Estimating the Best Reference Homography for Planar Mosaics From Videos

Fabio Bellavia, Carlo Colombo

2015

Abstract

This paper proposes a novel strategy to find the best reference homography in mosaics from video sequences. The reference homography globally minimizes the distortions induced on each image frame by the mosaic homography itself. This method is designed for planar mosaics on which a bad choice of the first reference image frame can lead to severe distortions after concatenating several successive homographies. This often happens in the case of underwater mosaics with non-flat seabed and no georeferential information available. Given a video sequence of an almost planar surface, sub-mosaics with low distortions of temporally close image frames are computed and successively merged according to a hierarchical clustering procedure. A robust and effective feature tracker using an approximated global position map between image frames allows us to build the mosaic also between locally close but not temporally consecutive frames. Sub-mosaics are successively merged by concatenating their relative homographies with another reference homography which minimizes the distortion on each frame of the fused image. Experimental results on challenging real underwater videos show the validity of the proposed method.

References

  1. Bellavia, F., Gagliano, G., Tegolo, D., and Valenti, C. (2007). Global archaeological mosaicing for underwater scenes. WSEAS Transactions on Signal Processing, 2(7):997-1003.
  2. Bellavia, F. and Tegolo, D. (2011). noRANSAC for fundamental matrix estimation. In British Machine Vision Conference, pages 1-11.
  3. Bellavia, F., Tegolo, D., and Valenti, C. (2011). Improving Harris corner selection strategy. IET Computer Vision, 5(2):87-96.
  4. Bellavia, F., Tegolo, D., and Valenti, C. (2014). Keypoint descriptor matching with context-based orientation estimation. Image and Vision Computing, 32(9):559 - 567.
  5. Brown, M. and Lowe, D. G. (2007). Automatic panoramic image stitching using invariant features. International Journal of Computer Vision, 74(1):59-73.
  6. Capel, D. P. (2001). Image Mosaicing and Super-resolution. PhD thesis, University of Oxford.
  7. Cormen, T. H., Leiserson, C. E., Rivest, R. L., and Stein, C. (2009). Introduction to Algorithms (3. ed.). MIT Press.
  8. Hartley, R. and Zisserman, A. (2003). Multiple View Geometry in Computer Vision. Cambridge University Press, 2 edition.
  9. Haykin, S. (1998). Neural Networks: A Comprehensive Foundation. Prentice Hall, 2 edition.
  10. Konolige, K. and Agrawal, M. (2008). Frameslam: From bundle adjustment to real-time visual mapping. IEEE Transactions on Robotics, 24(5):1066-1077.
  11. Kwatra, V., Schödl, A., Essa, I. A., Turk, G., and Bobick, A. F. (2003). Graphcut textures: image and video synthesis using graph cuts. 22(3):277-286.
  12. Lin, W. Y., Liu, S., Matsushita, Y., Ng, T. T., and Cheong, L. F. (2011). Smoothly varying affine stitching. In IEEE Conference on Computer Vision and Pattern Recognition, pages 345-352.
  13. Lowe, D. G. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision, 60(2):91-110.
  14. Pizarro, O. and Singh, H. (2003). Toward large-area mosaicing for underwater scientific applications. IEEE Journal of Oceanic Engineering, 28(4):651-672.
  15. Prados, R., Garcia, R., Gracias, N., Escartin, J., and Neumann, L. (2012). A novel blending technique for underwater giga-mosaicing. IEEE Journal of Oceanic Engineering, 37(4):626-644.
  16. Reinhard, E., Ashikhmin, M., Gooch, B., and Shirley, P. (2001). Color transfer between images. IEEE Computer Graphics and Applications, 21(5):34-41.
  17. Uyttendaele, M., Eden, A., and Szeliski, R. (2001). Eliminating ghosting and exposure artifacts in image mosaics. In Computer Vision and Pattern Recognition, pages 509-516.
  18. Zaragoza, J., Chin, T. J., Tran, Q. H., Brown, M., and Suter, D. (2014). As-Projective-As-Possible image stitching with moving DLT. IEEE Transaction on Pattern Analysis and Machine Intelligence, 36(7):1285-1298.
  19. Zhang, F. and Liu, F. (2014). Parallax-tolerant image stitching. In IEEE Conference on Computer Vision and Pattern Recognition, pages 3262-3269.
Download


Paper Citation


in Harvard Style

Bellavia F. and Colombo C. (2015). Estimating the Best Reference Homography for Planar Mosaics From Videos . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-091-8, pages 512-519. DOI: 10.5220/0005297305120519


in Bibtex Style

@conference{visapp15,
author={Fabio Bellavia and Carlo Colombo},
title={Estimating the Best Reference Homography for Planar Mosaics From Videos},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={512-519},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005297305120519},
isbn={978-989-758-091-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)
TI - Estimating the Best Reference Homography for Planar Mosaics From Videos
SN - 978-989-758-091-8
AU - Bellavia F.
AU - Colombo C.
PY - 2015
SP - 512
EP - 519
DO - 10.5220/0005297305120519