Advertisement

Research of Camera Track Based on Image Matching

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 152)

Abstract

Description of camera motion is one of the critical issues to implement automatic return for camera. This paper employs the Affine Transform Model to describe global motion, thus reconstructing movement of the camera according to information extracted from features of adjacent frames. Algorithm for feature point extraction is mainly discussed. In combination with secondary matching, SIFT (Scale Invariant Feature Transform) is improved by taking the density of points into consideration. The experimental results show that this method enhances the precision of matching with good real-time performance.

References

  1. 1.
    Luo J, Tang X, Xu D (2011) Computer vision. University of Science and Technology of China Press, Hefei, pp 1–3Google Scholar
  2. 2.
    Sturm P (2011) A historical survey of geometric computer vision. In: 14th international conference on computer analysis of images and patterns, Grenoble, pp 1–8Google Scholar
  3. 3.
    Liu Y (2010) A survey of computer vision applied in aerial robotic vehicles. In: 2nd international conference on optics, photonics and energy engineering, Wuhan, pp 277–280Google Scholar
  4. 4.
    Frew E, McGee T, Kim Z, Xiao X, Jackson S et al (2004) Vision-based road- following using a small autonomous aircraft. In: IEEE aerospace conference, pp 3006–3015Google Scholar
  5. 5.
    Fanyan B (2010) Research on digital image matching. Hefei Industry University, HefeiGoogle Scholar
  6. 6.
    Zhou Y (2008) Research on image matching. Xidian University, XianGoogle Scholar
  7. 7.
    Wang Q, Guan W, You S (2011) Augment distinctive feature for efficient image matching. In: IEEE workshop on application of computer vision, Kona, pp 15–22Google Scholar
  8. 8.
    Alhwarin F, Ristic Durrant D, Graser A (2010) Speeded up image matching using split and extended sift features. In: International conference on computer vision theory and applications, Angers, vol 5, pp 17–21Google Scholar
  9. 9.
    Grishin VA (2010) Two-channel algorithm of match making in computer vision systems. Sens Syst 65–68 Google Scholar
  10. 10.
    Mortensen EN, Deng H, Shapiro L (2005) A SIFT descriptor with global context. In: IEEE computer society conference on computer vision and pattern recognition, pp 184–190Google Scholar
  11. 11.
    Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. In: IEEE transactions on pattern analysis and machine intelligence, pp 1615–1630Google Scholar
  12. 12.
    Zhang J, Xiaojing B, Xu L (2009) A method of correcting SIFT mismatching based on spatial distribution descriptor. J Image Graphics 14(7):1369–1377Google Scholar
  13. 13.
    Baumberg A (2000) Reliable feature matching across widely separated views. In: IEEE conference on computer vision and pattern recognition, pp 774–781Google Scholar
  14. 14.
    Li R, Zeng B, Liou ML (1994) A new three-step search algorithm for block motion estimation. In: IEEE transactions on circuits and systems for video technology, pp 438–442Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Northeastern UniversityShenyangChina

Personalised recommendations