L. C. Chen* C. M. Chen** J. Y. Rau***

Image matching is one of the most important tasks in automated extraction of digital terrain models in digital photogrammetry. Area-based matching usually works well for the smooth terrain with low relief, especially when low resolution image pairs are used. However, area-based matching is not feasible for high resolution image pairs where artificial buildings exist. On the other hand, feature matching has better chance to cope with the problem. Hence, we propose a scheme which extracts image features first then organizes a feature matching strategy, and develops a new feature-based matching scheme, i.e., Azimuth-Moment Matching method, to correspond the potential conjugate features. Experimental results indicate that for a pair of high resolution aerial photographs the proposed scheme may accomplish the task that conventional templet matching dose not.

feature-based matching, edge, azimuth-moment matching

*Professor, Center for Space and Remote Sensing Research & Department of Civil Engineering, National Central University

**Master, Department of Civil Engineering, National Central University.

***Ph. D. Student, Department of Civil Engineering, National Central University.

[go back]