Event Extraction Using Transportation of Temporal Optical Flow Fields

Abstract

In this paper, we develop a method to transform a sequence of images to a sequence of events. Optical flow, which is the vector fields of pointwise motion computed from monocular image sequences, describes pointwise motion in an environment. The method extracts the global smoothness and continuity of motion fields and detects collapses of the smoothness of the motion fields in long-time image sequences using transportation of the temporal optical flow field.

Cite

Text

Gotoh et al. "Event Extraction Using Transportation of Temporal Optical Flow Fields." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11024-6_52

Markdown

[Gotoh et al. "Event Extraction Using Transportation of Temporal Optical Flow Fields." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/gotoh2018eccvw-event/) doi:10.1007/978-3-030-11024-6_52

BibTeX

@inproceedings{gotoh2018eccvw-event,
  title     = {{Event Extraction Using Transportation of Temporal Optical Flow Fields}},
  author    = {Gotoh, Itaru and Hiraoka, Hiroki and Imiya, Atsushi},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {692-705},
  doi       = {10.1007/978-3-030-11024-6_52},
  url       = {https://mlanthology.org/eccvw/2018/gotoh2018eccvw-event/}
}