NRC Research Associate Programs
Fellowships Office
Policy and Global Affairs

Participating Agencies

  sign inOpen Printer View

Opportunity at Air Force Research Laboratory (AFRL)

Real-Time Multisensor Image Registration of Wide Area Streaming Data


Sensors Directorate, RY/Sensors Division

RO# Location
13.35.01.B7373 Wright-Patterson AFB, OH 454337542


name email phone
Kevin L Priddy 937-656-6704


The primary objective of this research is to perform real-time image processing on wide-area motion imagery to develop and implement algorithms, which support multi-sensor image registration, automated tracking, data compression, and image understanding.

The image processing chain is impacted by image data capture, data rate, image compression, and effects the chain may have on other processing such as tracking and track formation. Tracking of dismounts and vehicles in cluttered urban settings place a strain on the current state-of-the-art in registration, considering that registration needs to be performed in near real time in order to meet system constraints.

One key aspect of the research will be to find a transformation that matches two or more input images to a reference image taken at different times, from different sensors types, and/or from different aspect angles. A transformation must be found so that the points in one image can be related to the corresponding pixels in the other image.

Many military systems which evaluate images require the registration of images, or a closely related operation, as an intermediate step. Image registration is often necessary for the following problems: integrating information taken from different sensors, finding changes in images taken at different times under different conditions, inferring three-dimensional information from images in which either the sensor or the targets in the scene have moved, and for object recognition. In many military applications, the images need to be aligned with one another so that differences can be detected. An example application arises when the geospatial location of the pixels in the reference image may be known making it possible to geo-locate objects or targets in the input images (that are not found in the reference image) in geospatial coordinates. Other examples of military systems where image registration is a significant component include matching a target with a real-time image of a scene for target recognition and matching stereo images to recover shape for autonomous navigation.

Over the years, a broad range of techniques have been developed for various types of data and problems. These techniques have been studied for military applications, resulting in a large body of research. Image registration methods can be viewed as different combinations of the following four components: features space, transformation space, similarity metrics, and search strategies.

The goal of our research is to gather knowledge about the characteristics of each type of algorithm to affect the choice of feature space, search space, similarity measure, and search strategy, which will make up the final technique. We wish to understand the merits and relationships between the wide varieties of existing techniques to assist in the selection of the most suitable technique for a specific problem. We also wish to develop methods that work well with different sensor types such as synthetic aperture radar and infrared sensors as registration of images under differing phenomenology is the way military systems are moving in the near future.


Wide are motion imagery; Optimal feature selection; Change detection; Real-time image registration; Similarity metrics; Pixelpedia; Exquisite geo-registration; Automated tracking; Multisensor registration;


Citizenship:  Open to U.S. citizens
Level:  Open to Postdoctoral and Senior applicants


Base Stipend Travel Allotment Supplementation
$76,542.00 $4,000.00

$3,000 Supplement for Doctorates in Engineering & Computer Science

Experience Supplement:
Postdoctoral and Senior Associates will receive an appropriately higher stipend based on the number of years of experience past their PhD.

Copyright © 2022. National Academy of Sciences. All rights reserved.Terms of Use and Privacy Policy