ISPRS Commission III, Vol.34, Part 3A „Photogrammetric Computer Vision“, Graz, 2002
geometric or radiometric properties, but by the mathematical
transformation that describes the geometrical relationship
between two images. In other words, this approach does not
require feature matching. Instead, a search is conducted in
the space of admissible transformation. Geometrically
invariant features are adopted to decompose the
computational complexity of the transformation. This
approach solves simultaneously for the registration
parameters and the matched features.
This approach is highly robust as compared to the traditional
M-estimators (Rosseeuw and Leroy, 1987), which tolerates
only up to 5096 of outliers. Combining the developed
approach with the least squares estimator facilitate the
achievement of subpixel accuracy in the final registration
parameters. Research effort is underway to characterize
performance metrics and pathological cases, in order to
extend this approach in its methodology and applications.
1987-1991
Figure 5: Shows the results of
resampling using the registration
parameters.
6. ACKNOWLEDGEMENTS
We would like to express our great appreciation to the
Pacific Northwest National Laboratory for the full financial
support under project No. 43429.
7. REFERENCES
Brown, L., (1992). A Survey of Image Registration
Techniques. ACM Comput. Surv. 24, No. 4, pp. 325-376.
Dare, P., L, Dowman, (2001). An Improved Model for
Automatic Feature-Based Registration of SAR and SPOT
Images. ISPRS Journal of Photogrammetry and Remote
Sensing, 56 (2001) pp. 13-28.
Habib, A., A., Asmamaw, D., Kelly, (2000). New Approach
to Solve the Matching Problem in Photogrammetry. Xe
ISPRS Congress, Amsterdam, The Netherlands (16-23 July
2000).
Habib, A., D., Kelley. 2001*. Single Photo Resection Using
Modified Iterative Hough Transform. Journal of
Photogrammetric Engineering and Remote Sensing, Vol. 67,
August 2001, pp. 909-914.
Habib, A., D., Kelley. 2001°. Automatic Relative orientation
of Large Scale Imagery over Urban Areas Using Modified
Iterative Hough Transform. International Journal of
Photogrammetry and Remote Sensing, 56 (2001), pp. 29-41.
Habib, A., T., Schenk, (1999). New Approach for Matching
Surfaces from Laser Scanners and Optical Sensors. Joint
Workshop of ISPRS III/5 and III/2 on Mapping Surface
Structure and Topography by Air-borne and Space-borne
Lasers, La Jolla, San Diego, CA (November 9-11 1999).
Habib, A., Y., Lee, M. Morgan, (2001). Surface Matching
and Change Detection Using Modified Iterative Hough
Transform for Robust Parameter Estimation.
Photogrammetric Record, 17 (98), October 2001, pp. 303-
315.
Hough, P., (1962). Methods and Means for Recognizing
Complex Pattern, US Patent 3,069,654.
Hsieh J., H. Liao, K. Fan, M. Ko, Y. Hung, (1997). Image
Registration Using a New Edge-Based Approach, Computer
Vision and Image Understanding, Vol. 67,No. 2, August, pp.
112-130.
Li, H., B., Manjunath, S., Mitra, (1995). A Contour-Based
Approach to Multi-sensor Image Registration. /EEE
Transaction on Image Processing, Vol. 4, No. 3, March
1995, pp. 320-334.
Moravec, H., (1977). Towards Automatic Visual Obstacle
Avoidance. Proc. 5" Int. Joint Conference on Artificial
Intelligence, MIT, Cambridge, MA, USA, p. 584.
Mundy, J., A., Zisserman, (1992). Towards a New
Framework for Vision. Geometric Invariance in Computer
Vision (Mundy and Zisserman, editors), The MIT Press.
Rousseew, P., A., Leroy, (1987). Robust Regression and
Outlier Detection. Wiley, New York.
Schaffrin, B., (1997). Class Notes
computations. The Ohio State University.
Thepaut, O., K., Kpalma, J., Roseph, (2000). Automatic
Registration of ERS and SPOT Multisensor Images in a Data
Fusion Context. Forest Ecology and Management, 128
(2000), pp. 93-100.
Wolfson, H., (1990). On Curve Matching. /EEE Transaction
on Pattern Recognition and Machine Intelligence, Vol. 12,
No. 5, May 1990, pp. 483-489.
on Adjustment