Integration of geometric elements, Euclidean relations, and motion curves for parametric shape and motion estimation

Pierre Louis Bazin, Jean Marc Vézien

Research output: Contribution to journalArticlepeer-review

Abstract

This paper presents an approach to shape and motion estimation that integrates heterogeneous knowledge into a unique model-based framework. We describe the observed scenes in terms of structured geometric elements (points, line segments, rectangles, 3D corners) sharing explicitly Euclidean relationships (orthogonality, parallelism, colinearity, coplanarity). Camera trajectories are represented with adaptative models which account for the regularity of usual camera motions.Two different strategies of automatic model building lead us to reduced models for shape and motion estimation with a minimal number of parameters. These models increase the robustness to noise and occlusions, improve the reconstruction, and provide a high-level representation of the observed scene. The parameters are optimally computed within a sequential Bayesian estimation procedure that gives accurate and reliable results on synthetic and real video imagery.

Original languageEnglish (US)
Pages (from-to)1960-1976
Number of pages17
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume27
Issue number12
DOIs
StatePublished - Dec 2005

Keywords

  • Bayesian estimation
  • Constraint reconstruction
  • Geometric reduction
  • Geometric relations
  • Model selection
  • Model-based estimation
  • Motion modeling
  • Shape and motion recovery

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Integration of geometric elements, Euclidean relations, and motion curves for parametric shape and motion estimation'. Together they form a unique fingerprint.

Cite this