A ROBUST OPTICAL FLOW COMPUTATION

被引:2
|
作者
Lu Zongqing Xie Weixin Pei Jihong (School of Electronic Engineering
机构
基金
中国国家自然科学基金;
关键词
Optical flow; Tensor; Brightness Constancy Model (BCM); Local Structure Constancy Model (LSCM);
D O I
暂无
中图分类号
TN929.1 [光波通信、激光通信];
学科分类号
0803 ;
摘要
This paper presents a new method for robust and accurate optical flow estimation.The sig- nificance of this work is twofold.Firstly,the idea of bi-directional scheme is adopted to reduce the model error of optical flow equation,which allows the second order Taylor’s expansion of optical flow equation for accurate solution without much extra computational burden;Secondly,this paper establishs a new optical flow equation based on LSCM (Local Structure Constancy Model) instead of BCM (Brightness Constancy Model),namely the optical flow equation does not act on scalar but on tensor-valued (ma- trix-valued) field,due to the two reason:(1) structure tensor-value contains local spatial structure information,which provides us more useable cues for computation than scalar;(2) local image structure is less sensitive to illumination variation than intensity,which weakens the disturbance of non-uniform illumination in real sequences.Qualitative and quantitative results for synthetic and real-world scenes show that the new method can produce an accurate and robust results.
引用
收藏
页码:635 / 641
页数:7
相关论文
共 50 条
  • [31] Variational optical flow computation in real time
    Bruhn, A
    Weickert, J
    Feddern, C
    Kohlberger, T
    Schnörr, C
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2005, 14 (05) : 608 - 615
  • [32] ON THE DETECTION OF MOTION AND THE COMPUTATION OF OPTICAL-FLOW
    DUNCAN, JH
    CHOU, TC
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (03) : 346 - 352
  • [33] Salient Feature Detection for Optical Flow Computation
    Yang, Jiaoru
    Wang, Rui
    Xu, Rui
    2016 IEEE CHINESE GUIDANCE, NAVIGATION AND CONTROL CONFERENCE (CGNCC), 2016, : 2473 - 2476
  • [34] Comparison of accumulative computation with traditional optical flow
    Fernandez-Caballero, Antonio
    Perez-Jimenez, Rafael
    Fernandez, Miguel A.
    Lopez, Maria T.
    KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS: KES 2007 - WIRN 2007, PT I, PROCEEDINGS, 2007, 4692 : 447 - +
  • [35] Evaluation of Efficient Methods for Optical Flow Computation
    Frey, Daniel
    Ulrich, Markus
    Hinz, Stefan
    PHOTOGRAMMETRIE FERNERKUNDUNG GEOINFORMATION, 2010, (01): : 5 - 16
  • [36] Optical Flow Computation with Locally Quadratic Assumption
    Kato, Tomoya
    Itoh, Hayato
    Imiya, Atsushi
    COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2015, PT I, 2015, 9256 : 223 - 234
  • [37] Optical flow computation using extended constraints
    DelBimbo, A
    Nesi, P
    Sanz, JLC
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 1996, 5 (05) : 720 - 739
  • [38] A VLSI System Architecture for Optical Flow Computation
    Bhattacharya, Koustav
    Venkataraman, Mahalingam
    Ranganathan, Nagarajan
    ISCAS: 2009 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-5, 2009, : 357 - 360
  • [39] Multiresolution Optical Flow Computation of Spherical Images
    Mochizuki, Yoshihiko
    Imiya, Atsushi
    COMPUTER ANALYSIS OF IMAGES AND PATTERNS: 14TH INTERNATIONAL CONFERENCE, CAIP 2011, PT 2, 2011, 6855 : 348 - 355
  • [40] A NONLINEAR FILTERING BASED OPTICAL FLOW COMPUTATION
    Lu Zongqing
    Liao Qingmin
    Pei Jihong
    INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS, 2009, 9 (01) : 121 - 132