ML Anthology

Fast Probabilisitic Estimation of Egomotion from Image Intensities

Jamil Draréni, Nicolas Martin, Sébastien Roy
CVPRW 2010 pp. 31-37
doi:10.1109/CVPRW.2010.5543796 /cvprw/2010/drareni2010cvprw-fast/

Abstract

This paper proposes a real-time probabilistic solution to the problem of camera motion estimation in a video sequence. Instead of using explicit tracking of features, it only uses instantaneous image intensity variations without prior estimation of optical flow. We represent the camera motion as a probability density which is constructed from the individual motion densities, estimated from spatio-temporal derivatives, of each pixel of the image. The density is formed by accumulating the contribution of each pixel, making it very robust to local perturbations in the image. A fast algorithm is proposed and experimental results show how real-time motion estimation is possible directly from the image stream with good precision.

CVPRW Semantic Scholar

Cite

Text

Draréni et al. "Fast Probabilisitic Estimation of Egomotion from Image Intensities." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010. doi:10.1109/CVPRW.2010.5543796

Markdown

[Draréni et al. "Fast Probabilisitic Estimation of Egomotion from Image Intensities." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010.](https://mlanthology.org/cvprw/2010/drareni2010cvprw-fast/) doi:10.1109/CVPRW.2010.5543796

BibTeX

@inproceedings{drareni2010cvprw-fast,
  title     = {{Fast Probabilisitic Estimation of Egomotion from Image Intensities}},
  author    = {Draréni, Jamil and Martin, Nicolas and Roy, Sébastien},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2010},
  pages     = {31-37},
  doi       = {10.1109/CVPRW.2010.5543796},
  url       = {https://mlanthology.org/cvprw/2010/drareni2010cvprw-fast/}
}