15-06-2012, 11:17 AM
A Method for Automatic Image Registration
Through Histogram-Based Image Segmentation
[attachment=24521]
Abstract
Automatic image registration is still an actual challenge
in several fields. Although several methods for automatic
image registration have been proposed in the last few years, it
is still far from a broad use in several applications, such as in
remote sensing. In this paper, a method for automatic image registration
through histogram-based image segmentation (HAIRIS)
is proposed.
INTRODUCTION
AUTOMATIC image registration (AIR) is still a present
challenge regarding image processing related applications.
Reviews concerning image registration methods can be
found in [3] and [45]. Remote sensing applications is one of
the fields where further research on AIR methods is required.
HAIRIS DESCRIPTION
Finding the relationship between two coordinate systems
using pairs of measurements of the coordinates of a number of
points in both systems is a classic photogrammetric task [19].
The transformation between two Cartesian coordinate systems
can be thought of as the result of a rigid-body motion and can,
thus, be decomposed into a rotation and a translation [19].
Suppose that we have a pair of images in the same scale (same
pixel size with respect to the scene), and the existence of a translation
and/or rotation difference between the two images, where
one of them is “static” (image 1) and the other (image 2) is to be
registered onto the “static” image. Assuming that are the
coordinates of the “static” image and are the (Pixel,Line)
pair of the image to be registered. The transformation may be
written as [3].
APPLICATION OF HAIRIS
In this section, the assessment of HAIRIS performance is performed
in the following situations: simulated rotation and translation,
the same simulated rotation and translation with different
levels of Gaussian white noise added to the image to be registered,
as well as in simulated and real examples of remote
sensing applications. For each image, the values considered for
parameter ranged from 0% to 100%, through steps of 20%,
10%, and 5%, in order to allow for a sensitivity analysis of the
parameter . The results were obtained on a computer with an
Intel Core 2 6400 2.13 GHz processor and 2.0 Gbytes of physical
memory, using MATLAB Release 2009b.
DISCUSSION AND CONCLUSION
A large variety of automatic image registration methods can
be found in [3] and [45]. In several applications, the registration
model only assumes rotation and translation [22], where the registration of satellite images is an example [2], [40]. In this paper,
a new approach for automatic image registration through histogram-
based image segmentation (HAIRIS) is proposed.
Through Histogram-Based Image Segmentation
[attachment=24521]
Abstract
Automatic image registration is still an actual challenge
in several fields. Although several methods for automatic
image registration have been proposed in the last few years, it
is still far from a broad use in several applications, such as in
remote sensing. In this paper, a method for automatic image registration
through histogram-based image segmentation (HAIRIS)
is proposed.
INTRODUCTION
AUTOMATIC image registration (AIR) is still a present
challenge regarding image processing related applications.
Reviews concerning image registration methods can be
found in [3] and [45]. Remote sensing applications is one of
the fields where further research on AIR methods is required.
HAIRIS DESCRIPTION
Finding the relationship between two coordinate systems
using pairs of measurements of the coordinates of a number of
points in both systems is a classic photogrammetric task [19].
The transformation between two Cartesian coordinate systems
can be thought of as the result of a rigid-body motion and can,
thus, be decomposed into a rotation and a translation [19].
Suppose that we have a pair of images in the same scale (same
pixel size with respect to the scene), and the existence of a translation
and/or rotation difference between the two images, where
one of them is “static” (image 1) and the other (image 2) is to be
registered onto the “static” image. Assuming that are the
coordinates of the “static” image and are the (Pixel,Line)
pair of the image to be registered. The transformation may be
written as [3].
APPLICATION OF HAIRIS
In this section, the assessment of HAIRIS performance is performed
in the following situations: simulated rotation and translation,
the same simulated rotation and translation with different
levels of Gaussian white noise added to the image to be registered,
as well as in simulated and real examples of remote
sensing applications. For each image, the values considered for
parameter ranged from 0% to 100%, through steps of 20%,
10%, and 5%, in order to allow for a sensitivity analysis of the
parameter . The results were obtained on a computer with an
Intel Core 2 6400 2.13 GHz processor and 2.0 Gbytes of physical
memory, using MATLAB Release 2009b.
DISCUSSION AND CONCLUSION
A large variety of automatic image registration methods can
be found in [3] and [45]. In several applications, the registration
model only assumes rotation and translation [22], where the registration of satellite images is an example [2], [40]. In this paper,
a new approach for automatic image registration through histogram-
based image segmentation (HAIRIS) is proposed.