적응 정합 값 변환을 이용한 영상 모자이크 과정에서의 최적 Seam-Line 결정

Optimal Seam-line Determination for the Image Mosaicking Using the Adaptive Cost Transform

  • 발행 : 2005.03.01

초록

A seam-line determination algorithm is proposed to determine image border-line in mosaicing using the transformation of gray value differences and dynamic programming. Since visually good border-line is the one along which pixel differences are as small as possible, it can be determined in association with an optimal path finding algorithm. A well-known effective optimal path finding algorithm is the Dynamic Programming (DP). Direct application of the dynamic programming to the seam-line determination causes the distance effect, in which seam-line is affected by its length as well as the gray value difference. In this paper, an adaptive cost transform algorithm with which the distance effect is suppressed is proposed in order to utilize the dynamic programming on the transformed pixel difference space. Also, a figure of merit which is the summation of fixed number of the biggest pixel difference on the seam-line (SFBPD) is suggested as an evaluation measure of seamlines. The performance of the proposed algorithm has been tested in both quantitively and visually on various kinds of images.

키워드

참고문헌

  1. S. Coorg, S. Teller, 'Spherical mosaics with quaternions and dense correlation' In IJCV, vol. 37, No. 3, pp. 259-273, June 2000 https://doi.org/10.1023/A:1008184124789
  2. H.-Y. Shum, R. Szeliski, 'Systems and experiment paper' construction of panoramic image mosaics with global and local alignment,' In IJCV, vol. 36, No. 2, pp. 101-130, 2000 https://doi.org/10.1023/A:1008195814169
  3. Z. Zhu, A. R. Hanson, H. Schultz, E. M. Riseman, 'Generalized parallel-perspective stereo mosaics from airborne video,' IEEE Transactions on PAMI, 26(2), pp. 226-237, 2C04 https://doi.org/10.1109/TPAMI.2004.1262190
  4. http://mitchntsl.cr.usgs.gov/projects/aerial.html, USGS Hurricane Mitch Program Projects
  5. H. Sawhney and S. Ayer, 'Compact representation of video through dominant and multiple motion estimation, 'IEEE Trans. PAMI, vol. 18, pp. 814-830, Aug. 1997 https://doi.org/10.1109/34.531801
  6. J. S. Chou, J. Qian, Z. Wu, H. Schramm, 'Automatic mosaic and display from a sequence of peripheral angiographic images,' Proc. SPIE, vol. 3034, pp. 1077-1087, Medical Imaging, April 1997 https://doi.org/10.1117/12.274088
  7. R. Szeliski, 'Video mosaic for virtual enviroment,' Comput. Graph. Applicat, pp. 22-30, Mar. 1996
  8. H. Nicilas, 'New methods for dynamic mosaicking,' IEEE Trans. on PAMI, vol. 10, no.8, pp. 1239-1251, AUG. 2001 https://doi.org/10.1109/83.935039
  9. Martin Kerschner, 'Seamline detection in colour orthoimage mosaicking by use of twin snakes,' ISPRS Journal of Photogrammetry & Remote Sensing, vol. 56, pp. 53-64, 2001 https://doi.org/10.1016/S0924-2716(01)00033-8
  10. M. Kass, A. Witkin and D. Terzopoulos 'Snakes, active contour models,' International Journal of Computer Vision, Vol.1, 1987, pp.321-331 https://doi.org/10.1007/BF00133570
  11. Amir A. A., Terry E. W. and Ramesh C. J., 'Using Dynamic Programming for Solving Variational Problems in Vision,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No. 9, pp. 855-867, 1990 https://doi.org/10.1109/34.57681
  12. Marie-Lise Duplaquet, 'Bulding large image mosaics with invisible seam-lines,' Proc. SPIE, vol. 3387, April 1998
  13. Satya Prakash Mallick, 'Feature Based Image Mosaicing,' www.cs.ucsd.edu/classes/fa02/cse252c/smallick.pdf