### Abstract

The authors first present an image-matching algorithm that uses multiple attributes associated with a pixel to yield a generally overdetermined system of constraints, taking into account possible structural discontinuities and occlusions. Both top-down and bottom-up data flows are used in a multiresolution computational structure. The matching algorithm computes dense displacement fields and the associated occlusion maps. The motion and structure parameters are estimated thorugh optimal estimation (e.g., maximal likelihood) using the solution of a linear algorithm as an initial guess. To investigate the intrinsic stability of the problem in the presence of noise, a theoretical lower bound on error variance of the estimates, the Cramer-Rao bound, is determined for motion parameters. Experiments showed that the performance of the proposed algorithm has essentially reached the bound. In addition, the bounds show that, intrinsically, motion estimation from two perspective views is a fairly stable problem if the image disparities are relatively large, but is unstable if the disparities are very small (as required by optical-flow approaches).

Original language | English (US) |
---|---|

Title of host publication | Proc Workshop Visual Motion |

Editors | Anon |

Pages | 359-366 |

Number of pages | 8 |

State | Published - Dec 1 1989 |

Event | Proceedings: Workshop on Visual Motion - Washington, DC, USA Duration: Mar 28 1989 → Mar 31 1989 |

### Publication series

Name | Proc Workshop Visual Motion |
---|

### Other

Other | Proceedings: Workshop on Visual Motion |
---|---|

City | Washington, DC, USA |

Period | 3/28/89 → 3/31/89 |

### ASJC Scopus subject areas

- Engineering(all)

## Fingerprint Dive into the research topics of 'Motion from images: image matching, parameter estimation and intrinsic stability.'. Together they form a unique fingerprint.

## Cite this

*Proc Workshop Visual Motion*(pp. 359-366). (Proc Workshop Visual Motion).