ad
Ahmed Elaksher
ATE
—-COST
150j-
Ha of points
Figure 9. Error Distributions from the the COST and ATE Systems
5 CONCLUSIONS
This paper has described an integrated stereo matching technique for object -surface reconstruction. The matching
problem is addressed by the integration of both signal and feature based approaches. To address stereo matching in
urban area images, we developed two innovative features, i.e., the plateau and spike. The classic dynamic programming
for feature matching is modified and enhanced to integrate signal and feature matching into a simultaneous
profile/surface determination. The initial global error statistics indicate that no improvement has been achieved over
strictly correlation based methods. However examination of some individual area (see Figure 7) indicate that the
methods offers promising potential in exactly the circumstances where area correlation is weak. This approach can be
further developed with other features, other match criteria, and improved search methods to yield even better results in
the future.
ACKNOWLEDGEMENTS
The work described in this paper was partially supported by the U.S. Army Research Office under Grant Number
DAAHO4-96-1-0444. The authors would like to acknowledge the support of Dr. Edward Mikhail, the project director.
They would also like to thank Ahmed Elaksher for his help in data analysis.
REFERENCES
l. Bellman, R., 1957, Dynamic Programming, Princeton University Press, Princeton NJ
ta
Bernard, M., Boutaleb, A., Kolbl, O., Penny, C., 1986, Automatic Stereophotogrammetry: Implementation and
Comparison of Classical Correlation Methods and Dynamic Programming Based Techniques
3. Bethel, J., Mikhail, E., Kim, K., Marshall, J., 1998, Intelligent Map Understanding — Automated Feature
Recognition and Delineation, Technical Report, School of Civil Engineering, Purdue University
4. Burns, J., Hanson, A., Riseman, E., 1986, ‘Extracting Straight Lines”, IEEE Transactions on Pattern Analysis and
Machine Intelligence, PAMI-8:429-455
5. Canny, J., 1986, “A Computational Approach to Edge Detection”, IEEE Transactions on Pattern Analysis and
Machine Intelligence, PAMI-8(6):679-698
6. Ohta, Y., and Kanade, T., 1985, “Stereo by Intra- and Interscanline Search Using Dynamic Programming”, IEEE
Transactions on Pattern Analysis and Machine Intelligence , PAMI-7:139-154
International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B3. Amsterdam 2000. 273