标题: | 多视点视讯产生、传输与分析---子计画三:机器学习方法于视讯编码与处理应用 Application of Machine Learning Approach to Video Coding and Processing |
作者: | 彭文孝 PENG WEN-HSIAO 国立交通大学资讯工程学系(所) |
关键字: | 机器学习;高效能视讯编码;精简描述子应用于视觉化搜寻;编码端 控制;视觉化搜寻;Machine Learning;High Efficiency Video Coding (HEVC);Compact Descriptors for Visual Search (CDVS);Encoder control;Visual Search |
公开日期: | 2014 |
摘要: | 国立交通大学资讯工程学系 计画名称: 机器学习方法于视讯编码与处理应用 计画主持人: 彭文孝(主持人) 经费来源: 行政院国家科学委员会 关键字: 机器学习、高效能视讯编码、精简描述子应用于视觉化搜寻、编码端 控制、视觉化搜寻 本子计昼利用机器学习(Machine Learning)为视讯编码与处理的应用设计高效能演 算法。近年来由于大量影像及影片资料的产生与取得变得容易,以往模型导向 (Model-based)在视讯编码与处理中存在的一些问题,可望用资料导向(Data-driven) 的方式来解决。又机器学习的方法非常适合处理资料导向的问题,因此本子计昼目标为 利用机器学习的方法,针对(1)高效能视讯编码(High Efficiency Video Coding, HEVC) 与(2)精简描述子应用在视觉化搜寻(Compact Descriptors for Visual Search, CDVS) 两项ISO/IEC MPEG与ITU-T VCEG正在开发的标准,为视讯编码及处理两项重要的多媒 体应用,设计高效能之演算法。前两年我们会参与HEVC及CDVS之标准制定会议。同时 计昼(1)第一年产生大量HEVC编码训练资料,以机器学习方法解决分群及参数估测问 题,完成HEVC编码端快速模式决策、快速位元率控制及快速编码工具参数产生之演算 法开发;(2)第二年解决目前CDVS资料库决定代表点的问题,使用机器学习方式分析并 设计更好的代表点选择演算法,以及使用机器学习的方法设计使用多种比对演算法之搭 配方式,达到更高的比对准确率;(3)第三年基于两项完成的标准,设计增进原有的演 算法效能之方法,以及改进演算法使其适用硬体设计。由于两项标准在两年内就会完 成,本子计昼发展之研究与演算法赶上标准的时程,将在随之而来的应用上具有重要的 影响力。 Department of Computer Science, National Chiao Tung University Proposal Title: Application of Machine Learning Approach to Video Coding and Processing Principle Investigator: Wen-Hsiao Peng (PI) Sponsor National Science Council Keywords: Machine Learning, High Efficiency Video Coding (HEVC), Compact Descriptors for Visual Search (CDVS), Encoder control, Visual Search This project aims at applying Machine Learning (ML) approaches to video coding and processing. Recently, production and acquisition of large amount of video/picture data become easier than before. Therefore some problems existing in the model-based video encoding and processing are expected to be solved by data-driven approaches. Since ML is good at dealing with data-driven problems, in this project we shall design highly efficient algorithms for video coding and processing via ML approaches. Our algorithms are based on two international standards being developed by ISO/IEC MPEG and ITU-T VCEG: (1) High Efficiency Video Coding (HEVC) and (2) Compact Descriptors for Visual Search (CDVS). In this 3-year project, we shall accomplish the following works.⑴ In the 1styear the ML approaches are applied to a large amount of data from HEVC compressed videos, trying to solve some difficult classification and parameter estimation problems. Those solutions will lead to the development of fast mode decision, fast rate control and fast parameter estimation, for the HEVC encoder control. (2) For the 2nd year, we study the problem of keypoint selection in the current design of CDVS database construction. ML approaches will be applied to analyze and develop a better keypoint selection algorithm. Moreover, we shall use the ML approach to develop a novel descriptor matching algorithm by merging several well-known matching methods, hoping to achieve higher matching accuracy. (3) Finally in the 3rd year we shall refine our algorithms and enhance them to be hardware-friendly. Furthermore, since HEVC and CDVS standards will be finalized within two years, we shall keep following the standard activities in the first two years. |
官方说明文件#: | NSC101-2221-E009-085-MY3 |
URI: | http://hdl.handle.net/11536/101833 https://www.grb.gov.tw/search/planDetail?id=8116563&docId=431287 |
显示于类别: | Research Plans |