ML Anthology

Robust Motion Analysis

Miroslaw Bober, Josef Kittler
CVPR 1994 pp. 947-952
doi:10.1109/CVPR.1994.323931 /cvpr/1994/bober1994cvpr-robust/

Abstract

We develop a new robust algorithm for the estimation of optic flow and extraction of other motion-relevant information. A novel combination of the Hough Transform, and robust statistical methods results in unbiased estimates for multiple motions, parallel segmentation and estimation and increased robustness to noise and changes of illumination. The algorithm is fast, due to application of multiresolution in both image and parameter space. A simple, translational motion model and a complex one coping with rotation and change of scale are applied. Also, an accuracy measure for the derived estimate is introduced. The paper includes experimental tests of this new approach and its comparison with several other widely-cited methods. The experiments were aimed at assessing the effect of noise, change of illumination and multiple motions on the algorithms performance. The results show that our approach is significantly more robust than other methods.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Bober and Kittler. "Robust Motion Analysis." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994. doi:10.1109/CVPR.1994.323931

Markdown

[Bober and Kittler. "Robust Motion Analysis." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994.](https://mlanthology.org/cvpr/1994/bober1994cvpr-robust/) doi:10.1109/CVPR.1994.323931

BibTeX

@inproceedings{bober1994cvpr-robust,
  title     = {{Robust Motion Analysis}},
  author    = {Bober, Miroslaw and Kittler, Josef},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1994},
  pages     = {947-952},
  doi       = {10.1109/CVPR.1994.323931},
  url       = {https://mlanthology.org/cvpr/1994/bober1994cvpr-robust/}
}