Kinematics of Image Flows,

Abstract

This study concerns a new formulation and method for solution of the image flow problem. It is relevant to the maneuvering of a robotic system through an environment containing other moving objects and/or terrain. The tow-dimensional image flow is generated by the relative rigid body motion of a smooth, textured object along the line of sight to a monocular camera. By analyzing this evolving image sequence, one hopes to extract the instantaneous motion (described by six degrees of freedom) and local structure (slopes and curvatures) of the object along the line of sight. The formulation relates a new local representation of an image flow to object motion and structure by twelve nonlinear, algebraic equations. The representation parameters, termed observables, are given by the two components of image velocity, three components of rate-of-strain, spin, and six independent image gradients of rate-of-strain and spin, evaluated at the point on the line of sight. This representation is motivated by the deformation of a finite element of flowing continuum. A method for solving these equations was devised and successfully implemented on a VAX-750 computer. A number of examples were explored revealing two classes of ambiguous scenes (i.e., nonunique solutions are obtained). A sensitivity analysis was also begun in order to estimate noise levels in the representation parameters which still yield acceptable solutions. Estimates of computing time required for this approach to image flow analysis indicate that real-time implementation is not out of the question. (Author)

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1983
Accession Number
ADP001205

Entities

People

  • Allen M. Waxman

Organizations

  • University of Maryland

Tags

DTIC Thesaurus Topics

  • Computers
  • Curvature
  • Environment
  • Equations
  • Geometric Forms
  • Geometry
  • Kinematics
  • Line Of Sight
  • Lines (Geometry)
  • Mathematics
  • Sensitivity
  • Sequences
  • Virginia
  • Workshops

Readers

  • Computational Fluid Dynamics (CFD)
  • Computer Vision.
  • Finite Element Method (FEM) for solving Partial Differential Equations (PDEs)

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • Autonomy