Three-Dimensional Data Registration Based on Human Perception

Abstract

Registration, the process of transforming different sets of data into a common coordinate system, is often required to allow the comparison or integration of the data sets. Techniques such as the widely used Iterative Closest Point (ICP) algorithm have limited effectiveness on data sets that require significant transformation or that have large degrees of inconsistencies. This paper describes a biologically inspired algorithm for data registration that is based on two theories of human perception. The use of macro level registration based on these theories combined with micro level registration using the ICP algorithm provides enhanced registration of these challenging data sets. The new algorithm was tested extensively on simulated sensor images in several scenarios key to successful application to autonomous ground navigation. The excellent performance of the biologically inspired algorithm in these cases makes it a promising candidate for this field.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2006
Accession Number
ADA511131

Entities

People

  • Bruce Brendle

Organizations

  • Tank-automotive and Armaments Command

Tags

Communities of Interest

  • Biomedical
  • Sensors

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Autonomous Navigation
  • Coordinate Systems
  • Data Sets
  • Dead Reckoning
  • Detectors
  • Diagnostic Imaging
  • Image Processing
  • Image Registration
  • Laser Radar
  • Navigation
  • Perception
  • Standards
  • Three Dimensional
  • Translations
  • Unmanned Vehicles

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Geodesy
  • Sensor Fusion and Tracking Systems.