Structure from Motion: Beyond the Epipolar Constraint

被引:0
|
作者
Tomáš Brodský
Cornelia Fermüller
Yiannis Aloimonos
机构
[1] University of Maryland,Computer Vision Laboratory, Center for Automation Research
来源
International Journal of Computer Vision | 2000年 / 37卷
关键词
3D motion estimation; scene reconstruction; smoothing and discontinuity detection; depth variability constraint;
D O I
暂无
中图分类号
学科分类号
摘要
The classic approach to structure from motion entails a clear separation between motion estimation and structure estimation and between two-dimensional (2D) and three-dimensional (3D) information. For the recovery of the rigid transformation between different views only 2D image measurements are used. To have available enough information, most existing techniques are based on the intermediate computation of optical flow which, however, poses a problem at the locations of depth discontinuities. If we knew where depth discontinuities were, we could (using a multitude of approaches based on smoothness constraints) accurately estimate flow values for image patches corresponding to smooth scene patches; but to know the discontinuities requires solving the structure from motion problem first. This paper introduces a novel approach to structure from motion which addresses the processes of smoothing, 3D motion and structure estimation in a synergistic manner. It provides an algorithm for estimating the transformation between two views obtained by either a calibrated or uncalibrated camera. The results of the estimation are then utilized to perform a reconstruction of the scene from a short sequence of images.
引用
收藏
页码:231 / 258
页数:27
相关论文
共 50 条
  • [1] Structure from motion:: Beyond the epipolar constraint
    Brodsky, T
    Fermüller, C
    Aloimonos, Y
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2000, 37 (03) : 231 - 258
  • [2] Image correspondence from motion subspace constraint and epipolar constraint
    Sugimoto, Shigeki
    Takahashi, Hidekazu
    Okutomoi, Masatoshi
    COMPUTER VISION - ACCV 2007, PT II, PROCEEDINGS, 2007, 4844 : 384 - +
  • [3] Data driven structure-from-motion using the epipolar corridor constraint
    Steinbach, E
    Girod, B
    Chaudhuri, S
    VISUAL COMMUNICATIONS AND IMAGE PROCESSING '97, PTS 1-2, 1997, 3024 : 558 - 567
  • [4] Optimal motion estimation from multiview normalized epipolar constraint
    Vidal, R
    Ma, Y
    Hsu, S
    Sastry, S
    EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, 2001, : 34 - 41
  • [5] Estimating Relative Camera Motion from the Antipodal-Epipolar Constraint
    Lim, John
    Barnes, Nick
    Li, Hongdong
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (10) : 1907 - U188
  • [6] Motion estimation and compensation based on epipolar geometry constraint
    Wu, Chengke
    Yan, Yaoping
    Lu, Zhaoyang
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 1998, 26 (10): : 66 - 69
  • [7] Epipolar geometry estimation via RANSAC benefits from the oriented epipolar constraint
    Chum, O
    Werner, T
    Matas, J
    PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, 2004, : 112 - 115
  • [8] Radial distortion from epipolar constraint for rectilinear cameras
    Lehtola V.V.
    Kurkela M.
    Rönnholm P.
    Lehtola, Ville V. (ville.lehtola@iki.fi), 2017, MDPI (03)
  • [9] Robust estimation of multi-component motion in image sequences using the epipolar constraint
    Steinbach, E
    Chaudhuri, S
    Girod, B
    1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V: VOL I: PLENARY, EXPERT SUMMARIES, SPECIAL, AUDIO, UNDERWATER ACOUSTICS, VLSI; VOL II: SPEECH PROCESSING; VOL III: SPEECH PROCESSING, DIGITAL SIGNAL PROCESSING; VOL IV: MULTIDIMENSIONAL SIGNAL PROCESSING, NEURAL NETWORKS - VOL V: STATISTICAL SIGNAL AND ARRAY PROCESSING, APPLICATIONS, 1997, : 2689 - 2692
  • [10] EPIPOLAR-PLANE IMAGE-ANALYSIS - AN APPROACH TO DETERMINING STRUCTURE FROM MOTION
    BOLLES, RC
    BAKER, HH
    MARIMONT, DH
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 1987, 1 (01) : 7 - 55