ZTE

ZTE Communications ›› 2016, Vol. 14 ›› Issue (1): 50-53.DOI: 10.3969/j.issn.1673-5188.2016.01.007

• Special Topic • Previous Articles     Next Articles

Introduction to AVS2 Scene Video Coding Techniques

Jiaying Yan1,2,3, Siwei Dong1,3, Yonghong Tian1,3, and Tiejun Huang1,3   

  1. 1. National Engineering Laboratory for Video Technology, School of EE & CS, Peking University, Beijing 100871, China;
    2. School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen 518055, China;
    3. Cooperative Medianet Innovation Center, Beijing 100871, China
  • Online:2016-02-01 Published:2019-11-27
  • About author:Jiaying Yan (yanjiaying@pku.edu.cn) received the BS degree from Beijing Institute of Technology, China in 2014. He is currently pursuing the MS degree with the School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, China. His research interests include surveillance video coding and multimedia learning. Siwei Dong (swdong@pku.edu.cn) received the B.S. degree from Chongqing University, China in 2012. He is currently pursuing the PhD degree with the School of Electronics Engineering and Computer Science, Peking University, China. His research interests include video coding and multimedia learning. Yonghong Tian (yhtian@pku.edu.cn) is currently a professor with the National Engineering Laboratory for Video Technology, School of Electronics Engineering and Computer Science, Peking University, China. He received the PhD degree from the Institute of Computing Technology, Chinese Academy of Sciences, China in 2005, and was also a visiting scientist at Department of Computer Science/Engineering, University of Minnesota, USA from November 2009 to July 2010. His research interests include machine learning, computer vision, video analysis and coding, and multimedia big data. He is the author or coauthor of over 110 technical articles in refereed journals and Conferences. Dr. Tian is currently an associate editor of IEEE Transactions on Multimedia, a young associate editor of the Frontiers of Computer Science, and a member of the IEEE TCMC-TCSEM Joint Executive Committee in Asia (JECA). He was the recipient of the Second Prize of National Science and Technology Progress Awards in 2010, the best performer in the TRECVID content-based copy detection (CCD) task (2010-2011), the top performer in the TRECVID retrospective surveillance event detection (SED) task (2009-2012), and the winner of the WikipediaMM task in ImageCLEF 2008. He is a senior member of IEEE and a member of ACM. Tiejun Huang (tjhuang@pku.edu.cn) is a professor with the School of Electronic Engineering and Computer Science, the chair of Department of Computer Science and the director of the Institute for Digital Media Technology, Peking University, China. His research areas include video coding and image understanding, especially neural coding inspired information coding theory in last years. He received the PhD degree in pattern recognition and intelligent system from the Huazhong (Central China) University of Science and Technology in 1998, and the master’s and bachelor’s degrees in computer science from the Wuhan University of Technology in 1995 and 1992, respectively. Professor Huang received the National Science Fund for Distinguished Young Scholars of China in 2014. He is a member of the Board of the Chinese Institute of Electronics, the Board of Directors for Digital Media Project and the Advisory Board of IEEE Computing Now.

Introduction to AVS2 Scene Video Coding Techniques

Jiaying Yan1,2,3, Siwei Dong1,3, Yonghong Tian1,3, and Tiejun Huang1,3   

  1. 1. National Engineering Laboratory for Video Technology, School of EE & CS, Peking University, Beijing 100871, China;
    2. School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen 518055, China;
    3. Cooperative Medianet Innovation Center, Beijing 100871, China
  • 作者简介:Jiaying Yan (yanjiaying@pku.edu.cn) received the BS degree from Beijing Institute of Technology, China in 2014. He is currently pursuing the MS degree with the School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, China. His research interests include surveillance video coding and multimedia learning. Siwei Dong (swdong@pku.edu.cn) received the B.S. degree from Chongqing University, China in 2012. He is currently pursuing the PhD degree with the School of Electronics Engineering and Computer Science, Peking University, China. His research interests include video coding and multimedia learning. Yonghong Tian (yhtian@pku.edu.cn) is currently a professor with the National Engineering Laboratory for Video Technology, School of Electronics Engineering and Computer Science, Peking University, China. He received the PhD degree from the Institute of Computing Technology, Chinese Academy of Sciences, China in 2005, and was also a visiting scientist at Department of Computer Science/Engineering, University of Minnesota, USA from November 2009 to July 2010. His research interests include machine learning, computer vision, video analysis and coding, and multimedia big data. He is the author or coauthor of over 110 technical articles in refereed journals and Conferences. Dr. Tian is currently an associate editor of IEEE Transactions on Multimedia, a young associate editor of the Frontiers of Computer Science, and a member of the IEEE TCMC-TCSEM Joint Executive Committee in Asia (JECA). He was the recipient of the Second Prize of National Science and Technology Progress Awards in 2010, the best performer in the TRECVID content-based copy detection (CCD) task (2010-2011), the top performer in the TRECVID retrospective surveillance event detection (SED) task (2009-2012), and the winner of the WikipediaMM task in ImageCLEF 2008. He is a senior member of IEEE and a member of ACM. Tiejun Huang (tjhuang@pku.edu.cn) is a professor with the School of Electronic Engineering and Computer Science, the chair of Department of Computer Science and the director of the Institute for Digital Media Technology, Peking University, China. His research areas include video coding and image understanding, especially neural coding inspired information coding theory in last years. He received the PhD degree in pattern recognition and intelligent system from the Huazhong (Central China) University of Science and Technology in 1998, and the master’s and bachelor’s degrees in computer science from the Wuhan University of Technology in 1995 and 1992, respectively. Professor Huang received the National Science Fund for Distinguished Young Scholars of China in 2014. He is a member of the Board of the Chinese Institute of Electronics, the Board of Directors for Digital Media Project and the Advisory Board of IEEE Computing Now.
  • 基金资助:
    This work is partial y supported by the National Basic Research Program of China under grant 2015CB351806, the National Natural Science Foundation of China under contract No.61425025, No.61390515 and No.61421062, and Shenzhen Peacock Plan

PDF

Abstract: The second generation Audio Video Coding Standard (AVS2) is the most recent video coding standard. By introducing several new coding techniques, AVS2 can provide more efficient compression for scene videos such as surveillance videos, conference videos, etc. Due to the limited scenes, scene videos have great redundancy especially in background region. The new scene video coding techniques applied in AVS2 mainly focus on reducing redundancy in order to achieve higher compression. This paper introduces several important AVS2 scene video coding techniques. Experimental results show that with scene video coding tools, AVS2 can save nearly 40% BD-rate (Bj?ntegaard?Delta bit-rate) on scene videos.

Key words: AVS2, scene videos coding, background prediction

摘要： The second generation Audio Video Coding Standard (AVS2) is the most recent video coding standard. By introducing several new coding techniques, AVS2 can provide more efficient compression for scene videos such as surveillance videos, conference videos, etc. Due to the limited scenes, scene videos have great redundancy especially in background region. The new scene video coding techniques applied in AVS2 mainly focus on reducing redundancy in order to achieve higher compression. This paper introduces several important AVS2 scene video coding techniques. Experimental results show that with scene video coding tools, AVS2 can save nearly 40% BD-rate (Bj?ntegaard?Delta bit-rate) on scene videos.

关键词: AVS2, scene videos coding, background prediction