Multibody Structure-from-Motion in Practice

被引:72
|
作者
Ozden, Kemal Egemen [1 ]
Schindler, Konrad [2 ]
Van Gool, Luc [1 ]
机构
[1] Katholieke Univ Leuven, EAST PSI VISICS, B-3001 Heverlee, Belgium
[2] Tech Univ Darmstadt, Dept Comp Sci, D-64289 Darmstadt, Germany
基金
美国国家科学基金会;
关键词
Structure-from-motion; motion segmentation; scale ambiguity; model selection; affine degeneracy; INDEPENDENTLY MOVING-OBJECTS; STRUCTURE-AND-MOTION; MODEL-SELECTION;
D O I
10.1109/TPAMI.2010.23
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multibody structure from motion (SfM) is the extension of classical SfM to dynamic scenes with multiple rigidly moving objects. Recent research has unveiled some of the mathematical foundations of the problem, but a practical algorithm which can handle realistic sequences is still missing. In this paper, we discuss the requirements for such an algorithm, highlight theoretical issues and practical problems, and describe how a static structure-from-motion framework needs to be extended to handle real dynamic scenes. Theoretical issues include different situations in which the number of independently moving scene objects changes: Moving objects can enter or leave the field of view, merge into the static background (e. g., when a car is parked), or split off from the background and start moving independently. Practical issues arise due to small freely moving foreground objects with few and short feature tracks. We argue that all of these difficulties need to be handled online as structure-from-motion estimation progresses, and present an exemplary solution using the framework of probabilistic model-scoring.
引用
收藏
页码:1134 / U24
页数:8
相关论文
共 50 条
  • [31] Reliable structure-from-motion for image pairs
    Zuverlässiges Structure-From-Motion für Bildpaare
    Cheremukhin, S. (Sergey.Cheremukhin@FernUni-Hagen.de), 1600, Springer Verlag (36):
  • [32] Refractive Structure-from-Motion on Underwater Images
    Jordt-Sedlazeck, Anne
    Koch, Reinhard
    2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2013, : 57 - 64
  • [33] STRUCTURE-FROM-MOTION UNDER ORTHOGRAPHIC PROJECTION
    HARRIS, C
    IMAGE AND VISION COMPUTING, 1991, 9 (05) : 329 - 332
  • [34] A new theory of structure-from-motion perception
    Fernandez, Julian M.
    Farell, Bart
    JOURNAL OF VISION, 2009, 9 (11):
  • [35] Surface interpolation in structure-from-motion displays
    Bocheva, N.
    PERCEPTION, 1996, 25 : 123 - 123
  • [36] Global Structure-from-Motion by Similarity Averaging
    Cui, Zhaopeng
    Tan, Ping
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 864 - 872
  • [37] Segmentation in structure-from-motion: a computational approach
    Rubin, N.
    Caudek, C.
    PERCEPTION, 1998, 27 : 110 - 110
  • [38] Optimizing the Viewing Graph for Structure-from-Motion
    Sweeney, Chris
    Sattler, Torsten
    Hollerer, Tobias
    Turk, Matthew
    Pollefeys, Marc
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 801 - 809
  • [39] A PARALLEL IMPLEMENTATION OF A STRUCTURE-FROM-MOTION ALGORITHM
    WANG, H
    BOWMAN, C
    BRADY, M
    HARRIS, C
    LECTURE NOTES IN COMPUTER SCIENCE, 1992, 588 : 272 - 276
  • [40] Outliers Handling in the Structure-from-Motion Algorithm
    Zhou, Haoyin
    Zhang, Tao
    2014 4TH IEEE INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND TECHNOLOGY (ICIST), 2014, : 164 - 167