Pair-Wise Range Image Registration: A Study in Outlier Classification

Abstract

In this paper, we present a robustness study on several popular techniques for performing fine registration of partially overlapping 2.5D range image pairs, with a focus on model building. In our first set of tests, we qualitatively evaluate the output of several iterative closest point (ICP) variants on real-world data. Our second set of tests expands to include additional ICP variants and an implementation of Chen and Medioni s point-to-plane minimizing algorithm. These tests evaluate quantitatively how well these algorithm variants are able to correct initial simulated rigid rotation and translation errors. The aim of these variants in both sets of tests is to classify as outliers particular point pairs containing vertices outside of the region of overlap of the two range images. In addition to testing these variants with different parameter settings, we also study how performing topologically uniform subsampling of the meshes affects the registration quality.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 06, 2002
Accession Number
ADA597669

Entities

People

  • Gerald Dalley
  • Patrick J. Flynn

Organizations

  • Ohio State University

Tags

Communities of Interest

  • Air Platforms
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Autonomous Navigation
  • Classification
  • Computer Science
  • Computer Vision
  • Data Sets
  • Electrical Engineering
  • Electronic Mail
  • Engineering
  • Gaussian Noise
  • Heuristic Methods
  • Histograms
  • Image Registration
  • Images
  • Robot Navigation
  • Sampling
  • Test Beds

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Computer Vision.
  • Regression Analysis.