Geometric Grouping of Repeated Elements within Images

Frederik Schaffalitzky, Andrew Zisserman

Abstract

The objective of this work is the automatic detection and grouping of imaged elements which repeat on a plane in a scene (for example tiled floorings). It is shown that structures that repeat on a scene plane are related by particular parametrized transformations in perspective images. These image transformations provide powerfulgrou ping constraints, and can be used at the heart of hypothesize and verify grouping algorithms. The parametrized transformations are global across the image plane and may be computed without knowledge of the pose of the plane or camera calibration.
BibTeX
@inproceedings{schaffalitzky1999geometric,
  author = {Frederik Schaffalitzky and Andrew Zisserman},
  title = {{Geometric Grouping of Repeated Elements within Images}},
  booktitle = {Shape, Contour and Grouping in Computer Vision},
  year = {1999},
  doi = {10.1007/3-540-46805-6\_10},
}

Loading related content...

Figure