ML Anthology

The Sensitivity of Motion and Structure Computations

John L. Barron, Allan D. Jepson, John K. Tsotsos
AAAI 1987 pp. 700-705
/aaai/1987/barron1987aaai-sensitivity/

Abstract

We address the problem of interpreting image velocity fields generated by a moving monocular observer viewing a stationary environment under perspective projection to obtain 3-D information about the relative motion of the observer (egomotion) and the rela-tive depth of environmental surface points (environmental layout). The algorithm presented in this paper involves computing motion and structure from a spatio-temporal distribution of image velocities that are hypothesized to belong to the same 3-D planar surface. However, the main result of this paper is not just another motion and structure algorithm that exhibits some novel features but rather an extensive error analysis of the algorithm’s preformance for various types of noise in the image velocities. Waxman and Ullman [83] have devised an algorithm for com-puting motion and structure using image velocity and its 1st and 2d

PDF AAAI Semantic Scholar

Cite

Text

Barron et al. "The Sensitivity of Motion and Structure Computations." AAAI Conference on Artificial Intelligence, 1987.

Markdown

[Barron et al. "The Sensitivity of Motion and Structure Computations." AAAI Conference on Artificial Intelligence, 1987.](https://mlanthology.org/aaai/1987/barron1987aaai-sensitivity/)

BibTeX

@inproceedings{barron1987aaai-sensitivity,
  title     = {{The Sensitivity of Motion and Structure Computations}},
  author    = {Barron, John L. and Jepson, Allan D. and Tsotsos, John K.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1987},
  pages     = {700-705},
  url       = {https://mlanthology.org/aaai/1987/barron1987aaai-sensitivity/}
}