Robust line matching through line-point invariants

  • Authors:

  • Bin Fan;Fuchao Wu;Zhanyi Hu

  • Affiliations:

  • National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 100190 Beijing, China;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 100190 Beijing, China;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 100190 Beijing, China

  • Venue:
  • Pattern Recognition
  • Year:
  • 2012

Quantified Score

Hi-index 0.01

Visualization

Abstract

This paper is about line matching by line-point invariants which encode local geometric information between a line and its neighboring points. Specifically, two kinds of line-point invariants are introduced in this paper, one is an affine invariant constructed from one line and two points while the other is a projective invariant constructed from one line and four points. The basic idea of our proposed line matching methods is to use cheaply obtainable matched points to boost line matching via line-point invariants, even if the matched points are susceptible to severe outlier contamination. To deal with the inevitable mismatches in the matched points, two line similarity measures are proposed, one is based on the maximum and the other is based on the maximal median. Therefore, four different line matching methods are obtained by combining different line-point invariants with different similarity measures. Their performances are evaluated by extensive experiments. The results show that our proposed methods outperform the state-of-the-art methods, and are robust to mismatches in the matched points used for line matching.