Wide baseline correspondence extraction beyond local features

R. Lakemond; S. Sridharan; C. Fookes

Wide baseline correspondence extraction beyond local features

Access Full Text

Wide baseline correspondence extraction beyond local features

Author(s): R. Lakemond ; S. Sridharan ; C. Fookes
DOI: 10.1049/iet-cvi.2010.0045

For access to this article, please select a purchase option:

Buy article PDF

Buy Knowledge Pack

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership

Recommend Title Publication to library

IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Author(s): R. Lakemond ¹ ; S. Sridharan ¹ ; C. Fookes ¹
- Affiliations: 1: Image and Video Research Laboratory, Queensland University of Technology, Brisbane, Australia
Source: Volume 5, Issue 4, July 2011, p. 222 – 231
DOI: 10.1049/iet-cvi.2010.0045 , Print ISSN 1751-9632, Online ISSN 1751-9640

Published

Robust, affine covariant, feature extractors provide a means to extract correspondences between images captured by widely separated cameras. Advances in wide baseline correspondence extraction require looking beyond the robust feature extraction and matching approach. This study examines new techniques of extracting correspondences that take advantage of information contained in affine feature matches. Methods of improving the accuracy of a set of putative matches, eliminating incorrect matches and extracting large numbers of additional correspondences are explored. It is assumed that knowledge of the camera geometry is not available and not immediately recoverable. The new techniques are evaluated by means of an epipolar geometry estimation task. It is shown that these methods enable the computation of camera geometry in many cases where existing feature extractors cannot produce sufficient numbers of accurate correspondences.

References

1. 1)
  - Furukawa, Y., Ponce, J.: `Accurate, dense, and robust multi-view stereopsis', IEEE Conf. on Computer Vision and Pattern Recognition 2007 (CVPR’07), 2007, p. 1–8.
2. 2)
  - Beaudet, P.R.: `Rotationally invariant image operators', Int. Joint Conf. on Pattern Recognition, 1978, Kyoto, Japan, p. 579–583.
3. 3)
  - Harris, C., Stephens, M.: `A combined corner and edge detector', Alvey Vision Conf., 1988, p. 189–192.
4. 4)
  - M. Pollefeys , L. Van Gool , M. Vergauwen . Visual modeling with a hand-held camera. Int. J. Comput. Vis. , 3 , 207 - 232
5. 5)
  - F. Rothganger , S. Lazebnik , C. Schmid , J. Ponce . 3d object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. Int. J. Comput. Vis. , 3 , 231 - 259
6. 6)
  - K. Mikolajczyk , C. Schmid . A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. , 10 , 1615 - 1629
7. 7)
  - Lakemond, R., McKinnon, D.N.R., Fookes, C., Sridharan, S.: `A feature clustering algorithm for scale-space analysis of image structures', Int. Conf. on Signal Processing and Communication Systems, ICSPCS’2007, 2007, Gold Coast, Australia.
8. 8)
  - Tuytelaars, T., Gool, L.V.: `Content-based image retrieval based on local affinely invariant regions', Visual Information and Information Systems, 1999, Berlin, Heidelberg, p. 656–656, (LNCS, 1614).
9. 9)
  - Lindeberg, T., Gårding, J.: `Shape-adapted smoothing in estimation of 3-d depth cues from affine distortions of local 2-d brightness structure', Computer Vision – ECCV ’94, 1994, Berlin, Heidelberg, p. 389–400, (LNCS, 800).
10. 10)
  - K. Mikolajczyk , T. Tuytelaars , C. Schmid , A. Zisserman , J. Matas , F. Schaffslatzky , T. Kadir , V.L. Gool . A comparison of affine region detectors. Int. J. Comput. Vis. , 1 , 43 - 72
11. 11)
  - D.G. Lowe . Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis , 2 , 91 - 110
12. 12)
  - N. Snavely , S. Seitz , R. Szeliski . Modeling the world from internet photo collections. Int. J. Comput. Vis. , 2 , 189 - 210
13. 13)
  - R. Hartley . (2003) Multiple view geometry in computer vision.
14. 14)
  - P. Moreels , P. Perona . Evaluation of features detectors and descriptors based on 3d objects. Int. J. Comput. Vis. , 3 , 263 - 284
15. 15)
  - T. Tuytelaars , K. Mikolajczyk . Local invariant feature detectors: a survey. Found. Trends Comput. Graph. Vis. , 3 , 177 - 280
16. 16)
  - K. Mikolajczyk , C. Schmid . Scale & affine invariant interest point detectors. Int. J. Comput. Vis. , 1 , 63 - 86
17. 17)
  - R.I. Hartley , P. Sturm . Triangulation. Comput. Vis. Image Underst. , 2 , 146 - 157
18. 18)
  - H.C. Longuet-Higgins . A computer algorithm for reconstructing a scene from two projections. Nature , 5828 , 133 - 135
19. 19)
  - Lakemond, R., Fookes, C., Sridharan, S.: `Dense correspondence extraction in difficult uncalibrated scenarios', Proc. Digital Image Computing: Techniques and Applications, 2009, Melbourne, Australia, p. 53–60.
20. 20)
  - M.A. Fischler , R.C. Bolles . Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM , 381 - 395
21. 21)
  - Baumberg, A.: `Reliable feature matching across widely separated views', IEEE Conf. on Computer Vision and Pattern Recognition, 2000, Hilton Head Island, South Carolina, USA, 1, p. 774–781.
22. 22)
  - Lakemond, R., Fookes, C., Sridharan, S.: `Affine adaptation of local image features using the hessian matrix', Proc. IEEE Conf. on Advanced Video and Signal Based Surveillance, 2009, Genoa, Italy, p. 496–501.
23. 23)
  - J.-P. Pons , R. Keriven , O. Faugeras . Multi-view stereo reconstruction and scene flow estimation with a global image-based matching score. Int. J. Comput. Vis. , 2 , 179 - 193
24. 24)
  - S. Baker , I. Matthews . Lucas–Kanade 20 years on: a unifying framework. Int. J. Comput. Vis. , 221 - 255
25. 25)
  - Matas, J., Chum, O., Urban, M., Pajdla, T.: `Robust wide baseline stereo from maximally stable extremal regions', British Machine Vision Conf., BMVC 2002, 2002, Cardiff, UK, 1, p. 384–393.
26. 26)
  - P. Carbonetto , G. Dorkó , C. Schmid , H. Kück , N. de Freitas . Learning to recognize objects with little supervision. Int. J. Comput. Vis. , 1 , 219 - 237

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Wide baseline correspondence extraction beyond local features

Wide baseline correspondence extraction beyond local features

Buy article PDF

Buy Knowledge Pack

Thank you

References

Related content