1 August 1990 A new method for automated control point selection in image registration
Author Affiliations +
Proceedings Volume 1395, Close-Range Photogrammetry Meets Machine Vision; 139529 (1990) https://doi.org/10.1117/12.2294324
Event: Close-Range Photogrammetry Meets Machine Vision, 1990, Zurich, Switzerland
Abstract
The selection for control points is a necessity in registration for remotely sensed images. This paper is to propose a new progressive method to automatically generate control point pairs with uniform distribution. The Voronoi-Delaunay dual graph is used to predict the optimal locations first. Interest operators are then used to extract point features for potential control points. Finally, a hierarchical coarse-to-fine matching procedure is applied. The area-based matching is also integrated for accomplishing the image correspondence to sub- pixel level. A consistency check by Robust Estimation is also included. A pair of digitized aerial photos are used in the case study. Results indicate that the proposed has many attractive merits.
© (1990) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Liang-Hwei Lee, Liang-Hwei Lee, Liang-Chien Chen, Liang-Chien Chen, } "A new method for automated control point selection in image registration", Proc. SPIE 1395, Close-Range Photogrammetry Meets Machine Vision, 139529 (1 August 1990); doi: 10.1117/12.2294324; https://doi.org/10.1117/12.2294324
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT


Back to Top