National Tsing Hua University Institutional Repository:An accurate and adaptive optical flow estimation algorithm
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 54367/62174 (87%)
造访人次 : 14197669      在线人数 : 25
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTHU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻
    National Tsing Hua University Institutional Repository > 電機資訊學院 > 資訊工程學系 > 會議論文  >  An accurate and adaptive optical flow estimation algorithm


    题名: An accurate and adaptive optical flow estimation algorithm
    作者: Chin-Hung Teng
    Shang-Hong Lai
    Yung-Sheng Chen
    Wen-Hsing Hsu
    教師: 賴尚宏
    日期: 2004
    出版者: Institute of Electrical and Electronics Engineers Inc
    關聯: ICIP'04.2004 International Conference on Volume 3,24-27 Oct.2004, Page(s):1839-1842 Vol.3
    关键词: brightness
    conjugate gradient methods
    image sequences
    least squares approximations
    motion estimation
    摘要: In this paper we present a very accurate algorithm for computing optical flow with non-uniform brightness variations. The proposed algorithm is based on a generalized dynamic image model (GDIM) in conjunction with a regularization framework to cope with the problem of non-uniform brightness variations. To alleviate flow constraint errors due to image aliasing and noise, we employ a reweighted least-squares method to suppress unreliable flow constraints, thus leading to robust estimation of optical flow. In addition, a dynamic smoothness adjustment scheme is proposed to efficiently suppress the smoothness constraint in the vicinity of the motion and brightness variation discontinuities, thus preserving motion boundaries. To efficiently minimize the resulting energy function for optical flow computation, we apply an incomplete Cholesky preconditioned conjugate gradient algorithm to solve the large linear system. Experimental results on some synthetic and real image sequences show that the proposed algorithm outperforms most existing techniques reported in literature in terms of accuracy in optical flow computation with 100 % density.
    显示于类别:[資訊工程學系] 會議論文
    [資訊系統與應用研究所] 會議論文
    [電腦與通訊科技研發中心] 會議論文


    档案 描述 大小格式浏览次数
    2030227030009.pdf288KbAdobe PDF1281检视/开启


    SFX Query


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈