Main > Acta Optica Sinica >  Volume 34 >  Issue 2 >  Page 215003 > Article
  • Abstract
  • Abstract
  • View Summary
  • Figures (0)
  • Tables (0)
  • Equations (0)
  • References (12)
  • Get PDF(in Chinese)
  • Paper Information
  • Received: Jul. 30, 2013

    Accepted: --

    Posted: Feb. 1, 2014

    Published Online: Jan. 23, 2014

    The Author Email: Qiang Zhang (jhtzq@ysu.edu.cn)

    DOI: 10.3788/aos201434.0215003

  • Get Citation
  • Copy Citation Text

    Zhang Qiang, Hao Kai, Li Haibin. Research on Scale Invariant Feature Transform Feature Matching Based on Underwater Curve Constraint[J]. Acta Optica Sinica, 2014, 34(2): 215003

    Download Citation

  • Category
  • Machine Vision
  • Share
Acta Optica Sinica, Vol. 34, Issue 2, 215003 (2014)

Research on Scale Invariant Feature Transform Feature Matching Based on Underwater Curve Constraint

Qiang Zhang1,*, Kai Hao1, and Haibin Li1,2

Author Affiliations

  • 1[in Chinese]
  • 2[in Chinese]

Abstract

In the light of underwater binocular image matching cannot satisfy the epipolar constraint of air, and the mismatching rate of underwater image processed by the scale invariant feature transform (SIFT) algorithm is high, we put forward an underwater feature matching algorithm based on curve constraint. Binocular camera should be calibrated, and some relevant parameters are obtained, as well as the reference image and the image to be matched; the SIFT feature matching algorithm can help to match two images, at the same time, the feature points can be extracted from the reference image to deduce the corresponding curve on the image to be matched. The curve is used as a constraint to determine whether the corresponding feature is on it, thus mismatching points will be excluded to achieve a higher accuracy. The test results show that this algorithm is superior to SIFT algorithm and can help to exclude mismatching points effectively. The matching accuracy can increase by about 12%. The problem of SIFT algorithm′s high rate of mismatching for underwater binocular stereo matching is solved.

keywords

Please Enter Your Email: