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
  • [1] Theory and Practice of Structure-from-Motion using Affine Correspondences
    Raposo, Carolina
    Barreto, Joao P.
    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 5470 - 5478
  • [2] Learning Structure-from-Motion from Motion
    Pinard, Clement
    Chevalley, Laure
    Manzanera, Antoine
    Filliat, David
    COMPUTER VISION - ECCV 2018 WORKSHOPS, PT III, 2019, 11131 : 363 - 376
  • [3] Structure-from-Motion Revisited
    Schonberger, Johannes L.
    Frahm, Jan -Michael
    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 4104 - 4113
  • [4] DETECTION OF NONRIGIDITY IN STRUCTURE-FROM-MOTION
    JEON, K
    BRAUNSTEIN, ML
    HOFFMAN, DD
    INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 1995, 36 (04) : S361 - S361
  • [5] DETECTION OF SURFACES IN STRUCTURE-FROM-MOTION
    TURNER, J
    BRAUNSTEIN, ML
    ANDERSEN, GJ
    JOURNAL OF EXPERIMENTAL PSYCHOLOGY-HUMAN PERCEPTION AND PERFORMANCE, 1995, 21 (04) : 809 - 821
  • [6] Transformers in Unsupervised Structure-from-Motion
    Chawla, Hemang
    Varma, Arnav
    Arani, Elahe
    Zonooz, Bahram
    COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VISIGRAPP 2022, 2023, 1815 : 281 - 303
  • [7] THE FST STRUCTURE-FROM-MOTION ILLUSION
    BRADSHAW, MF
    FRISBY, JP
    MAYHEW, JEW
    PERCEPTION, 1988, 17 (03) : 418 - 418
  • [8] QUALITATIVE CONSTRAINTS FOR STRUCTURE-FROM-MOTION
    THOMPSON, WB
    PAINTER, JS
    CVGIP-IMAGE UNDERSTANDING, 1992, 56 (01): : 69 - 77
  • [9] A critique of structure-from-motion algorithms
    Oliensis, J
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2000, 80 (02) : 172 - 214
  • [10] A new structure-from-motion ambiguity
    Oliensis, J
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (07) : 685 - 700