Landmarks are unique image features used to establish correspondence between two images of a scene.
Landmarks are most useful because their coordinates can be directly used to determine the parameters of
the transformation that registers the images. Examples of landmark detection are given below. Various
landmark detection algorithms developed by Image Registration and Fusion Systems makes it possible to
adjust the spacing between the landmarks and obtain a desired number of them. Detected landmarks are
stable under a wide range of image resolutions and orientations. This invariance makes it possible to select
similar landmarks in images captured under different conditions of a scene.
Two examples of this software are given below. For more examples, please visit the Point Detectors page.
Landmarks are most useful because their coordinates can be directly used to determine the parameters of
the transformation that registers the images. Examples of landmark detection are given below. Various
landmark detection algorithms developed by Image Registration and Fusion Systems makes it possible to
adjust the spacing between the landmarks and obtain a desired number of them. Detected landmarks are
stable under a wide range of image resolutions and orientations. This invariance makes it possible to select
similar landmarks in images captured under different conditions of a scene.
Two examples of this software are given below. For more examples, please visit the Point Detectors page.
 |  |
Fig. 1. (a) Landmarks selected in two images of the Art Museum in Washington, D.C., taken from slightly different view
points. Many of the landmarks selected in the images show the same physical points in the scene. (b) Landmarks selected
in two images of the World Trade Center, New York City. Original images of the New York City are courtesy of NASA.
points. Many of the landmarks selected in the images show the same physical points in the scene. (b) Landmarks selected
in two images of the World Trade Center, New York City. Original images of the New York City are courtesy of NASA.
To obtain a license for this software, please follow the link =>
2-D point (landmark) detection |
| Image Registration and Fusion Systems |
