ML Anthology

Multi-Frame Infinitesimal Motion Model for the Reconstruction of (Dynamic) Scenes with Multiple Linearly Moving Objects

Amnon Shashua, Anat Levin
ICCV 2001 pp. 592-599
doi:10.1109/ICCV.2001.937680 /iccv/2001/shashua2001iccv-multi/

Abstract

We introduce new small-motion multi-frame equations applicable to the reconstruction of dynamic scenes in which points are allowed to move along straight-line paths with constant velocity. The motion equations apply to both static and dynamic points, thus prior segmentation is not necessary. We present a reconstruction algorithm of camera motion, scene structure, and point trajectories embedded into a multi-frame factorization principle which requires the minimum of 11 images and 7 points (out of which at feast 3 are dynamic).

PDF ICCV Semantic Scholar

Cite

Text

Shashua and Levin. "Multi-Frame Infinitesimal Motion Model for the Reconstruction of (Dynamic) Scenes with Multiple Linearly Moving Objects." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.937680

Markdown

[Shashua and Levin. "Multi-Frame Infinitesimal Motion Model for the Reconstruction of (Dynamic) Scenes with Multiple Linearly Moving Objects." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/shashua2001iccv-multi/) doi:10.1109/ICCV.2001.937680

BibTeX

@inproceedings{shashua2001iccv-multi,
  title     = {{Multi-Frame Infinitesimal Motion Model for the Reconstruction of (Dynamic) Scenes with Multiple Linearly Moving Objects}},
  author    = {Shashua, Amnon and Levin, Anat},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2001},
  pages     = {592-599},
  doi       = {10.1109/ICCV.2001.937680},
  url       = {https://mlanthology.org/iccv/2001/shashua2001iccv-multi/}
}