ISPRS Commission III, Vol.34, Part 3A „Photogrammetric Computer Vision“, Graz, 2002
A metric for comparing relational descriptions. (a)
IEEE trans. PAMI, 7(1), pp. 90-94.
Vosselman, G., 1992.
Relational matching. LNCS 628, Springer-Verlag, Berlin.
Kim, W. Y and Kak, A. C., 1991.
3-D object recognition using bipartite matching embedded in
discrete relaxation. JEEE trans. PAMI, 13(3), pp. 224-251.
Oommen, B. J. and Loke, R. K. S., 2001.
On the pattern recognition of noisy subsequence trees.
IEEE trans. PAMI, 23(9), pp. 929-946.
Geman, S. and Geman, D., 1984.
Stochastic relaxation, Gibbs distribution and the Bayesian
restoration of images. IEEE trans. PAMI, 6, pp. 721-741.
Young, T. Y. and Fu, K. S. Eds., 1986. Handbook of pattern
recognition and image processing. Academic Press, San Diego.
Ohta, Y., 1985. Knowledge-based interpretation of outdoor
natural color scenes, Pitman Publishing, Boston.
Chang, S. K., Shi, Q. Y., and Yan, C. W., 1987.
Iconic indexing by 2-D strings.
IEEE trans. PAMI, 9(3), pp. 413-428.
Mohan, A., Papageorgiou, C., and Poggio, T., 2001.
Example-based object detection in image by components.
IEEE trans. PAMI, 23(4), pp. 349-361.
Suto, T., Nishikawa, Y., Watanabe, T., and Sugawara, K., 2000.
Recognizing objects in aerial images.
Proc. JSPRS 2000, pp.263-266. (in Japanese).
Nishikawa, Y., Kubo, T., Watanabe, T., and Shinada, T., 2001.
MLDI: Matching largely deviated landmark-less images.
Proc. JSPRS 2001, pp.149-152. (in Japanese).
Vapnik, V., 1998.
Statistical learning theory. John Wiley & Sons, Inc., New York.
Samet, H., 1993.
Applications of spatial data structures, Addison-Wesley.
Figure 9. Matching experiment using real images
(a) and (b) Task images;
ACKNOWLEDGEMENTS (a) (408x606) pixels. (scaling, rotation) = (1.00, 0° y,
(b) (scaling, rotation) — (1.25, 60^),
(c) and (d) the most similar triangles found in two segmented images
are shown. The vertices are gravity centers of found ICOs. Gravity
centers of triangles are also shown;
(e) matching result
T. Suto, Y. Nishikawa and T. Kubo, students in our laboratory,
are acknowledged for prototyping several applications of the
NSR theory. Mr. F. Komura at Hitachi is acknowledged for
discussions on aerial image registration problems. Prof. Dr. A.
Gruen at ATH, who suggested to post this work to PCV'02, is
also acknowledged.
A - 393