combined with NN search for predlift transform”, M53331, 130th MPEG Meeting: by teleconference, 15–24 April 2020. （进入核心实验）
Wei Zhang, Na Dai, Fuzheng Yang, Zexing Sun, Yuanfang Yu, Yang Liu, “CE13.26 report on RAHT transform order”, M53332, 130th MPEG Meeting: by teleconference, 15–24 April 2020. （被MPEG-PCC采纳）
Wei Zhang, Mary-Luc Champel, “[G-PCC][New] Planar coding improvement”, M53522, 130th MPEG Meeting: by teleconference, 15–24 April 2020.
Junyan Huo, Yanzhuo Ma, Shuai Wan, Zhecheng Wang, Lihui Yang, Yuanfang Yu, Yang Liu, “[G-PCC][New][CE13.31-related] A neighbour search method for spatial scalability”, M53860, 130th MPEG Meeting: by teleconference, 15–24 April 2020. （进入核心实验）

荣誉获奖

华为优秀合作方
点击网页顶部“添加栏目”可以添加其他栏目
把鼠标放在栏目标题处，尝试拖动栏目。

科研团队
学校宣传材料（到华为去！到西电来！！！）中“在2005年与华为成立了多媒体联合实验室”，即为我们团队。
团队教师
张伟博士副教授博导
霍俊彦博士副教授硕导
马彦卓博士副教授
宋佳润博士硕导
李鹏博士硕导
邹文杰博士硕导

博士研究生
硕士研究生

课程教学
目前本人承担的教学任务：
本科：计算机网络、视觉媒体通信
研究生：网络多媒体

招生要求
~~~~~~~~~~~~~~~~~~~~~~~~~~
关于研究生招生的信息：
~~~~~~~~~~~~~~~~~~~~~~~~~~
欢迎2022级保送生联系。
2021年3月
欢迎旁听《视觉媒体通信》了解相关研究方向，信远118，周五 1/2、3/4节

Profile
Fuzheng Yang
Professor
School of Telecommunications Engineering
Xidian University

Contact Information
Email: fzhyang@mail.xidian.edu.cn
Tel: 86 828

Introduction
Fuzheng Yangreceived the Ph.D. in Communication and Information System from Xidian University, Xi’an, China, in 2005. He is now a Professor in Xidian University. During 2006-2007, he served as a visiting scholar and postdoctoral researcher in Department of Electronic Engineering in Queen Mary, University of London.

Research Interests
1．Video coding: HEVC, 3DV, RDO, rate control.
2.Video quality assessment: ITU-T standards P.NAMS, P.NBAMS
3．Video processing: preprocessing and post processing for camera video.
4．QoE control for wireless video communications.

Research
Projects:
1. Video coding
2. Video quality assessment
3. QoE control of wireless communication

Papers
Fuzheng Yang, Shuai Wan, “Bitstream-Based Quality Assessment for Networked Video - A Review,” IEEE Communications Magazine, vol 50, no.11, pp.203-209, Nov. 2012..（2011 IF：3.785）
Fuzheng Yang, Jiarun Song, Shuai Wan and Hong Ren Wu, “Content-adaptive packet-layer model for quality assessment of networked video services,” IEEE Journal of Selected Topics in Signal Processing, vol.6, no. 6, Oct. 2012. （2011 IF：2.88）
Honglei Su, Fuzheng Yang, Jiarun Song, “Packet-layer Quality Assessment for Networked Video,”International Journal of Computers, Communications & Control, no.3, Sep. 2012.
Fuzheng Yang, Liangliang Jiang, Xiao Li, “Real-time Quality Assessment for Voice over IP,”Concurrency and Computation: Practice and Experience, DOI: 10.1002/cpe.1907，2011
Xu Yang, Yilin Chang, Bingbing Li and Fuzheng Yang, “Adaptive Wiener Filter based Chrominance Up-Sampling Enhancement Method for Video Coding,” IEEE Transactions on Consumer Electronics,Vol.57, No. 4, 1851-1856, Nov. 2011
Peng Li, Yilin Chang, Nina Feng, and Fuzheng Yang, “A Cross-Layer Algorithm of Packet Scheduling and Resource Allocation for Multi-User Wireless Video Transmission,” IEEE Transactions on Consumer Electronics,Vol.57, No. 3, 1128-1134, Aug. 2011
Fuzheng Yang, and Shuai Wan, “Quality of experience measurement of 3G video services,”Recent Patents on Computer Science, vol. 4, no. 2, pp. 134-142, May 2011.
Hui Yuan, Yilin Chang, Junyan Huo, Fuzheng Yang, and Zhaoyang Lu, Model based Joint Bit Allocation between Texture Videos and Depth Maps for 3D Video Coding, IEEE Trans. CSVT, vol.21, no.4, pp:485-497, April 2011
Fuzheng Yang, Shuai Wan, Qingpeng Xie and Hong Ren Wu, “No-reference Quality Assessment for Networked Video via Primary Analysis of Bit-stream,” IEEE Trans. CSVT, vol.20, no. 11, pp.1544-1554, Nov. 2010.
Ming Li, Yilin Chang, Fuzheng Yang, Shuai Wan. Rate-Distortion Criterion Based Picture Padding for Arbitrary Resolution Video Coding Using H.264/MPEG-4 AVC, IEEE Trans. CSVT, vol.20, no. 9, pp. 1233-1241, Sep. 2010.
Nina Feng, Yilin Chang, Fuzheng Yang, Zhaoyang Lu, and Peng Li, “Picture-group-based priority sorting method for H.264/AVC video transmission over wireless channels,” Optical Engineering, Vol. 49, 080501(2010); doi:10.1117/1.**.
Fuzheng Yang, Shuai Wan, Yilin Chang and Qingpeng Xie, “Coding distortion assessment for streaming video,” Journal of Multimedia, vol. 5, no. 2, April, 2010.
Fuzheng Yang and Shuai Wan, “Spatial-temporal video quality assessment based on two-level temporal pooling, International Journal of Image and Graphics, vol.10, no. 4, Dec. 2010.
Shuai Wan, Fuzheng Yang, and Ebroul Izquierdo, “Lagrange multiplier selection in wavelet-based scalable video coding for quality scalability,” Signal Processing: Image Communication, vol. 24, no. 9, Oct. 2009.
Li Ming, Chang Yilin, Yang Fuzheng, ShuaiWan, SixinLin, and Lianhuan Xiong, “Frame layer rate control for H.264/AVC with hierarchical B-frames,” Signal Processing: Image Communication, vol. 24, no. 3, Mar. 2009.
Fuzheng Yang, Shuai Wan and Yilin. Chang, “A no-reference blocking artifact metric for B-DCT video”, Journal of Zhejiang University (Science), v 7, pp. 95-100, May 2006.
Fuzheng Yang, Shuai Wan, Yilin Chang et al. A novel objective no-reference metric for digital video quality assessment. IEEE Signal Processing Letters, 12(10), pp.685-689, 2005.
Fuzheng Yang, Shuai Wan and Yilin Chang, “Improved method for gradient-threshold edge detector based on HVS”, Lecture Notes in Computer Science, Dec. 2005, pp. 1051-1056.
Shuai Wan, Fuzheng Yang and Yilin Chang, “Error concealment for video transmission based on content adaptive block matching,” Lecture Notes in Computer Science, Dec. 2005, pp. 97-604.
Fuzheng Yang, Yilin Chang and S. Wan, “Gradient-threshold edge detection based on the human visual system”, Optical Engineering, vol. 44, no. 2, 2005.
Jian Wang, Fuzheng Yang, Zhiqing Xie, and Shuai Wan, Evaluation on Perceptual Audiovisual Delay using Average Talkspurts and Delay, Proc. International Congress on Image and Signal Processing (CISP'10), Oct. 2010
Shuai Wan, Fuzheng Yang, Zhiqing Xie. Evaluation of Video Quality Degradation due to Packet Loss, Proc. ISPACS, Dec. 2010.
Shuai Wan, Fuzheng Yang; Xun Zhang; Chenglong Jiang, “Frame-loss Adaptive Temporal Pooling for Video Quality Assessment,” Proceedings of the SPIE Visual Communications and Image Processing 2010, v 7744, p 77440W (7 pp.), 2010.
Wei Li, Fuzheng Yang, Shuai Wan, “Quality assessment for networked speech based on active packet detection,” 2010 International Conference on Computer and Communication Technologies in Agriculture Engineering (CCTAE 2010), p 561-4, 2010.
Ming Li, Yilin Chang, Fuzheng Yang, Shuai Wan, “Quadratic curve based buffer management for H.264/AVC rate control,” Proceedings of the 2010 International Conference on Information and Automation (ICIA 2010), p 1763-8, 2010.
Ming Li, Yilin Chang, Fuzheng Yang, Shuai Wan, “Advanced technologies for high-performance video coding” 4th International Conference on Communications and Networking in China, CHINACOM 2009, p 499-503, 2009.
Ma Yanzhuo, Wan Shuai, Chang Yilin, and Yang Fuzheng, “Adaptive GOP structure based on motion coherence, The International Society for Optical Engineering,” Proc. Satellite Data Compression, Communication, and Processing, June 2009.
Fuzheng Yang, Shuai Wan, Yilin Chang and Qingpeng Xie, “Frame-rate adaptive temporal pooling for video quality assessment,” in Proc. Fourth International Workshop on Video Processing and Quality Metrics for Consumer Electronics, Scottsdale, US, Jan. 2009.
Fuzheng Yang, Shuai Wan, Yilin Chang and Qingpeng Xie, “Coding distortion assessment for streaming video,” in Proceeding of the International Conference on Visual Information Engineering 2008, Xi’an, China, July 2008.
Shuai Wan, Fuzheng Yang, Mingyi He and Ebroul Izquierdo, Rate distortion optimised motion estimation based on a general framework, in Proceeding of the International Conference on Visual Information Engineering 2008, Xi’an, China, July 2008.
Shuai Wan, Fuzheng Yang and Mingyi He, Gradient-threshold edge detection based on perceptually adaptive threshold selection, ICIEA 2008 , singapore, Jun. 2008
Ming Li, Yilin Chang, Shuai Wan, Fuzheng Yang, “Analysia of bit allocation of temporal scalability using hierarchical B frames,” in Proceeding of the International Conference on Visual Information Engineering 2008, Xi’an, China, July 2008.
Fuzheng Yang, Shuai Wan, and E. Izquierdo, “Lagrange multiplier selection for 3D wavelet based scalable video coding,” in Proceedings of the IEEE International Conference on Image Processing 2007, San Antonio, USA, Sep. 2007.
Fuzheng Yang, Shuai Wan and E. Izquierdo, “Optimised motion estimation for robust video coding in packet loss environment,” in Proceedings of the 8th International Workshop on Image Analysis for Multimedia Interactive Services, Santorini, Greece, June 2007.
Shuai Wan, E. Izquierdo, Fuzheng Yang and Yilin Chang, “End-to-End Rate-Distortion Optimized Motion Estimation”, in ProceedingInternational Conference on Image Processing 2006, Atlanta, USA, Oct. 2006.
Fuzheng Yang, Shuai Wan and Yilin Chang, “A no-reference blocking artifact metric for B-DCT video”, The 15th International Packet Video Workshop, Apr. 2006.
Fuzheng Yang, Shuai Wan and Yilin Chang, “Temporal error concealment based on content adaptive block matching”, in Proceeding the 25th Picture Coding Symposium, Apr. 2006.
Shuai Wan, Yilin Chang and Fuzheng Yang, “Frame-layer rate control for JVT video coding using improved rate-distortion model”, in Proceeding Visual Communications and Image Processing 2005, July 2005.

Honors
点击网页顶部“添加栏目”可以添加其他栏目
把鼠标放在栏目标题处，尝试拖动栏目。

Team
团队教师

博士研究生
硕士研究生

Teaching
Computer networking
Multimedia communication

Admission
~~~~~~~~~~~~~~~~~~~~~~~~~~
关于研究生招生的信息：
~~~~~~~~~~~~~~~~~~~~~~~~~~