Scene Segmentation and Reasoning under Uncertainty

Abstract

Segmentation of range images has long been considered in computer vision as an important but extremely difficult problem. A new paradigm for the segmentation of range images into piecewise continuous patches is presented. Data aggregation is performed via model recovery in terms of variable-order bi- variate polynomials using iterative regression. All the recovered models are potential candidates for the final description of the data. Selection of the models is achieved through a maximization of quadratic Boolean problem.. The procedure can be adapted to prefer certain kinds of descriptions (one which describes more data points, or has smaller error, or has lower order model). They have developed a fast optimization procedure for model selection. The major novelty of the approach is in combining model extraction and model selection in a dynamic way. Partial recovery of the models is followed by the optimization (selection) procedure where only the best models are allowed to develop further. The results obtained in this way are comparable with the results obtained when using the selection module only after all the models are fully recovered, while the computational complexity is significantly reduced. The procedure was tested on several real range images.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 30, 1991
Accession Number
ADA248889

Entities

People

  • Ruzena Bajcsy

Organizations

  • Air Force Office of Scientific Research

Tags

Communities of Interest

  • Autonomy
  • Sensors

DTIC Thesaurus Topics

  • Applied Computer Science
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Computational Complexity
  • Computational Processes
  • Computer Science
  • Computer Vision
  • Computing-Related Activities
  • Decision Theory
  • Detectors
  • Identification
  • Information Science
  • Reasoning
  • Sensor Fusion
  • Statistical Decision Theory
  • Three Dimensional
  • Uncertainty

Readers

  • Neural Network Machine Learning.
  • Operations Research
  • Regression Analysis.

Technology Areas

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