The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B4. Beijing 2008
6. CONCLUSION AND FUTURE WORK
This paper introduced a novel matching approach to the
georegistration problem based on graph matching. It offers the
ability to utilize information about the topology and geometry
of a network to establish correspondence. The ability to utilize
both allows us to reduce the ambiguity of local consistency,
especially when inexact matching takes place. Furthermore, the
approach does not require user input, other than detecting road
intersections through image processing. Thus our approach
offers a robust and general solution to the image-to-x
registration problem using networks.
Future work will further investigate additional attributes to give
rise to invariant description of patterns in networks. It will also
include an extension of the proposed approach to more complex
networks.
ACKNOWLEDGEMENT
This work was supported by the National Geospatial-
Intelligence Agency through NURI grant NMA 401-02-1-2008.
REFERENCES
Barrow, H. G. and Popplestone, R. J., 1971. Relational
descriptions in picture processing. Machine Intelligence, 6,
Edinburgh.
Bunke, H., 1999. Error correcting graph matching: On the
influence of the underlying cost function. IEEE Trans. PAMI,
21(9), pp. 917-922.
Drewniok, C. and Rohr, K., 1996. Automatic exterior
orientation of aerial images in urban environments. In:
Proceedings of ISPRS, Vienna, Austria, Vol. XXXI, Part B3, pp.
146-152.
Gautama S., & Borgharaef, A., 2005. Detecting change in road
networks using continuous relaxation labelling. In: ISPRS
"Hannover Workshop 2005, Hannover.
Hummel, R.A. and Zucker, S.W., 1983. On the foundations of
relaxation labeling processes. IEEE Transactions on Pattern
Analysis and Machine Intelligence, PAMI-5(3), pp. 267-287.
Jain, B. J. and Wysotzki, F., 2002. Fast winner-takes-all
networks for the maximum clique problem. In: Proceedings of
the 25th Annual German Conference on AI: Advances in
Artificial Intelligence, pp. 163-173.
Li, S. Z., 1992. Matching: Invariant to translations, rotations
and scale changes. Pattern Recognition, 25(6), pp. 583-594.
Li, S. Z., 1994. A markov random field model for object
matching under contextual constraints”. In Proceedings of the
IEEE Computer Vision and Pattern Recognition Conference
(CVPR), Seattle, Washington, pp. 866-pp.869.
Luo B. & Hancock, E. R., 2001. Structural graph matching
using the EM algorithm and singular value decomposition.
IEEE Trans. PAMI, 23(10), pp. 1120-1136.
Pelillo, M., 1999. Replicator equations, maximal cliques, and
graph isomorphism. Neural Computation, 11(9), pp. 1933-1955.
Rohr, K., 2001. Landmark-based image analysis: using
geometric and intensity models. Kluwer Academic Publisher.
Rosenfeld, A., Hummel, R. and Zucker, S., 1976. Scene
labeling by relaxation operations. IEEE Trans. Syst. Man.
Cybem., 6, pp. 420-433.
Shapiro, L.G. and Haralick, R.M., 1985. A metric for
comparing relational descriptions. IEEE Trans. PAMI, 7(1 ):90—
94.
Shi, J. and Malik, J., 1998. Self inducing relational distance and
its application to image segmentation. Lecture Notes in
Computer Science, 1406, pp. 528.
Wilson, R.C. & Hancock, E. R., 1997. Structural matching by
discrete relaxation. IEEE PAMI, 19(6), pp. 634-648.
