Edge Detection in Optical Flow Fields

Abstract

Optical flow is potentially valuable as a source of spatial information. Current techniques provide flow fields which are noisy and sparse, making the recovery of spatial properties difficult at best. This paper describes a technique for locating discontinuities in optical flow, which typically correspond to object boundaries. A simple blurring interpolator is used to smooth out noise and produce denser fields. Discontinuities are found by locating the vector field equivalent of zero crossings in the Laplacian of a scalar field. The technique is illustrated by applying it to realistic vector fields which are both noisy and sparse.

Cite

Text

Thompson et al. "Edge Detection in Optical Flow Fields." AAAI Conference on Artificial Intelligence, 1982.

Markdown

[Thompson et al. "Edge Detection in Optical Flow Fields." AAAI Conference on Artificial Intelligence, 1982.](https://mlanthology.org/aaai/1982/thompson1982aaai-edge/)

BibTeX

@inproceedings{thompson1982aaai-edge,
  title     = {{Edge Detection in Optical Flow Fields}},
  author    = {Thompson, William B. and Mutch, Kathleen M. and Berzins, Valdis},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1982},
  pages     = {26-29},
  url       = {https://mlanthology.org/aaai/1982/thompson1982aaai-edge/}
}