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
  • [21] Reliable structure-from-motion for image pairs [Zuverlässiges Structure-From-Motion für Bildpaare]
    Cheremukhin S.
    Informatik-Spektrum, 2013, 36 (4) : 382 - 388
  • [22] A tolerance analysis for structure-from-motion stimuli
    Hogervorst, M. A.
    Kappers, A. M. L.
    Koenderink, J. J.
    PERCEPTION, 1994, 23 : 37 - 38
  • [23] LiDAR-enhanced Structure-from-Motion
    Zhen, Weikun
    Hu, Yaoyu
    Yu, Huai
    Scherer, Sebastian
    2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2020, : 6773 - 6779
  • [24] Practical algorithms for stratified structure-from-motion
    Chen, GQ
    Medioni, GG
    IMAGE AND VISION COMPUTING, 2002, 20 (02) : 103 - 123
  • [25] STRUCTURE-FROM-MOTION BY TRACKING OCCLUSION BOUNDARIES
    THOMPSON, WB
    BIOLOGICAL CYBERNETICS, 1989, 62 (02) : 113 - 116
  • [26] Structure-From-Motion and RGBD Depth Fusion
    Chandrashekar, Akash
    Papadakis, John
    Willis, Andrew
    Gantert, Jamie
    IEEE SOUTHEASTCON 2018, 2018,
  • [27] STRUCTURE-FROM-MOTION UNDER ORTHOGRAPHIC PROJECTION
    HARRIS, C
    LECTURE NOTES IN COMPUTER SCIENCE, 1990, 427 : 118 - 123
  • [28] ROBUST AND ACCURATE HYBRID STRUCTURE-FROM-MOTION
    Li, Rui
    Gong, Dong
    Sun, Jinqiu
    Zhu, Yu
    Wei, Ziwei
    Zhang, Yanning
    2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 494 - 498
  • [29] Amblyopic deficits in processing structure-from-motion
    Husk, Jesse S.
    Farivar, Reza
    Hess, Robert F.
    JOURNAL OF VISION, 2012, 12 (04):
  • [30] Structure-From-Motion With Varying Principal Point
    Smith, W. A. P.
    Lewinska, P.
    Cooper, M. A.
    Hancock, E. R.
    Dowdeswell, J. A.
    Rippin, D. M.
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19