Dense Structure from a Dense Optical Flow Sequence.

Abstract

This paper presents a structure from motion system which delivers dense structure information from a sequence of dense optical flows. Most traditional feature based approaches cannot be extended to compute dense structure due to impractical computational complexity. We demonstrate that by decomposing uncertainty information into independent and correlated parts we can decrease these complexities from 0 (N2) to 0(N), where is the number of pixels in the images. We also show that this dense structure from motion system requires only local optical flows, i.e. image matchings between two adjacent frames, instead of the trucking of features over a long sequence of frames.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1995
Accession Number
ADA311290

Entities

People

  • Steven Arthur Shafer
  • Yalin Xiong

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Air Platforms
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Cameras
  • Computational Science
  • Computations
  • Coordinate Systems
  • Eigenvalues
  • Eigenvectors
  • Equations
  • Factor Analysis
  • Molecular Dynamics
  • Relative Motion
  • Sequences
  • Shape
  • Translations
  • Uncertainty
  • Video
  • Video Recording

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Graph Algorithms and Convex Optimization.