Review article: A 1D approach to correlation-based stereo matching

  • Authors:
  • SéBastien Lefebvre;SéBastien Ambellouis;FrançOis Cabestaing

  • Affiliations:
  • IFSTTAR, LEOST, F-59666 Villeneuve d'Ascq, France and Univ Lille Nord de France, F-59000 Lille, France;IFSTTAR, LEOST, F-59666 Villeneuve d'Ascq, France and Univ Lille Nord de France, F-59000 Lille, France;LAGIS - UMR CNRS 8146 F-59655 Villeneuve d'Ascq, France and Univ Lille Nord de France, F-59000 Lille, France

  • Venue:
  • Image and Vision Computing
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In stereovision, indices allowing pixels of the left and right images to be matched are basically one-dimensional features of the epipolar lines. In some situations, these features are not significant or cannot be extracted from the single epipolar line. Therefore, many techniques use 2D neighbourhoods to increase the available information. In this paper, we discuss the systematic use of 2D neighbourhoods for stereo matching. We propose an alternative approach to stereo matching using multiple 1D correlation windows, which yields a semi-dense disparity map and an associated confidence map. A particular technique derived from this approach - using fuzzy filtering and a basic decision rule - is compared to about 80 other methods on the Middlebury image datasets [1]. Results are first presented in the framework of the Middlebury website, then on the Receiver Operating Characteristics (ROC) evaluation [2] and, finally, on stereo image pairs of slanted surfaces. We show that a 1D correlation window is sufficient to provide correct matchings in most cases.