Nonlinear motion estimation using the supercoupling approach

被引：12
|
作者：
Bober, M [1 ]
Petrou, M [1 ]
Kittler, J [1 ]
机构：
[1] Univ Surrey, Sch Elect Engn Informat Technol & Math, Guildford GU2 5XH, Surrey, England
来源：
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1998年 / 20卷 / 05期
关键词：
motion analysis; motion segmentation; supercoupling approach; Markov random fields; stochastic relaxation;
D O I：
10.1109/34.682185
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents the application of a very efficient multiresolution transformation, which is related to the renormalization group approach of physics, to the problem of motion segmentation. The proposed approach is much faster and yields much better results than the full resolution approach. The problem is formulated as one of global optimization where a cost function is constructed to combine the information obtained by various processors as well as the constraints we impose to the problem. The cost function is optimized using the supercoupling multiresolution approach.
引用
收藏
页码：550 / 555
页数：6
相关论文
共 50 条
  • [1] Motion estimation using tangent distance
    Fabrizio, Jonathan
    Dubuisson, Severine
    2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7, 2007, : 489 - 492
  • [2] Global motion estimation combining with motion segmentation
    Zhao, Yaxiang
    Fan, Xiaoping
    Liu, Shaoqiang
    FIFTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2013), 2013, 8878
  • [3] Motion estimation using segmentation and consistency constraint
    Wang, DM
    Haighton, P
    Wang, LM
    Vincent, A
    VISUAL COMMUNICATIONS AND IMAGE PROCESSING '97, PTS 1-2, 1997, 3024 : 568 - 577
  • [4] A Joint Approach to Global Motion Estimation and Motion Segmentation from a Coarsely Sampled Motion Vector Field
    Chen, Yue-Meng
    Bajic, Ivan V.
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2011, 21 (09) : 1316 - 1328
  • [5] Motion estimation with quadtree splines
    Szeliski, R
    Shum, HY
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1996, 18 (12) : 1199 - 1210
  • [6] Motion estimation using modified dynamic programming
    Mozerov, M
    Kober, V
    Tchernykh, A
    Choi, TS
    OPTICAL ENGINEERING, 2002, 41 (10) : 2592 - 2598
  • [7] GENERAL-APPROACH TO BLOCK-MATCHING MOTION ESTIMATION
    SEFERIDIS, V
    GHANBARI, M
    OPTICAL ENGINEERING, 1993, 32 (07) : 1464 - 1474
  • [8] Stereo and motion correspondences using nonlinear optimization method
    Park, E
    Wohn, K
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2006, 101 (03) : 194 - 203
  • [9] Nonlinear Dance Motion Analysis and Motion Editing using Hilbert-Huang Transform
    Dong, Ran
    Cai, Dongsheng
    Asai, Nobuyoshi
    CGI'17: PROCEEDINGS OF THE COMPUTER GRAPHICS INTERNATIONAL CONFERENCE, 2017,
  • [10] ROBUST GLOBAL MOTION ESTIMATION USING MOTION VECTORS OF VARIABLE SIZE BLOCKS AND AUTOMATIC MOTION MODEL SELECTION
    Haller, Martin
    Krutz, Andreas
    Sikora, Thomas
    2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, : 737 - 740
12345