|Image alignment/registration software
|Image Registration and Fusion Systems
Analysis of two or more images of a scene often requires spatial alignment of the images to bring the images under the
same coordinate system. This is required when creating a mosaic from two or more overlapping images, finding scene
changes in multi-temporal images, combining information in multi-modality images, and separating moving objects from
the background in a video obtained by a moving platform. Following are example applications of image alignment.
Image mosaicking: By aligning two or more images of a scene at their overlap areas, a larger image is created
covering a larger area. An example is give below. For more examples, see the Image mosaicking page.
Change detection: By aligning images of a scene taken at different times, it becomes possible to compare and
find changes occurred in the scene over time. This capability can be used to compare before and after disaster
images and assess the damages caused as a result. Plates (a) and (b) show New Jersey shore before and after the
hurricane Sandy. These images are courtesy of NOAA. Plate (c) shows alignment of images (a) and (b). Image (a) is
shown in light blue while image (b) is shown in red. Red and light blue regions highlight differences in the images and
identify areas in the scene that have changed due to the hurricane.
Image fusion: By aligning multi-modality images, different properties of the images are combined into an image that
contains more information than any of the individual images. The example below shows alignment of (a) an optical
image and (b) a thermal image to create (c) a new image that contains both optical and thermal information. Images
(a) and (b) are courtesy of USGS.
Motion detection: When images are captured by a moving platform, image motion can be due to camera motion,
object motion, or both. To separate object morion from camera motion, images are aligned at the background. Since
background is static, once video frames are aligned at the background, only motion of objects remains, facilitating
detection of moving objects. Plates (a) and (b) show two video frames taken moments apart by a moving platform.
Registration of the images is shown in plate (c). The green and blue bands in image (c) are the same as the green
and blue bands in image (a), and the red band in image (c) is the same as the red band in image (b) after it is
resampled to align with image (a). The combined image shows the static background in the natural color of the scene,
while moving objects (cars and tree branches) in the scene appear as red or light blue regions. The light blue cars in
the bottom-left part of image (c) show cars in image (a) that have moved out of view in image (b).