Göm meny

Automatic Estimation of Epipolar Geometry from Blob Features

Per-Erik Forssén, Anders Moe
August 2004


This report describes how blob features can be used for automatic estimation of the fundamental matrix from two perspective projections of a 3D scene. Blobs are perceptually salient, homogeneous, compact image regions. They are represented by their average colour, area, centre of gravity and inertia matrix. Coarse blob correspondences are found by voting using colour and local similarity transform matching on blob pairs. We then do RANSAC sampling of the coarse correspondences, and weight each estimate according to how well the approximating conics and colours of two blobs correspond. The initial voting significantly reduces the number of RANSAC samples required, and the extra information besides position, allows us to reject false matches more accurately than in RANSAC using point features.

Full Paper

Portable document format file PDF ()

Bibtex entry

  author = 	 {Per-Erik Forss{\'e}n and Anders Moe},
  title = 	 {Automatic Estimation of Epipolar Geometry from Blob Features},
  institution =  {Dept. EE, Link\"oping University},
  year =         {2004},
  number =       {LiTH-ISY-R-2620},
  address =      {SE-581 83 Link\"oping, Sweden},
  month =        {August},

Per-Erik Forssén

Per-Erik Forssén


Computer Vision Laboratory
Department of Electrical Engineering
Building B
Room 2D:521
SE-581 83 Linköping, Sweden
+46(0)13 285654

< >

My pages:

Informationsansvarig: Per-Erik Forss&eacute;n
Senast uppdaterad: 2023-09-06