Publication detail

3D Reconstruction: Novel Method for Finding of Corresponding Points

BOLEČEK, L. ŘÍČNÝ, V. SLANINA, M.

Original Title

3D Reconstruction: Novel Method for Finding of Corresponding Points

English Title

3D Reconstruction: Novel Method for Finding of Corresponding Points

Type

journal article - other

Language

en

Original Abstract

Paper deal with the reconstruction of spatial coordinates of an arbitrary point from a scene using two images scanned by the 3D camera or two displaced cameras. Calculations are based on the perspective geometry. Accurate determination of corresponding points is a fundamental step in this process. The usually used methods can have a problem with points, which lie in areas without sufficient contrast. This paper describes our proposed method based on the use of the relationship between the selected points and area features points. The proposed method finds correspondence using a set of feature points found by SURF. For this purpose an algorithm was proposed and described for quick removal of false correspondences, which could ruin the correct reconstruction. The new method, which makes use of images displaying in pseudo colors (pseudo coloring) has been proposed subsequently. By means of this method it is possible to significantly increase the color contrast of the surveyed image, and therefore add more information to find the correct correspondence. Reliability of the found correspondence can be verified by reconstruction of 3D position of selected points. Executed experiments confirm our assumptions.

English abstract

Paper deal with the reconstruction of spatial coordinates of an arbitrary point from a scene using two images scanned by the 3D camera or two displaced cameras. Calculations are based on the perspective geometry. Accurate determination of corresponding points is a fundamental step in this process. The usually used methods can have a problem with points, which lie in areas without sufficient contrast. This paper describes our proposed method based on the use of the relationship between the selected points and area features points. The proposed method finds correspondence using a set of feature points found by SURF. For this purpose an algorithm was proposed and described for quick removal of false correspondences, which could ruin the correct reconstruction. The new method, which makes use of images displaying in pseudo colors (pseudo coloring) has been proposed subsequently. By means of this method it is possible to significantly increase the color contrast of the surveyed image, and therefore add more information to find the correct correspondence. Reliability of the found correspondence can be verified by reconstruction of 3D position of selected points. Executed experiments confirm our assumptions.

Keywords

3D reconstruction, features points, image correspondence, pseudo color

RIV year

2013

Released

08.04.2013

Location

Brno

Pages from

82

Pages to

91

Pages count

10

BibTex


@article{BUT99296,
  author="Libor {Boleček} and Václav {Říčný} and Martin {Slanina}",
  title="3D Reconstruction: Novel Method for Finding of Corresponding Points",
  annote="Paper deal with the reconstruction of spatial coordinates of an arbitrary point from a scene using two images scanned by the 3D camera or two displaced cameras. Calculations are based on the perspective geometry. Accurate determination of corresponding points is a fundamental step in this process. The usually used methods can have a problem with points, which lie in areas without sufficient contrast. This paper describes our proposed method based on the use of the relationship between the selected points and area features points. The proposed method finds correspondence using a set of feature points found by SURF. For this purpose an algorithm was proposed and described for quick removal of false correspondences, which could ruin the correct reconstruction. The new method, which makes use of images displaying in pseudo colors (pseudo coloring) has been proposed subsequently. By means of this method it is possible to significantly increase the color contrast of the surveyed image, and therefore add more information to find the correct correspondence. Reliability of the found correspondence can be verified by reconstruction of 3D position of selected points. Executed experiments confirm our assumptions.",
  chapter="99296",
  number="1",
  volume="22",
  year="2013",
  month="april",
  pages="82--91",
  type="journal article - other"
}