Qualitative Description of Camera Motion and Scene Depth from Histograms of Normal Flow

Abstract

If we histogram the normal flow vectors in images of a scene viewed by a moving observer, we can use the time varying histogram to derive qualitative information about the observer's motion; for example, whether it is (primarily) translational or rotational, and whether the direction of translation or axis of rotation is (roughly) parallel or perpendicular to the camera axis. This is illustrated using flow histograms obtained from a variety of real image sequences. If the motion is translational, qualitative information about the scene depth can also be obtained from the flow histograms; for example, whether the scene depth is unimodal or bimodal. This is illustrated for real scenes containing a layer of vegetation seen against a textured background, or two layers of vegetation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1998
Accession Number
ADA353730

Entities

People

  • Azriel Rosenfeld
  • Ehud Rivlin
  • Peter Cucka
  • Zoran Duric

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Air Platforms
  • Autonomy

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Collision Avoidance
  • Computer Science
  • Computer Vision
  • Detectors
  • Flow Fields
  • Ground Vehicles
  • Histograms
  • Image Processing
  • Observers
  • Pattern Recognition
  • Plants
  • Recognition
  • Sequences
  • Three Dimensional
  • Two Dimensional
  • Vegetation

Readers

  • Fluid Dynamics.
  • Image Processing and Computer Vision.
  • Statistical inference.