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
  • [11] Perceptual segmentation in structure-from-motion
    Caudek, C.
    Rubin, N.
    PERCEPTION, 1998, 27 : 110 - 110
  • [12] SIZE CONSTANCY IN STRUCTURE-FROM-MOTION
    TURNER, J
    BRAUNSTEIN, ML
    PERCEPTION, 1995, 24 (10) : 1155 - 1164
  • [13] ACCURACY OF STRUCTURE-FROM-MOTION INTERPOLATION
    SAIDPOUR, A
    BRAUNSTEIN, ML
    HOFFMAN, DD
    INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 1991, 32 (04) : 1277 - 1277
  • [14] A generic structure-from-motion framework
    Ramalingam, Srikumar
    Lodha, Suresh K.
    Sturm, Peter
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2006, 103 (03) : 218 - 228
  • [15] Unified Underwater Structure-from-Motion
    Ichimaru, Kazuto
    Taguchi, Yuichi
    Kawasaki, Hiroshi
    2019 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2019), 2019, : 524 - 532
  • [16] Batched Incremental Structure-from-Motion
    Cui, Hainan
    Shen, Shuhan
    Gao, Xiang
    Hu, Zhanyi
    PROCEEDINGS 2017 INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2017, : 205 - 214
  • [17] Metamerisms in structure-from-motion perception
    van Veen, H. A. H. C.
    Werkhoven, P.
    Kappers, A. M. L.
    Koenderink, J. J.
    PERCEPTION, 1994, 23 : 38 - 38
  • [18] HSfM: Hybrid Structure-from-Motion
    Cui, Hainan
    Gao, Xiang
    Shen, Shuhan
    Hu, Zhanyi
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 2393 - 2402
  • [19] Metamerisms in structure-from-motion perception
    vanVeen, HAHC
    Werkhoven, P
    VISION RESEARCH, 1996, 36 (14) : 2197 - 2210
  • [20] Global Structure-from-Motion Revisited
    Pan, Linfei
    Barath, Daniel
    Pollefeys, Marc
    Schonberger, Johannes L.
    COMPUTER VISION - ECCV 2024, PT XL, 2025, 15098 : 58 - 77