FEATURE POINT CORRESPONDENCE IN THE PRESENCE OF OCCLUSION

被引：83
|
作者：
SALARI, V
SETHI, IK
机构：
[1] Department of Computer Science, Wayne State University, Detroit
来源：
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1990年 / 12卷 / 01期
关键词：
Correspondence; Dynamic scenes; Motion; Occlusion; Smoothness of motion; Tracking;
D O I：
10.1109/34.41387
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Occlusion and poor feature point detection are two main difficulties in the use of multiple frames for establishing correspondence of feature points. A new formulation of the correspondence problem as an optimisation problem is discussed to handle these difficulties. Modifications to an existing iterative optimization procedure are discussed to solve the new formulation of the correspondence problem. Experimental results are presented to show the merits of the new formulation. © 1990 IEEE.
引用
收藏
页码：87 / 91
页数：5
相关论文
共 50 条
  • [1] Contrast-invariant feature point correspondence
    Li, Ping
    Farin, Dirk
    Gunnewiek, Rene Klein
    de With, Peter H. N.
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PTS 1-3, PROCEEDINGS, 2007, : 477 - +
  • [2] Feature point correspondence of stereo images by monogenic phase
    Takaya, Kunio
    2007 IEEE PACIFIC RIM CONFERENCE ON COMMUNICATIONS, COMPUTERS AND SIGNAL PROCESSING, VOLS 1 AND 2, 2007, : 268 - 271
  • [3] Establishing motion-based feature point correspondence
    Mehrotra, R
    PATTERN RECOGNITION, 1998, 31 (01) : 23 - 30
  • [4] Establishing motion-based feature point correspondence
    Eastman Kodak Co, Rochester, United States
    Pattern Recognit, 1 (23-30):
  • [5] Image-Based Visual Servoing With Unknown Point Feature Correspondence
    McFadyen, Aaron
    Jabeur, Marwen
    Corke, Peter
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2017, 2 (02): : 601 - 607
  • [6] Multi-scale sparse feature point correspondence by graph cuts
    ZHANG Hong 1
    2 Beijing Research Institute of Special Electromechanical Technology
    3 National Key Laboratory on Optical Features of Environment and Target
    ScienceChina(InformationSciences), 2010, 53 (06) : 1224 - 1232
  • [7] Multiscale Point Correspondence Using Feature Distribution and Frequency Domain Alignment
    Zhao, Zeng-Shun
    Feng, Xiang
    Teng, Sheng-Hua
    Li, Yi-Bin
    Zhang, Chang-Shui
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2012, 2012
  • [8] Motion feature point correspondence based on target tracking and neural optimization
    Wang, Yaming
    Zhongguo Jixie Gongcheng/China Mechanical Engineering, 2001, 12 (11):
  • [9] Feature point correspondence between consecutive frames based on genetic algorithm
    Wang, Y.
    International Journal of Robotics and Automation, 2006, 21 (01) : 35 - 38
  • [10] Feature point correspondence between consecutive frames based on genetic algorithm
    Wang, Y
    INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION, 2006, 21 (01): : 35 - 38
12345