Motion Representation with Acceleration Images

Abstract

Information of time differentiation is extremely important cue for a motion representation. We have applied first-order differential velocity from a positional information, moreover we believe that second-order differential acceleration is also a significant feature in a motion representation. However, an acceleration image based on a typical optical flow includes motion noises. We have not employed the acceleration image because the noises are too strong to catch an effective motion feature in an image sequence. On one hand, the recent convolutional neural networks (CNN) are robust against input noises.

Cite

Text

Kataoka et al. "Motion Representation with Acceleration Images." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-49409-8_3

Markdown

[Kataoka et al. "Motion Representation with Acceleration Images." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/kataoka2016eccv-motion/) doi:10.1007/978-3-319-49409-8_3

BibTeX

@inproceedings{kataoka2016eccv-motion,
  title     = {{Motion Representation with Acceleration Images}},
  author    = {Kataoka, Hirokatsu and He, Yun and Shirakabe, Soma and Satoh, Yutaka},
  booktitle = {European Conference on Computer Vision},
  year      = {2016},
  pages     = {18-24},
  doi       = {10.1007/978-3-319-49409-8_3},
  url       = {https://mlanthology.org/eccv/2016/kataoka2016eccv-motion/}
}