ML Anthology

Accurate Optical Flow in Noisy Image Sequences

Hagen Spies, Hanno Scharr
ICCV 2001 pp. 587-592
doi:10.1109/ICCV.2001.10088 /iccv/2001/spies2001iccv-accurate/

Abstract

Optical flow estimation in noisy image sequences requires a special denoising strategy. Towards this end we introduce a new tensor-driven anisotropic diffusion scheme which is designed to enhance optical-flow-like spatio-temporal structures. This is achieved by selecting diffusivities in a special manner depending on the eigenvalues of the well known structure tensor. We illustrate how the proposed choice differs from edge- and coherence-enhancing anisotropic diffusion. Furthermore we extend a recently discovered discretization scheme for anisotropic diffusion to 3D data. An automatic stop criterion to terminate the diffusion after a suitable time is given. The performance of the introduced method is examined quantitatively using image sequences with a substantial amount of noise added.

ICCV Semantic Scholar

Cite

Text

Spies and Scharr. "Accurate Optical Flow in Noisy Image Sequences." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.10088

Markdown

[Spies and Scharr. "Accurate Optical Flow in Noisy Image Sequences." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/spies2001iccv-accurate/) doi:10.1109/ICCV.2001.10088

BibTeX

@inproceedings{spies2001iccv-accurate,
  title     = {{Accurate Optical Flow in Noisy Image Sequences}},
  author    = {Spies, Hagen and Scharr, Hanno},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2001},
  pages     = {587-592},
  doi       = {10.1109/ICCV.2001.10088},
  url       = {https://mlanthology.org/iccv/2001/spies2001iccv-accurate/}
}